WO2025067077A1 - Channel state feedback method and communication apparatus - Google Patents

Abstract

The present application provides a channel state feedback method and a communication apparatus. The channel state feedback method comprises: an encoder compressing M pieces of channel information to obtain a first sequence, wherein the M pieces of channel information are part or all of L pieces of measured channel information, L is less than or equal to N, N is the number of pieces of channel information determined on the basis of reference signals on K antenna port groups, N is a positive integer, and the first sequence consists of X joint feedback quantities corresponding to the N pieces of channel information; determining a second sequence on the basis of the first sequence, the second sequence consisting of Y joint feedback quantities corresponding to the M pieces of channel information; and sending the second sequence to a decoder. A terminal device can perform partial measurement and partial compression and feedback on a plurality of analog beams within the maximum analog beam range, avoiding the storage/switching overhead of AI models and reducing the complexity of implementation.

Description

Method and communication device for feeding back channel status

This application claims priority to a Chinese patent application filed with the State Intellectual Property Office of China on September 28, 2023, with application number 202311292016.X and invention name “Method and communication device for feedback of channel status”, the entire contents of which are incorporated by reference in this application.

Technical Field

The present application relates to the field of communication technology, and more specifically, to a method and a communication device for feeding back channel status.

Background Art

In a communication system, network equipment needs to obtain downlink channel information fed back by terminal equipment in order to perform precoding and other processing on downlink data. In the current feedback mechanism, network equipment can send a reference signal to the terminal equipment, the terminal equipment determines the channel based on the reference signal, and then feeds back the corresponding channel state information (CSI), which may include, for example, precoding information, the number of transmission streams supported by the channel (i.e., the rank of the channel), and the channel quality indicator (CQI), which is used to feed back the modulation coding scheme (MCS) recommended by the terminal equipment under the current channel quality.

When the terminal device reports, for example in a multiple-input multiple-output (MIMO) system, in order to save the feedback overhead of the precoding matrix, the terminal device can compress the precoding information before reporting. For example, the network device/terminal device can design and train an autoencoder based on an AI model to perform space-frequency dual-domain compression.

In high-frequency communication systems, network devices use different analog beam weights to send reference signals, and terminal devices measure the reference signals separately and feedback the measurement results of each reference signal. For terminal devices with different reporting capabilities, network devices need to be configured with different AI models to support different reporting capabilities, which increases the storage/switching overhead of network devices and terminal devices.

Therefore, there is an urgent need for a method for feeding back channel status in order to reduce the storage/switching overhead of network devices and terminal devices.

Summary of the invention

The present application provides a method and a communication device for feeding back channel status, which can reduce the storage/switching overhead of network equipment and terminal equipment.

In a first aspect, a method for feeding back a channel status is provided. The method may be executed by a terminal device, or may be executed by an encoder configured in the terminal device, and the present application does not limit this.

The method comprises: compressing M channel information to obtain a first sequence, wherein the M channel information is part or all of L measured channel information, L is less than or equal to N, N is the number of channel information determined based on reference signals on K antenna port groups, the first sequence is X joint feedback amounts corresponding to the N channel information, M, L and N are positive integers; determining a second sequence according to the first sequence, the second sequence is Y joint feedback amounts corresponding to the M channel information; and sending the second sequence to a decoder.

Among them, N channel information corresponds to N simulation beams, and N can also be understood as the maximum number of simulation beams.

The N simulated beams are different from each other, and there is an overlapping area in the coverage range of the N simulated beams.

In the present application, the network device and the terminal device may predefine or predetermine the maximum number of simulated beams N and the maximum feedback overhead X for joint feedback.

It can be understood that the terminal device can measure L channel information and compress and feedback M of the channel information.

Based on the above technical solution, the terminal device can perform partial measurement and partial compression feedback on multiple simulated beams within the maximum simulated beam range, avoiding the storage/switching overhead of the AI model and reducing the complexity of implementation.

In combination with the first aspect, in certain implementations of the first aspect, when the first sequence or the second sequence is a sequence before quantization, the joint feedback amount is the length of the first sequence or the second sequence, or, when the first sequence or the second sequence is a sequence after quantization, the joint feedback amount is the number of bits of the first sequence or the second sequence.

In combination with the first aspect, in a possible implementation method, the correspondence between the stacking positions of the N channel information at the encoder input end and the stacking positions of the M channel information at the encoder input end is determined; and Y joint feedback amounts corresponding to the M channel information are determined based on the correspondence.

In this technical solution, the beam position correspondence between the partial feedback amount and the full feedback amount at the encoder input end is defined. The relationship can determine the matrix of partial feedback amounts corresponding to the M channel information from the matrix of the full feedback amount output from the encoder output end, thereby realizing compression and feedback of partial channel information.

In combination with the first aspect, in a possible implementation manner, the first sequence includes N first features and O second features, the N first features correspond to the N channel information, the first features indicate a specific feature of each channel information, and the O second features indicate a common feature of the N channel information, and determining Y joint feedback amounts corresponding to the M channel information according to the corresponding relationship includes: determining M first features according to the corresponding relationship and the N first features, the M first features corresponding to the M channel information; determining P second features corresponding to the M channel information according to the corresponding relationship and the O second features, where P is less than or equal to O, and O and P are positive integers; and determining Y joint feedback amounts corresponding to the M channel information according to the M first features and the P second features.

In this technical solution, the common features and unique features in N channel information are defined separately, so that separable joint feedback can be achieved. Through partial feedback, feedback of channel information under different numbers of simulated beams and different feedback overheads is supported.

In combination with the first aspect, in a possible implementation, the positions of the N first features in the first sequence correspond to the positions of the M first features in the second sequence, and the positions of the O second features in the first sequence correspond to the positions of the P second features in the second sequence.

In this technical solution, the corresponding relationship between different simulated beam characteristics and the position of the total feedback amount is defined.

In combination with the first aspect, in a possible implementation, the N first features and the O second features include a feature principal component and a feature supplement component, the feature principal component is used to complete the reconstruction of the channel information, and the feature supplement component is used to supplement the accuracy of the channel information.

In this technical solution, feedback of different accuracies is achieved through the principal component and supplementary component corresponding to the feature, thereby increasing the flexibility of the feedback.

In combination with the first aspect, in one possible implementation, each of the M first features includes the feature principal component, some or all of the M first features include the feature supplementary component, each of the P second features includes the feature principal component, and some or all of the P second features include the feature supplementary component.

In this technical solution, among the M channel information that are compressed and fed back, different channel information can be fed back with different precisions, thus achieving flexible feedback.

In combination with the first aspect, in a possible implementation, the characteristic principal component of each first feature among the N first features has a corresponding relationship with the characteristic principal components of some or all of the first features among the M first features; the supplementary component of each first feature among the N first features has a corresponding relationship with the supplementary components of some or all of the M first features; the characteristic principal component of each second feature among the O second features has a corresponding relationship with the characteristic principal component of each second feature among the P second features, and the characteristic supplementary component of each second feature among the O second features has a corresponding relationship with the characteristic supplementary component of each second feature among the P second features.

In this technical solution, among the M channel information of compressed feedback, the features corresponding to each channel information have a corresponding relationship with the features corresponding to the N channel information.

In combination with the first aspect, in a possible implementation manner, accuracy levels corresponding to the M channel information are determined.

In combination with the first aspect, in a possible implementation manner, the M channel information or the accuracy level corresponding to the M channel information is determined by a network device, or the M channel information or the accuracy level corresponding to the M channel information is determined by a terminal device.

In combination with the first aspect, in a possible implementation method, the M channel information or the accuracy level corresponding to the M channel information is determined by the network device based on the priority information of the L channel information; or, the M channel information or the accuracy level corresponding to the M channel information is determined by the terminal device based on the measurement results of the L channel information and/or the priority information of the L channel information.

In this technical solution, the feedback channel information and accuracy are determined according to the priority, thereby ensuring the efficiency and reliability of multi-beam reporting.

In combination with the first aspect, in a possible implementation method, when the M channel information are determined by the network device, the correspondence between the M channel information and the L channel information is sent; when the precision categories corresponding to the M channel information are determined by the network device, the precision categories corresponding to the M channel information are sent.

In combination with the first aspect, in a possible implementation manner, the encoder is used in a terminal device.

In a second aspect, a method for feeding back channel status is provided. The method may be executed by a network device, or may be executed by a decoder configured in the network device, and the present application does not limit this.

The method comprises: receiving a second sequence, wherein the second sequence is Y joint feedback amounts corresponding to M channel information, wherein the M channel information is part or all of L measured channel information, L is less than or equal to N, and N is a reference signal decision based on K antenna port groups. The method comprises the following steps: determining a first sequence according to the second sequence, wherein the first sequence is X joint feedback amounts corresponding to the N channel information; and reconstructing the first sequence to obtain the M channel information.

Based on the above technical solution, the network device can reconstruct the joint feedback amount of part of the channel information fed back by the terminal device to obtain M channel information, thereby avoiding the storage/switching overhead of the AI model and reducing the complexity of the implementation.

In combination with the second aspect, in a possible implementation manner, when the first sequence or the second sequence is a sequence before quantization, the joint feedback amount is the length of the first sequence or the second sequence, or, when the first sequence or the second sequence is a sequence after quantization, the joint feedback amount is the number of bits of the first sequence or the second sequence.

In combination with the second aspect, in a possible implementation method, the correspondence between the stacking positions of the M channel information at the decoder input end and the stacking positions of the N channel information at the decoder input end is determined; and X joint feedback amounts corresponding to the N channel information are determined according to the correspondence.

In this technical solution, the beam position correspondence between the partial feedback amount and the full feedback amount at the input end of the decoder side is defined. Based on this correspondence, the matrix input decoder of the full feedback amount can be determined according to the matrix of the partial feedback amount corresponding to the M channel information of the terminal device, thereby realizing the reconstruction of partial channel information.

In combination with the second aspect, in a possible implementation manner, the second sequence includes M first features and P second features, the M first features correspond to the M channel information, the first feature indicates a specific feature of each channel information, and the second feature indicates a common feature of the M channel information, and determining X joint feedback amounts corresponding to the N channel information according to the corresponding relationship includes: determining N first features according to the corresponding relationship and the M first features, the N first features corresponding to the N channel information; determining O second features corresponding to the N channel information according to the corresponding relationship and the P second features, where P is less than or equal to O; and determining X joint feedback amounts corresponding to the N channel information according to the N first features and the O second features.

In combination with the second aspect, in a possible implementation, the positions of the M first features in the second sequence correspond to the positions of the N first features in the first sequence, and the positions of the P second features in the second sequence correspond to the positions of the O second features in the first sequence.

In combination with the second aspect, in a possible implementation, the M first features and the P second features include a feature principal component and a feature supplement component, the feature principal component is used to complete the reconstruction of the channel information, and the feature supplement component is used to supplement the accuracy of the channel information.

In combination with the second aspect, in one possible implementation, each of the N first features includes the feature principal component, some or all of the N first features include the feature supplementary component, each of the O second features includes the feature principal component, and some or all of the O second features include the feature supplementary component.

In this technical solution, among the M channel information that are compressed and fed back, different channel information is fed back with different precisions, and the decoder can reconstruct the channel information according to the different precisions to obtain channel information with different precisions.

In combination with the second aspect, in a possible implementation, the characteristic principal component of each first feature among the N first features has a corresponding relationship with the characteristic principal components of some or all of the first features among the M first features; the supplementary component of each first feature among the N first features has a corresponding relationship with the supplementary components of some or all of the M first features; the characteristic principal component of each second feature among the O second features has a corresponding relationship with the characteristic principal component of each second feature among the P second features, and the characteristic supplementary component of each second feature among the O second features has a corresponding relationship with the characteristic supplementary component of each second feature among the P second features.

In combination with the second aspect, in a possible implementation manner, the accuracy levels corresponding to the M channel information are determined.

In combination with the second aspect, in a possible implementation manner, the M channel information or the accuracy level corresponding to the M channel information is determined by a network device, or the M channel information or the accuracy level corresponding to the M channel information is determined by a terminal device.

In combination with the second aspect, in a possible implementation method, the M channel information or the accuracy level corresponding to the M channel information is determined by the network device based on the priority information of the L channel information; or, the M simulated beams or the accuracy level corresponding to the M simulated beams is determined by the terminal device based on the measurement results of the L channel information and/or the priority information of the L channel information.

In combination with the second aspect, in a possible implementation method, when the M channel information is determined by the terminal device, the correspondence between the M channel information and the L channel information is sent; when the precision categories corresponding to the M channel information are determined by the terminal device, the precision categories corresponding to the M channel information are sent.

In combination with the second aspect, in a possible implementation manner, determining a corresponding relationship between a stacking position of the M channel information at the decoder input end and a stacking position of the N channel information at the decoder input end; determining the M channel information according to the corresponding relationship; information.

In this technical solution, the network device can determine the output matrix corresponding to M channel information from the output matrix of the full feedback amount according to the beam position correspondence between the partial feedback amount and the full feedback amount at the decoder side input end.

In conjunction with the second aspect, in a possible implementation manner, the decoder is used in a network device.

In a third aspect, a communication device is provided. The device may be a terminal device, or may be an encoder configured in the terminal device, which is not limited in the present application.

The device includes: a processing unit, used for compressing M channel information to obtain a first sequence, wherein the M channel information is part or all of L measured channel information, L is less than or equal to N, N is the number of channel information determined based on reference signals on K antenna port groups, N is a positive integer, and the first sequence is X joint feedback amounts corresponding to the N channel information; the processing unit is also used for determining a second sequence according to the first sequence, wherein the second sequence is Y joint feedback amounts corresponding to the M channel information; and a transceiver unit is used for sending the second sequence to a decoder.

Among them, N channel information corresponds to N simulation beams, and N can also be understood as the maximum number of simulation beams.

The N simulated beams are different from each other, and there is an overlapping area in the coverage range of the N simulated beams.

In the present application, the network device and the terminal device may predefine or predetermine the maximum number of simulated beams N and the maximum feedback overhead X for joint feedback.

It can be understood that the terminal device can measure L channel information and compress and feedback M of the channel information.

Based on the above technical solution, the terminal device can perform partial measurement and partial compression feedback on multiple simulated beams within the maximum simulated beam range, avoiding the storage/switching overhead of the AI model and reducing the complexity of implementation.

In combination with the third aspect, in certain implementations of the third aspect, when the first sequence or the second sequence is a sequence before quantization, the joint feedback amount is the length of the first sequence or the second sequence, or, when the first sequence or the second sequence is a sequence after quantization, the joint feedback amount is the number of bits of the first sequence or the second sequence.

In combination with the third aspect, in a possible implementation method, the processing unit is also used to determine the correspondence between the stacking positions of the N channel information at the encoder input end and the stacking positions of the M channel information at the encoder input end; the processing unit is also used to determine Y joint feedback amounts corresponding to the M channel information based on the correspondence.

In this technical solution, the beam position correspondence between the partial feedback amount and the full feedback amount at the encoder input end is defined. Based on this correspondence, the matrix of partial feedback amounts corresponding to M channel information can be determined from the matrix of full feedback amounts output from the encoder output end, thereby realizing compression and feedback of partial channel information.

In combination with the third aspect, in a possible implementation manner, the first sequence includes N first features and O second features, the N first features correspond to the N channel information, the first feature indicates a specific feature of each channel information, and the O second features indicate a common feature of the N channel information, and determining Y joint feedback amounts corresponding to the M channel information according to the corresponding relationship includes: determining M first features according to the corresponding relationship and the N first features, the M first features corresponding to the M channel information; determining P second features corresponding to the M channel information according to the corresponding relationship and the O second features, where P is less than or equal to O; and determining Y joint feedback amounts corresponding to the M channel information according to the M first features and the P second features.

In this technical solution, the common features and unique features in N channel information are defined separately, so that separable joint feedback can be achieved. Through partial feedback, feedback of channel information under different numbers of simulated beams and different feedback overheads is supported.

In combination with the third aspect, in a possible implementation, the positions of the N first features in the first sequence correspond to the positions of the M first features in the second sequence, and the positions of the O second features in the first sequence correspond to the positions of the P second features in the second sequence.

In this technical solution, the corresponding relationship between different simulated beam characteristics and the position of the total feedback amount is defined.

In combination with the third aspect, in a possible implementation, the N first features and the O second features include a feature principal component and a feature supplement component, the feature principal component is used to complete the reconstruction of the channel information, and the feature supplement component is used to supplement the accuracy of the channel information.

In this technical solution, feedback of different accuracies is achieved through the principal component and supplementary component corresponding to the feature, thereby increasing the flexibility of the feedback.

In combination with the third aspect, in one possible implementation, each of the M first features includes the feature principal component, some or all of the M first features include the feature supplementary component, each of the P second features includes the feature principal component, and some or all of the P second features include the feature supplementary component.

In this technical solution, among the M channel information compressed and fed back, different channel information can be fed back with different precisions, thus achieving Flexible feedback.

In combination with the third aspect, in a possible implementation, the characteristic principal component of each first feature among the N first features has a corresponding relationship with the characteristic principal components of some or all of the first features among the M first features; the supplementary component of each first feature among the N first features has a corresponding relationship with the supplementary components of some or all of the M first features; the characteristic principal component of each second feature among the O second features has a corresponding relationship with the characteristic principal component of each second feature among the P second features, and the characteristic supplementary component of each second feature among the O second features has a corresponding relationship with the characteristic supplementary component of each second feature among the P second features.

In this technical solution, among the M channel information of compressed feedback, the features corresponding to each channel information have a corresponding relationship with the features corresponding to the N channel information.

In combination with the third aspect, in a possible implementation manner, the processing unit is further used to determine the accuracy levels corresponding to the M channel information.

In combination with the third aspect, in a possible implementation, the M channel information or the accuracy level corresponding to the M channel information is determined by a network device, or the M channel information or the accuracy level corresponding to the M channel information is determined by a terminal device.

In combination with the third aspect, in a possible implementation method, the M channel information or the accuracy level corresponding to the M channel information is determined by the network device based on the priority information of the L channel information; or, the M channel information or the accuracy level corresponding to the M channel information is determined by the terminal device based on the measurement results of the L channel information and/or the priority information of the L channel information.

In this technical solution, the feedback channel information and accuracy are determined according to the priority, thereby ensuring the efficiency and reliability of multi-beam reporting.

In combination with the third aspect, in a possible implementation method, when the M channel information is determined by the network device, the transceiver unit is also used to send the correspondence between the M channel information and the L channel information; when the accuracy category corresponding to the M channel information is determined by the network device, the transceiver unit is also used to send the accuracy categories corresponding to the M channel information respectively.

In conjunction with the third aspect, in a possible implementation manner, the encoder is used in a terminal device.

In a fourth aspect, a communication device is provided. The device may be a network device, or may be a decoder configured in a network device, which is not limited in the present application.

The method includes: a transceiver unit, used to receive a second sequence, where the second sequence is Y joint feedback amounts corresponding to M channel information, where the M channel information is part or all of L measured channel information, where L is less than or equal to N, where N is the number of channel information determined based on reference signals on K antenna port groups, and N is a positive integer; a processing unit, used to determine a first sequence according to the second sequence, where the first sequence is X joint feedback amounts corresponding to the N channel information; and the processing unit is further used to reconstruct the first sequence to obtain the M channel information.

Based on the above technical solution, the network device can reconstruct the joint feedback amount of part of the channel information fed back by the terminal device to obtain M channel information, thereby avoiding the storage/switching overhead of the AI model and reducing the complexity of the implementation.

In combination with the fourth aspect, in a possible implementation manner, when the first sequence or the second sequence is a sequence before quantization, the joint feedback amount is the length of the first sequence or the second sequence, or, when the first sequence or the second sequence is a sequence after quantization, the joint feedback amount is the number of bits of the first sequence or the second sequence.

In combination with the fourth aspect, in a possible implementation method, the processing unit is also used to determine the correspondence between the stacking position of the M channel information at the decoder input end and the stacking position of the N channel information at the decoder input end; the processing unit is also used to determine X joint feedback amounts corresponding to the N channel information based on the corresponding relationship.

In this technical solution, the beam position correspondence between the partial feedback amount and the full feedback amount at the input end of the decoder side is defined. Based on this correspondence, the matrix input decoder of the full feedback amount can be determined according to the matrix of the partial feedback amount corresponding to the M channel information of the terminal device, thereby realizing the reconstruction of partial channel information.

In combination with the fourth aspect, in a possible implementation manner, the second sequence includes M first features and P second features, the M first features correspond to the M channel information, the first feature indicates a specific feature of each channel information, and the second feature indicates a common feature of the M channel information, and determining X joint feedback amounts corresponding to the N channel information according to the corresponding relationship includes: determining N first features according to the corresponding relationship and the M first features, the N first features corresponding to the N channel information; determining O second features corresponding to the N channel information according to the corresponding relationship and the P second features, where P is less than or equal to O; and determining X joint feedback amounts corresponding to the N channel information according to the N first features and the O second features.

In combination with the fourth aspect, in a possible implementation, the positions of the M first features in the second sequence correspond to the positions of the N first features in the first sequence, and the positions of the P second features in the second sequence correspond to the positions of the O second features in the first sequence.

In combination with the fourth aspect, in a possible implementation, the M first features and the P second features include a feature principal component and a feature supplement component, the feature principal component is used to complete the reconstruction of the channel information, and the feature supplement component is used to supplement the accuracy of the channel information.

In combination with the fourth aspect, in a possible implementation, each of the N first features includes the feature principal component, some or all of the N first features include the feature supplementary component, each of the O second features includes the feature principal component, and some or all of the O second features include the feature supplementary component.

In this technical solution, among the M channel information that are compressed and fed back, different channel information is fed back with different precisions, and the decoder can reconstruct the channel information according to the different precisions to obtain channel information with different precisions.

In combination with the fourth aspect, in a possible implementation method, the characteristic principal component of each first feature among the N first features has a corresponding relationship with the characteristic principal components of some or all of the first features among the M first features; the supplementary component of each first feature among the N first features has a corresponding relationship with the supplementary components of some or all of the M first features; the characteristic principal component of each second feature among the O second features has a corresponding relationship with the characteristic principal component of each second feature among the P second features, and the characteristic supplementary component of each second feature among the O second features has a corresponding relationship with the characteristic supplementary component of each second feature among the P second features.

In combination with the fourth aspect, in a possible implementation manner, the processing unit is further used to determine the accuracy levels corresponding to the M channel information.

In combination with the fourth aspect, in a possible implementation manner, the M channel information or the accuracy level corresponding to the M channel information is determined by a network device, or the M channel information or the accuracy level corresponding to the M channel information is determined by a terminal device.

In combination with the fourth aspect, in a possible implementation method, the M channel information or the accuracy level corresponding to the M channel information is determined by the network device based on the priority information of the L channel information; or, the M simulated beams or the accuracy level corresponding to the M simulated beams is determined by the terminal device based on the measurement results of the L channel information and/or the priority information of the L channel information.

In combination with the fourth aspect, in a possible implementation method, when the M channel information is determined by the terminal device, the transceiver unit is also used to send the correspondence between the M channel information and the L channel information; when the accuracy category corresponding to the M channel information is determined by the terminal device, the transceiver unit is also used to send the accuracy categories corresponding to the M channel information respectively.

In combination with the fourth aspect, in a possible implementation method, the processing unit is also used to determine the correspondence between the stacking positions of the M channel information at the decoder input end and the stacking positions of the N channel information at the decoder input end; the processing unit is also used to determine the M channel information based on the correspondence.

In this technical solution, the network device can determine the output matrix corresponding to M channel information from the output matrix of the full feedback amount according to the beam position correspondence between the partial feedback amount and the full feedback amount at the decoder side input end.

In conjunction with the fourth aspect, in a possible implementation manner, the decoder is used in a network device.

In a fifth aspect, a communication device is provided, which is used to execute the method provided in the first aspect or the second aspect. Specifically, the communication device may include a unit and/or module, such as a processing unit and/or a communication unit, for executing the method provided in any one of the above implementations of the first aspect or the second aspect.

In one implementation, the communication device includes a communication unit and a processing unit, the communication unit may be a transceiver, or an input/output interface; the processing unit may be at least one processor. Optionally, the transceiver may be a transceiver circuit. Optionally, the input/output interface may be an input/output circuit.

In another implementation, the communication device is a chip, a chip system or a circuit in a network device. When the NTN positioning device is a chip, a chip system or a circuit in a network device, the communication unit may be an input/output interface, an interface circuit, an output circuit, an input circuit, a pin or a related circuit on the chip, the chip system or the circuit; the processing unit may be at least one processor, a processing circuit or a logic circuit.

In a sixth aspect, a communication device is provided, comprising a processor and, optionally, a memory, wherein the processor is used to control a transceiver to send and receive signals, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the sending device executes a method in any possible implementation of the first aspect or the second aspect mentioned above.

Optionally, the processor is one or more and the memory is one or more.

Optionally, the memory may be integrated with the processor, or the memory may be provided separately from the processor.

Optionally, the first device further includes a transceiver, which may specifically be a transmitter (transmitter) and a receiver (receiver).

In a seventh aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program or code, and when the computer program or code is executed on a computer, the computer executes any possible implementation method of the first aspect or the second aspect. The method in the formula.

In an eighth aspect, a chip is provided, comprising at least one processor, wherein the at least one processor is coupled to a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a sending device equipped with the chip system executes a method in any possible implementation of the first aspect or the second aspect mentioned above.

The chip may include an input circuit or interface for sending information or data, and an output circuit or interface for receiving information or data.

In a ninth aspect, a computer program product is provided, which includes: a computer program code, which, when the computer program code is executed by a sending device, executes a method in any possible implementation of the first aspect or the second aspect.

The beneficial effects of the third to ninth aspects can refer to the beneficial effects of the first to second aspects and will not be elaborated on again.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic diagram of a communication system applicable to an embodiment of the present application.

FIG. 2 is a schematic diagram of another communication system applicable to an embodiment of the present application.

FIG. 3 is a schematic diagram of a possible application framework applicable to an embodiment of the present application.

FIG. 4 is a schematic diagram of a possible application framework applicable to an embodiment of the present application.

FIG5 is a schematic diagram of CSI compression feedback applicable to an embodiment of the present application.

FIG. 6 is a schematic diagram of a hardware architecture 600 applicable to an embodiment of the present application.

FIG. 7 is a schematic flowchart of a method 700 for feeding back channel information applicable to an embodiment of the present application.

FIG8 is a schematic diagram of an AI model design applicable to an embodiment of the present application.

FIG. 9 is a schematic diagram of a stacking method of N simulated beam channel information at input and output ends applicable to an embodiment of the present application.

FIG. 10 is a schematic diagram of a detachable joint feedback applicable to an embodiment of the present application.

FIG. 11 is a schematic flowchart of a method 1100 for feeding back channel information applicable to an embodiment of the present application.

FIG. 12 is a schematic diagram of a compression feedback process applicable to an embodiment of the present application.

FIG13 is a structural block diagram of a communication device applicable to an embodiment of the present application.

FIG. 14 is a structural block diagram of a communication device applicable to an embodiment of the present application.

DETAILED DESCRIPTION

The technical solution in this application will be described below in conjunction with the accompanying drawings.

The technical solution provided in this application can be applied to various communication systems, such as: the fifth generation (5th generation, 5G) or new radio (new radio, NR) system, long term evolution (long term evolution, LTE) system, LTE frequency division duplex (frequency division duplex, FDD) system, LTE time division duplex (time division duplex, TDD) system, etc. The technical solution provided in this application can also be applied to future communication systems, such as the sixth generation mobile communication system. The technical solution provided in this application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (machine type communication, MTC), and Internet of things (IoT) communication system or other communication systems.

The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

First, a communication system applicable to the present application is briefly introduced as follows.

FIG1 is a schematic diagram of a communication system applicable to a communication method of an embodiment of the present application. As shown in FIG1 , the communication system 100 may include at least one network device, such as the network device 110 shown in FIG1 ; the communication system 100 may also include at least one terminal device, such as the terminal device 120 and the terminal device 130 shown in FIG1 . The network device 110 and the terminal device (such as the terminal device 120 and the terminal device 130) may communicate via a wireless link. The communication devices in the communication system, for example, the network device 110 and the terminal device 120, may communicate via a multi-antenna technology.

It should be understood that FIG. 1 is only a simplified schematic diagram for ease of understanding, and the communication system may also include other network devices or other terminal devices, which are not shown in FIG. 1 .

It should also be understood that the communication system 100 shown in FIG. 1 is only an example of an application scenario of the embodiment of the present application, and the present application can also be applied to communication between any two devices, for example, communication between terminal devices and terminal devices, and communication between network devices and network devices. Communication between devices.

FIG2 is a schematic diagram of another communication system applicable to an embodiment of the present application. Compared with the communication system 100 shown in FIG1 , the communication system 200 shown in FIG2 further includes an AI network element 140. The AI network element 140 is used to perform AI-related operations, such as building a training data set or training an AI model.

In one possible implementation, the network device 110 may send data related to the training of the AI model to the AI network element 140, which constructs a training data set and trains the AI model. For example, the data related to the training of the AI model may include data reported by the terminal device. The AI network element 140 may send the results of the operations related to the AI model to the network device 110, and forward them to the terminal device through the network device 110. For example, the results of the operations related to the AI model may include at least one of the following: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a part of the trained AI model may be deployed on the network device 110, and another part may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Alternatively, the trained AI model may be deployed on the terminal device.

It should be understood that FIG. 2 only illustrates the example of the AI network element 140 being directly connected to the network device 110. In other scenarios, the AI network element 140 may also be connected to the terminal device. Alternatively, the AI network element 140 may be connected to the network device 110 and the terminal device at the same time. Alternatively, the AI network element 140 may also be connected to the network device 110 through a third-party network element. The embodiment of the present application does not limit the connection relationship between the AI network element and other network elements.

The AI network element 140 may also be provided as a module in a network device and/or a terminal device, for example, in the network device 110 or the terminal device shown in FIG. 1 .

It should be noted that FIG. 1 and FIG. 2 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and/or wireless backhaul devices, which are not shown in FIG. 1 and FIG. 2. In practical applications, the communication system may include multiple network devices and may also include multiple terminal devices. The embodiment of the present application does not limit the number of network devices and terminal devices included in the communication system.

In the embodiment of the present application, the network device is an access device for the terminal device to access the mobile communication system by wireless means, for example, including an access network (AN) device, such as a base station. The network device may also refer to a device that communicates with the terminal device at the air interface. The network device may include an evolved Node B (also referred to as eNB or e-NodeB) in an LTE system or an advanced long term evolution (LTE-A); the network device may also include a next generation node B (gNB) in a 5G NR system; or, the network device may also include an access node in a wireless fidelity (Wi-Fi) system, etc.; or the network device may be a relay station, an on-board device, and a future evolved public land mobile network (PLMN) device, a device in a D2D network, a device in a machine to machine (M2M) network, a device in an Internet of Things (IoT) network, or a network device in a PLMN network, etc. The embodiments of the present application do not limit the specific technology and specific device form adopted by the network device.

In addition, the base station in the embodiment of the present application may include a centralized unit (CU) and a distributed unit (DU), and multiple DUs may be centrally controlled by one CU. CU and DU may be divided according to the protocol layer functions of the wireless network they possess, for example, the functions of the packet data convergence protocol (PDCP) layer and the protocol layers above are set in the CU, and the functions of the protocol layers below the PDCP, such as the radio link control (RLC) layer and the medium access control (MAC) layer, are set in the DU. It should be noted that this division of the protocol layer is only an example, and it can also be divided in other protocol layers. The radio frequency device can be remote and not placed in the DU, or it can be integrated in the DU, or part of it can be remote and part of it can be integrated in the DU, and the embodiment of the present application does not impose any restrictions. In addition, in some embodiments, the control plane (CP) and the user plane (UP) of the CU can also be separated and divided into different entities for implementation, namely the control plane CU entity (CU-CP entity) and the user plane CU entity (CU-UP entity). In this network architecture, the signaling generated by the CU can be sent to the terminal device through the DU, or the signaling generated by the UE can be sent to the CU through the DU. The DU can directly encapsulate the signaling through the protocol layer and transparently transmit it to the UE or CU without parsing it. In this network architecture, the CU is divided into a network device on the radio access network (RAN) side. In addition, the CU can also be divided as a network device on the core network (CN) side, and this application does not limit this.

The access network device may also be a server, etc. For example, the network device in the vehicle to everything (V2X) technology may be a road side unit (RSU). The following describes the access network device by taking a base station as an example. The base station may communicate with the terminal device, or may communicate with the terminal device through a relay station. The terminal device may communicate with multiple base stations in different access technologies.

In the embodiment of the present application, the core network equipment is used to implement functions such as mobility management, data processing, session management, policy and billing. The names of the devices that implement the core network functions in systems with different access technologies may be different, and the embodiment of the present application does not limit this. Taking the 5G system as an example, the core network equipment includes: access and mobility management function (AMF), session management, policy and billing. Management function (session management function, SMF), policy control function (policy control function, PCF) or user plane function (user plane function, UPF), etc.

In the embodiment of the present application, the terminal device is a device with wireless transceiver function, which can send signals to the network device or receive signals from the network device. The terminal device may include user equipment (UE), sometimes also referred to as terminal, access station, UE station, remote station, wireless communication equipment, or user device, etc. The terminal device is used to connect people, objects, machines, etc., and can be widely used in various scenarios, such as but not limited to the following scenarios: cellular communication, D2D, V2X, machine-to-machine/machine-type communications (M2M/MTC), Internet of Things (IoT), virtual reality (VR), augmented reality (AR), industrial control, self-driving, remote medical, smart grid, smart furniture, smart office, smart wear, smart transportation, smart city, drone, robot and other scenarios of terminal devices. For example, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a VR terminal, an AR terminal, a wireless terminal in industrial control, a wireless terminal in unmanned driving, a smart speaker in an IoT network, a wireless terminal device in telemedicine, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc. As an example and not a limitation, in an embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be referred to as wearable smart devices or smart wearable devices, etc., which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. The various terminal devices introduced above, if located on a vehicle (for example, placed in a vehicle or installed in a vehicle), can be considered as vehicle-mounted terminal devices, and vehicle-mounted terminal devices are also referred to as on-board units (OBUs). The terminal device of the present application may also be a vehicle-mounted module, vehicle-mounted module, vehicle-mounted component, vehicle-mounted chip or vehicle-mounted unit that is built into the vehicle as one or more components or units. The vehicle can implement the method of the present application through the built-in vehicle-mounted module, vehicle-mounted module, vehicle-mounted component, vehicle-mounted chip or vehicle-mounted unit.

In the embodiment of the present application, the communication device for realizing the function of the network device may be a network device, or may be a device capable of supporting the network device to realize the function, such as a chip system, which may be installed in the network device. In the technical solution provided in the embodiment of the present application, the technical solution provided in the embodiment of the present application is described by taking the device for realizing the function of the network device as an example that the network device is used as the device.

The technical solution provided in the embodiments of the present application can be applied to the fourth generation mobile communication technology (the 4th generation, 4G) system, 5G system, NTN system, vehicle to everything (vehicle to everything, V2X), long-term evolution-vehicle network (LTE-vehicle, LTE-V), vehicle to vehicle (vehicle to vehicle, V2V), vehicle network, machine type communications (Machine Type Communications, MTC), Internet of things (internet of things, IoT), long-term evolution-machine to machine (LTE-machine to machine, LTE-M), machine to machine (machine to machine, M2M), Internet of Things, or future mobile communication systems.

Network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on the water; they can also be deployed on aircraft, balloons and satellites in the air. The scenarios in which network devices and terminal devices are located are not limited in the embodiments of the present application. In addition, terminal devices and network devices can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. The present application does not limit the specific forms of terminal devices and network devices.

In addition, in order to support AI technology in wireless networks, AI nodes may also be introduced into the network.

Optionally, the AI node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment, etc., or the AI node can also be deployed separately, for example, deployed in a location other than any of the above devices, such as a host or cloud server in an over-the-top (OTT) system. The AI node can communicate with other devices in the communication system, and the other devices can be, for example, one or more of the following: network equipment, terminal equipment, or network elements of the core network, etc.

It is understood that the present application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, such as different AI nodes are responsible for different functions.

It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

An AI node can be an AI network element or an AI module.

FIG3 is a schematic diagram of a possible application framework in a communication system. As shown in FIG3 , network elements in the communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. One or more AI modules are provided in one or more of these network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or OAM devices (for clarity, only one is shown in FIG3 ). The access network node may be a separate RAN node, or may include multiple RAN nodes, for example, including a CU and a DU. The CU and/or DU may also be One or more AI modules can be set. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are set in the CU-CP and/or CU-UP.

The AI module is used to implement the corresponding AI function. The AI modules deployed in different network elements may be the same or different. The model of the AI module can implement different functions according to different parameter configurations. The model of the AI module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the biases in the activation function), input parameters (such as the type of input parameters and/or the dimension of input parameters), or output parameters (such as the type of output parameters and/or the dimension of output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

An AI module can have one or more models. A model can be inferred to obtain an output, which includes one parameter or multiple parameters. The learning process, training process, or inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

FIG4 is a schematic diagram of a possible application framework in a communication system. As shown in FIG4 , the communication system includes a RAN intelligent controller (RIC). For example, the RIC may be the AI module shown in FIG3 , which is used to implement AI-related functions. The RIC includes a near-real-time RIC (near-real-time RIC, near-RT RIC) and a non-real-time RIC (non-real-time RIC, Non-RT RIC). Among them, the non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to delay, and the delay of the data may be in the order of seconds. The real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to delay, and the delay of the data is in the order of tens of milliseconds.

The near real-time RIC is used for model training and reasoning. For example, it is used to train an AI model and use the AI model for reasoning. The near real-time RIC can obtain information on the network side and/or the terminal side from a RAN node (e.g., CU, CU-CP, CU-UP, DU, and/or RU) and/or a terminal. This information can be used as training data or reasoning data. Optionally, the near real-time RIC can submit the reasoning results to the RAN node and/or the terminal. Optionally, the reasoning results can be exchanged between the CU and the DU, and/or between the DU and the RU. For example, the near real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

The non-real-time RIC is also used for model training and reasoning. For example, it is used to train an AI model and use the model for reasoning. The non-real-time RIC can obtain information on the network side and/or the terminal side from a RAN node (such as a CU, CU-CP, CU-UP, DU and/or RU) and/or a terminal. The information can be used as training data or reasoning data, and the reasoning results can be submitted to the RAN node and/or the terminal. Optionally, the reasoning results can be exchanged between the CU and the DU, and/or between the DU and the RU. For example, the non-real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

The near real-time RIC and the non-real-time RIC may also be separately set as a network element. Optionally, the near real-time RIC and the non-real-time RIC may also be part of other devices, for example, the near real-time RIC is set in a RAN node (for example, in a CU or DU), and the non-real-time RIC is set in an OAM, a cloud server, a core network device, or other network devices.

In order to facilitate understanding of the technical solutions of the embodiments of the present application, the terms in the embodiments of the present application are explained below.

1. Artificial Intelligence:

Artificial intelligence can be understood as machines having the ability to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. Artificial intelligence can also be understood as the intelligence displayed by machines made by humans. Usually artificial intelligence refers to the technology that presents human intelligence through computer programs. The goals of artificial intelligence include understanding intelligence by building computer programs with symbolic reasoning or inference.

2. Machine learning:

Machine learning is a way to implement artificial intelligence. Machine learning is a method that can give machines the ability to learn, so that machines can complete functions that cannot be completed by direct programming. In a practical sense, machine learning is a method of using data to train a model and then using the model to predict. There are many machine learning methods, such as neural networks (NN), decision trees, support vector machines, etc. Machine learning theory mainly designs and analyzes some algorithms that allow computers to learn automatically. Machine learning algorithms are a type of algorithm that automatically analyzes data to obtain patterns and uses the patterns to predict unknown data.

3. Neural Networks:

Neural network is a specific embodiment of machine learning method. Neural network is a mathematical model that imitates the behavioral characteristics of animal neural network and processes information. The idea of neural network comes from the neuron structure of brain tissue. Each neuron can perform weighted sum operation on its input value, and the result of weighted sum operation is used to generate output through an activation function.

A neural network generally includes a multi-layer structure, each layer of which may include one or more logic judgment units, which may be called neurons. By increasing the depth and/or width of a neural network, the expressive power of the neural network can be improved, providing a basis for complex systems. More powerful information extraction and abstract modeling capabilities. Among them, the depth of the neural network can be understood as the number of layers included in the neural network, and the number of neurons included in each layer can be called the width of the layer. In one possible implementation, the neural network includes an input layer and an output layer. The input layer of the neural network processes the received input through neurons and passes the result to the output layer, and the output layer obtains the output result of the neural network. In another possible implementation, the neural network includes an input layer, a hidden layer, and an output layer. The input layer of the neural network processes the received input through neurons and passes the result to the middle hidden layer, and the hidden layer then passes the calculation result to the output layer or the adjacent hidden layer, and finally the output layer obtains the output result of the neural network. A neural network can include one or more hidden layers connected in sequence without restriction.

During the training process of a neural network, a loss function can be defined. The loss function is used to measure the difference between the predicted value of the model and the true value. During the training process of a neural network, the loss function describes the gap or difference between the output value of the neural network and the ideal target value. The training process of a neural network is to adjust the parameters of the neural network so that the value of the loss function is less than the threshold value or meets the target requirements. Among them, the neural network parameters may include at least one of the following: the number of layers of the neural network, the width, the weight of the neuron, and the parameters in the activation function of the neuron.

4. AI Model:

An AI model is an algorithm or computer program that can implement AI functions. The AI model characterizes the mapping relationship between the input and output of the model, or the AI model is a function model that maps an input of a certain dimension to an output of a certain dimension, and the parameters of the function model can be obtained through machine learning training. For example, f(x)=ax2+b is a quadratic function model, which can be regarded as an AI model. a and b are the parameters of the AI model, and a and b can be obtained through machine learning training. Exemplarily, the AI models mentioned in the embodiments below of the present application are not limited to neural networks, linear regression models, decision tree models, support vector machines (SVM), Bayesian networks, Q learning models or other machine learning (ML) models.

AI model design mainly includes data collection (for example, collecting training data and/or inference data), model training and model inference. It can also include the application of inference results. In the aforementioned data collection link, the data source is used to provide training data sets and inference data. In the model training link, the AI model is obtained by analyzing or training the training data provided by the data source. Learning the AI model through the model training node is equivalent to using the training data to learn the mapping relationship between the input and output of the AI model. In the model inference link, the AI model trained through the model training link is used to perform inference based on the inference data provided by the data source to obtain the inference result. This link can also be understood as: inputting the inference data into the AI model, and obtaining the output through the AI model, which is the inference result. The inference result can indicate: the configuration parameters used (executed) by the execution object, and/or the operation performed by the execution object. The reasoning results are published in the reasoning result application link. For example, the reasoning results can be uniformly planned by the execution (actor) entity. For example, the execution entity can send the reasoning results to one or more execution objects (for example, core network equipment, access network equipment, or terminal equipment, etc.) for execution. For another example, the execution entity can also feedback the performance of the AI model to the data source to facilitate the subsequent update and training of the AI model.

It is understood that the implementation of the AI model can be a hardware circuit, or software, or a combination of software and hardware, without limitation. Non-limiting examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application, or software application, etc.

5. Double-ended model:

The two-end model can also be called a bilateral model, a collaborative model, a dual model, or a two-side model. The two-end model refers to a model composed of multiple sub-models. The multiple sub-models that constitute the model need to match each other. The multiple sub-models can be deployed in different nodes.

The embodiments of the present application involve an encoder for compressing CSI and a decoder for recovering compressed CSI. The encoder and the decoder are used in matching manner, and it can be understood that the encoder and the decoder are matching AI models. An encoder may include one or more AI models, and the decoder matched by the encoder also includes one or more AI models. The number of AI models included in the matching encoder and decoder is the same and corresponds one to one.

In one possible design, a set of matched encoders and decoders can be specifically two parts of the same auto-encoder (AE), for example, as shown in Figure 5. The AE model in which the encoder and decoder are deployed on different nodes is a typical bilateral model. The encoder and decoder of the AE model are usually a jointly trained encoder and decoder. The encoder processes the input V to obtain the processed result z, and the decoder can decode the encoder output z into the desired output V'.

An autoencoder is a neural network for unsupervised learning. Its characteristic is that it uses input data as label data. Therefore, an autoencoder can also be understood as a neural network for self-supervised learning. An autoencoder can be used for data compression and recovery. For example, the encoding in an autoencoder The encoder can compress (encode) data A to obtain data B; the decoder in the autoencoder can decompress (decode) data B to restore data A. Or it can be understood that the decoder is the inverse operation of the encoder.

Exemplarily, the AI model in the embodiment of the present application may include an encoder and a decoder. The encoder and the decoder are used in combination, and it can be understood that the encoder and the decoder are matching AI models. The encoder and the decoder can be deployed on the terminal device and the network device respectively.

Alternatively, the AI model in the embodiment of the present application may be a single-end model, which may be deployed on a terminal device or a network device.

6. Channel status information:

In a communication system (e.g., an LTE communication system or an NR communication system), network equipment needs to decide on the resource, MCS, and precoding configuration of the downlink data channel of the terminal device based on CSI. It can be understood that CSI is a type of channel information, which is information that can reflect channel characteristics and channel quality.

CSI measurement refers to the receiver solving the channel information based on the reference signal sent by the transmitter, that is, estimating the channel information using the channel estimation method. Exemplarily, the reference signal may include one or more of the channel state information reference signal (CSI-RS), synchronization signal/physical broadcast channel block (SSB), sounding reference signal (SRS) or demodulation reference signal (DMRS). CSI-RS, SSB and DMRS can be used to measure downlink CSI. SRS and DMRS can be used to measure uplink CSI.

Taking the FDD communication scenario as an example, in the FDD communication scenario, since the uplink and downlink channels are not reciprocal or cannot be guaranteed, the network equipment usually sends a downlink reference signal to the terminal device, and the terminal device performs channel measurement and interference measurement based on the received downlink reference signal to estimate the downlink CSI. The terminal device generates a CSI report according to the protocol predefined method or the network device configuration method, and feeds it back to the network device so that it can obtain the downlink CSI.

Exemplarily, CSI may include at least one of the following: channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), CSI-RS resource indicator (CRI), layer indicator (LI), reference signal receiving power (RSRP) or signal to interference plus noise ratio (SINR), etc. The signal to interference plus noise ratio may also be called signal to interference plus noise ratio.

Among them, RI is used to indicate the number of downlink transmission layers recommended by the terminal device, CQI is used to indicate the modulation and coding mode supported by the current channel conditions determined by the terminal device, and PMI is used to indicate the precoding recommended by the terminal device. The number of precoding layers indicated by PMI corresponds to RI.

It should be understood that the RI, CQI and PMI indicated in the above CSI report are only recommended values for the terminal device, and the network device may perform downlink transmission according to part or all of the information indicated in the CSI report. Alternatively, the network device may not perform downlink transmission according to the information indicated in the CSI report.

The introduction of AI technology into wireless communication networks has resulted in a CSI feedback method based on the AI model. The terminal device uses the AI model to compress and feedback the CSI, and the network device uses the AI model to restore the compressed CSI. In the AI-based CSI feedback, a sequence (such as a bit sequence) is transmitted, and the overhead is lower than that of traditional CSI feedback.

Taking Figure 5 as an example, Figure 5 shows a schematic diagram of CSI compression feedback of an embodiment of the present application. The encoder in Figure 5 can be a CSI generator, and the decoder can be a CSI reconstructor. The encoder can be deployed in a terminal device, and the decoder can be deployed in a network device. The terminal device can generate CSI feedback information z from the CSI original information V through the encoder. The terminal device reports a CSI report, which may include the CSI feedback information z. The network device can reconstruct the CSI information through the decoder, that is, obtain the CSI recovery information V'.

The CSI original information V may be obtained by the terminal device through CSI measurement. For example, the CSI original information V may include the channel response of the downlink channel or the eigenvector matrix (a matrix composed of eigenvectors) of the downlink channel. The encoder processes the eigenvector matrix of the downlink channel to obtain CSI feedback information z. In other words, the compression and/or quantization operation of the characteristic matrix according to the codebook in the related scheme is replaced by the operation of processing the characteristic matrix by the encoder to obtain CSI feedback information z. The terminal device reports the CSI feedback information z. The network device processes the CSI feedback information z through a decoder to obtain CSI recovery information V'.

The following further illustrates the training process and reasoning process of the AI model in the embodiment of the present application.

The training data used to train the AI model includes training samples and sample labels. For example, the training samples are channel information determined by the terminal device, and the sample labels are real channel information, i.e., true CSI. In the case where the encoder and decoder belong to the same autoencoder, the training data may only include training samples, or the training samples are sample labels.

In the field of wireless communications, the true CSI may be a high-precision CSI.

The specific training process is as follows: the model training node uses the encoder to process the channel information, that is, the training samples, to obtain CSI feedback information, and uses the decoder to process the feedback information to obtain the restored channel information, that is, the CSI restored information. Then, the difference between the CSI restored information and the corresponding sample label is calculated, that is, the value of the loss function, and the parameters of the encoder and decoder are updated according to the value of the loss function so that the restored information The difference between the channel information and the corresponding sample label is minimized, that is, the loss function is minimized. Exemplarily, the loss function can be the minimum mean square error (MSE) or cosine similarity. Repeating the above operation can obtain an encoder and decoder that meet the target requirements. The above model training node can be a terminal device, a network device, or other network elements with AI functions in the communication system.

It should be understood that the above only uses the AI model for CSI compression as an example. In CSI feedback, the AI model can also be used in other scenarios. For example, the AI model can be used for CSI prediction, that is, predicting the channel information at one or more future moments based on the channel information measured at one or more historical moments. The embodiment of the present application does not limit the specific use of the AI model in the CSI feedback scenario.

7. Antenna port:

Antenna port is a logical concept. There is no direct correspondence between an antenna port and a physical antenna. Antenna port is usually associated with reference signal, and its meaning can be understood as a transceiver interface on the channel through which the reference signal passes. For low frequency, an antenna port may correspond to one or more antenna elements, which jointly send reference signals. The receiving end can treat them as a whole without distinguishing these elements. For high frequency systems, antenna port may correspond to a beam. Similarly, the receiving end only needs to regard this beam as an interface without distinguishing each element.

8. Port Group:

The port group refers to the antenna port group/reference signal port group. A port group can contain multiple reference signals. In the present invention, the concept of port group refers to multiple reference signals sent by the base station using the same analog weight/analog beam. Therefore, in the present invention, the base station can use one or more reference signal port groups to measure the channel information under an analog beam.

9. Beam:

A beam is a communication resource. A beam can be a wide beam, a narrow beam, or other types of beams. The technology for forming a beam can be a beamforming technology or other technical means. The beamforming technology can be specifically digital beamforming technology, analog beamforming technology, and hybrid digital/analog beamforming technology. Different beams can be considered as different resources. The same information or different information can be sent through different beams. Optionally, multiple beams with the same or similar communication characteristics can be regarded as a beam. A beam can include one or more antenna ports for transmitting data channels, control channels, and detection signals. For example, a transmit beam can refer to the distribution of signal strength formed in different directions of space after the signal is transmitted by the antenna, and a receive beam can refer to the distribution of signal strength of wireless signals received from the antenna in different directions of space. It can be understood that one or more antenna ports that form a beam can also be regarded as an antenna port set. The embodiment of the beam in the protocol can still be a spatial filter.

10. Reference signal:

According to the Long Term Evolution LTE/NR protocol, at the physical layer, uplink communication includes the transmission of uplink physical channels and uplink signals. The uplink physical channels include random access channel (PRACH), uplink control channel (PUCCH), uplink data channel (PUSCH), etc. The uplink signals include channel sounding signal SRS, uplink control channel demodulation reference signal (PUCCH de-modulation reference signal, PUCCH-DMRS), uplink data channel demodulation reference signal PUSCH-DMRS, uplink phase noise tracking signal (PTRS), uplink positioning signal (uplink positioning RS), etc. Downlink communication includes the transmission of downlink physical channels and downlink signals. The downlink physical channels include physical broadcast channel (PBCH), downlink control channel (PDCCH), downlink data channel (PDSCH), etc. The downlink signals include primary synchronization signal (PSS)/secondary synchronization signal (SSS), downlink control channel demodulation reference signal PDCCH-DMRS, downlink data channel demodulation reference signal PDSCH-DMRS, phase noise tracking signal PTRS, channel status information reference signal (CSI-RS), cell signal (CRS), time/frequency tracking reference signal (TRS), LTE/NR positioning signal (positioning RS), etc.

11. Precoding and codebook:

The multiple input multiple output (MIMO) technology is used to increase system capacity and improve throughput. The mathematical expression is y=Hx+n, where y is the received signal, H is the MIMO channel, x is the transmitted signal, and n is the noise. In a communication system with multiple antennas, the signals of multiple transmitting antennas will be superimposed on any receiving antenna. Therefore, the method of transmitting the signal at the transmitter affects the performance of the system, and it is often complicated to restore the transmitted signal at the receiving end. In this context, precoding is used to reduce system overhead and maximize the system capacity of MIMO on the one hand, and to reduce the complexity of the receiver to eliminate the impact between channels on the other hand. At this time, the mathematical expression is y=Hx+n, and P is the precoding matrix (or vector). In order to simplify the implementation complexity, P can be selected from a predefined set of matrices (or vectors), which is called a codebook. This method is also called a codebook-based transmission method. If the transmitter can obtain all the information of H, P can be obtained by itself at the transmitter. This method is also called a non-codebook transmitter. law (non-codebook, NCB).

It should be understood that in the present application, indication includes direct indication (also called explicit indication) and implicit indication. Wherein, direct indication of information A means including the information A; implicit indication of information A means indicating information A through the correspondence between information A and information B and direct indication of information B. Wherein, the correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

It should be understood that in the present application, information C is used to determine information D, which includes information D being determined based only on information C, and information D being determined based on information C and other information. In addition, information C is used to determine information D, and it can also be indirectly determined, for example, information D is determined based on information E, and information E is determined based on information C.

In addition, "network element A sends information A to network element B" in each embodiment of the present application can be understood as the destination end of the information A or the intermediate network element in the transmission path between the destination end and the network element B, which may include directly or indirectly sending information to network element B. "Network element B receives information A from network element A" can be understood as the source end of the information A or the intermediate network element in the transmission path between the source end and the network element A, which may include directly or indirectly receiving information from network element A. The information may be processed as necessary between the source end and the destination end of the information transmission, such as format changes, etc., but the destination end can understand the valid information from the source end. Similar expressions in the present application can be understood similarly and will not be repeated here.

Exemplarily, the network device may be a core network device, an access network node (RAN node) or one or more devices in OAM as shown in FIG. 1. For example, the AI module may be the RIC shown in FIG. 4, such as a near real-time RIC or a non-real-time RIC. For example, the near real-time RIC is set in a RAN node (e.g., in a CU, DU), while the non-real-time RIC is set in an OAM, a cloud server, a core network device, or other network devices. RIC can be obtained by obtaining subsets from multiple terminal devices from a RAN node (e.g., a CU, CU-CP, CU-UP, DU and/or RU), reorganized into a training data set #2, and trained based on the training data set #2.

Exemplarily, the near real-time RIC and the non-real-time RIC may also be separately configured as a network element, and the network device may be the near real-time RIC or the non-real-time RIC.

At present, in communication systems with higher frequency bands, network equipment (and terminals in some frequency bands) usually use large-scale array antennas (for example, 500 to 1000 antenna units) to counteract the path loss caused by the increase in frequency bands through higher array gain and improve coverage. From the perspective of the implementation of network equipment, the same large array, different frequency bands and different array sizes use different array weighting methods (that is, different beamforming methods). According to the implementation scheme of beamforming, it can be roughly divided into the following three categories:

The first category: digital beamforming (DBF), each antenna unit or a group of antenna units is directly connected to a digital channel. Since each antenna signal is directly converted to the digital domain, the subsequent array weighting is performed in the digital domain, so it is called digital beamforming. The digital domain signal processing has a high degree of freedom and can support complex signal processing methods. Therefore, under the same array scale, the performance of the DBF architecture is good. On the other hand, due to the high power consumption and cost of the digital-to-analog/analog-to-digital converter (ADC/DAC) (especially under large bandwidth conditions), the cost of DBF is higher under the same array scale.

The second category: analog beamforming (ABF), each or a group of antenna units is connected to an analog phase shifter, and multiple antenna units are combined in the analog domain and then passed through a digital-to-analog/analog-to-digital converter. Compared with DBF, the entire ABF array corresponds to only one digital-to-analog/analog-to-digital converter. The advantages of the ABF architecture are low cost and power consumption. However, the phase shifter setting in the analog domain determines the direction of the beam after beamforming. Since the signal is directly combined as an electrical signal in the analog domain, it is impossible to use digital signal processing weighting like DBF. ABF must pre-configure the phase shifter setting during transmission and reception (that is, point the analog beam to the target terminal). This process needs to be completed through beam scanning during the link establishment phase, which brings additional delays. At the same time, once the analog beam is blocked or moved to cause misalignment, the link quality of the system will rapidly degrade or even terminate, so the communication reliability of ABF may not be as good as DBF.

The third category: hybrid beamforming (HBF) is an intermediate form between ABF and DBF. On the one hand, HBF has a certain number of digital ports to support digital beamforming, and each digital port drives an ABF subarray. Compared with ABF, at the same array scale, the analog subarray driven by each digital channel is smaller, so the beam is wider, the reliability is better, and the beam scanning overhead is smaller. The ratio of HBF digital ports and analog phase shifters varies with different frequencies and system design requirements. For example, the number of digital ports in the high-frequency band is very small (4 to 16), and the analog phase shifters corresponding to a single digital channel are more (16 to 32), which is closer to ABF, while the low-frequency band system has more digital ports (32 to 128) and fewer analog phase shifters (2 to 10) for a single digital channel.

Among them, both HBF and ABF architectures have analog beams. Only when the analog beam is aligned with the communication target, the signal quality is better. The direction of the analog beam (determined by the beam weight) needs to be configured before sending and receiving. For a certain terminal device, the process of network equipment selecting an analog beam is called beam training or beam scanning. Beam scanning usually uses network equipment to send reference signals using different analog beam weights. The terminal equipment measures the reference signals respectively and feeds back its measurement results to assist the network equipment in determining the beam with the best beam quality.

It should be understood that the HBF architecture has both digital ports and analog phase shifter arrays.

FIG6 shows a schematic diagram of a hardware architecture 600 .

The architecture 600 is the hardware structure of the network device HBF. The HBF architecture of the terminal device is similar to that of the network device HBF. The network device HBF is used as an example for explanation below. The architecture includes a processor 610, a memory 620, and a signal transceiver unit 630. Among them, the signal transceiver unit includes a transmitter 631 and a receiver 632, as well as an antenna 633. The transmitter and the receiver receive and send signals through the antenna. Among them, in the antenna 633 module, a square box represents a digital channel, and F in the square box is a digital precoding weight; a phase shifter (circle plus oblique arrow) represents an analog channel, connecting one array or multiple arrays, that is, in practice, one phase shifter can control multiple arrays, or the phase shifter and the array can be cross-connected.

Therefore, during the communication process, the HBF architecture will have multiple analog beams to choose from. Under each analog beam, the weighted value and MCS of the digital port used to serve a terminal need to be fed back using CSI information, which means that the network device needs to instruct the terminal device to measure the CSI information under each analog beam separately and then provide feedback. This process will cause the following problems. First, when the terminal device provides feedback, it may support different feedback overheads. For network devices, different AI models need to be configured to support different reporting capabilities. Terminal devices use different AI models for compression, which will increase the storage overhead or switching overhead of network devices and terminal devices.

Furthermore, in the prior art, under the HBF structure, the channel information corresponding to multiple analog beams needs to be measured and fed back independently. When there are N analog beams, the feedback overhead needs to be increased N times. In fact, the coverage areas of multiple analog beams will overlap to a certain extent, or the channel information between multiple analog beams is correlated. The prior art does not consider the correlation between channels between analog beams, resulting in large feedback overhead and low efficiency. Therefore, the present application solution needs to perform joint feedback for the channel information corresponding to multiple analog beams. In this case, the AI model needs to support joint compression under different analog beams. According to the solution of the prior art, multiple different AI models are required to support different analog beam compressions, which greatly increases the complexity of implementation and protocol design. At the same time, the storage of multiple AI models will also lead to an increase in the storage cost of terminal devices and network devices, and switching between multiple AI models will also increase the switching overhead of network devices and terminal devices.

In view of this, an embodiment of the present application provides a method and a communication device for feeding back channel status, which can reduce the storage/switching overhead of network equipment and terminal equipment.

Next, a method for feeding back channel status provided in an embodiment of the present application is described. The embodiment provided in the present application can be applied to the communication system shown in FIG. 1 and FIG. 2 above, without limitation.

In the following embodiments, as an example, the encoder is a terminal device and the decoder is a network device; or the encoder is a terminal device and the decoder is another terminal device; or the encoder is a network device and the decoder is another network device; or the encoder is a network device and the decoder is a terminal device, without limitation. It can be understood that the encoder in the following can be replaced by an encoding device, and the decoder can be replaced by a decoding device. In addition, it can also be understood that the encoder in the following can include circuits other than the AI model, such as processing circuits, storage circuits, transceiver circuits, and the like.

In the following embodiments, the encoder may deploy multiple sets of AI models, so that the encoder can encode based on the deployed AI models, such as compressing channel information; the decoder may deploy multiple sets of AI models, so that the decoder can decode based on the deployed AI models, such as recovering compressed information to obtain channel information. For simplicity, the AI model deployed by the encoder is referred to as the AI model of the encoder, and the AI model deployed by the decoder is referred to as the AI model of the decoder.

Figure 7 is a schematic flow chart of a method 700 for feeding back channel status provided by an embodiment of the present application. For ease of description, method 700 is exemplarily illustrated by taking an encoder and a decoder as the execution subject of the interaction. It can be understood that the encoder can be a terminal device or a component of a terminal device (such as a chip or circuit), the decoder can be a network device or a component of a network device (such as a chip or circuit), or the encoder or decoder can also be an AI node or a component of an AI node (such as a chip or circuit), without limitation. The method 700 shown in Figure 7 may include the following steps.

710. The encoder compresses M channel information to obtain a first sequence.

Among them, the M channel information is part or all of the L channel information measured by the terminal device, the L channel information corresponds to the L simulated beams, L is less than or equal to N, N is the number of channel information determined based on the reference signal on the antenna port group, and N is a positive integer.

The N channel information corresponds to N simulated beams, and N can also be understood as the maximum number of simulated beams.

In the present application, the network device and the terminal device may predefine or predetermine the maximum number of simulated beams N and the maximum feedback overhead X for joint feedback.

The maximum number N of simulated beams may be determined by the network device. For example, the network device may configure the total number of simulated beams.

In a possible implementation, the N simulation beams are different from each other, and there is an overlapping area in the coverage range of the N simulation beams.

For example, the coverage of some of the N simulated beams overlaps. For example, N is 5, including beam A, beam B, beam C, beam D and beam E, wherein the coverage of beam A and beam B overlaps.

For example, the coverage of the N simulated beams overlaps. For example, N is 5, including beam A, beam B, beam C, beam D and beam E, wherein the coverage of the five beams overlaps.

The N simulated beams correspond to the N channel information one by one. In other words, the N channel information is the channel information of the N simulated beams. For example, the channel information may be channel state information CSI. For details, please refer to the description of CSI above, which will not be repeated here.

In a possible implementation, the N channel information corresponds to N serial numbers, and the N serial numbers correspond one-to-one to the N simulated beams. In other words, the N simulated beams are associated with the N channel information through the N serial numbers. For example, N is 3, and the three simulated beams are beam A, beam B, and beam C, beam A corresponds to serial number 1, beam B corresponds to serial number 2, and beam C corresponds to serial number 3. At the same time, channel information A corresponds to serial number 1, channel information B corresponds to serial number 2, and channel information C corresponds to serial number 3, then channel information A corresponds to beam A, channel information B corresponds to beam B, and channel information C corresponds to beam C.

In other words, the N channel information corresponds to K port groups. The port group may be a CSI-RS port group.

For example, the K port groups are used to determine K groups of channel information, and the K groups of channel information and N groups of combination coefficients determine N groups of channel information, where N is greater than or equal to K and K is a positive integer.

Specifically, the following takes the precoding matrix as an example of channel information, which can be divided into the following two cases:

Case 1: N is equal to K. That is, K port groups are used to determine N=K groups of channel coefficients.

For example, the network device configures N port groups to the terminal, and each port group corresponds to an analog beam. The K port groups are used to measure the channel coefficients {H ₁ ,H ₂ ,H ₃ , _... } under N different analog beams (analog weights are {w ₁ ,w ₂ ,w ₃ ,...}) under the network device (such as base station) arrays A ₁ ,A 2 ,D ₁ ,D ₂ ,(horizontal and vertical array numbers, digital port numbers). The terminal then calculates the precoding matrices {v ₁ ,v ₂ ,v ₃ ,...} under N different analog beams through SVD decomposition.

Case 2: N is greater than K. That is, K port groups are used to determine N groups of channel coefficients.

For example, as shown in FIG11 , K port groups are used to obtain channel coefficients (or channel responses) of the K port groups, which are denoted as h ₁ , h ₂ , h ₃ , ..., h _k . Based on the channel information of the K port groups and the channel combination coefficients The channel coefficients under N simulated beams can be obtained The terminal then calculates the precoding matrices {v ₁ ,v ₂ ,v ₃ ,...} under N different simulated beams through SVD decomposition.

That is, when the N channel information are N precoding matrices, the N channel information are decomposed according to the channel coefficients of N analog beams, or the N channel information are decomposed according to the channel information of K port groups and the channel combination coefficients.

In the present application, the terminal device can measure L channel information and compress and feedback M of the channel information.

Next, a method of determining M channel information from L channel information is exemplified.

In the present application, the network device or the terminal device may determine to report M channel information and corresponding feedback overhead Y, where the M channel information corresponds to M simulated beams.

In one implementation, the network device or the terminal device may determine to feedback M channel information and the corresponding feedback overhead Y according to the priority information.

The priority information may be the priorities corresponding to the L simulated beams.

Exemplarily, the network device determines M channel information and corresponding feedback overhead Y according to the priorities corresponding to the L simulated beams.

In this case, the network device may indicate to the terminal device the correspondence between the M channel information and the N channel information.

Exemplarily, the terminal report can determine M channel information and corresponding feedback overhead Y based on the priorities corresponding to L simulated beams configured based on the network device and the measurement results of the L simulated beams.

In this case, the terminal device may indicate the correspondence between the M channel information and the N channel information to the network device.

The measurement results of the L channel information include but are not limited to CQI, RSRP measurement, etc.

In the present application, it is determined to perform joint compression feedback on M channel information to obtain a first sequence.

In the present application, the first sequence is a compression result of M channel information, and the first sequence is X joint feedback amounts corresponding to N channel information.

It should be understood that the first sequence is a joint feedback amount of N channel information dimensions. In other words, the first sequence can indicate N channel information. In other words, the first sequence includes N channel information.

The first sequence may be a sequence before quantization. For example, the first sequence is a one-dimensional real number/complex number sequence.

The first sequence may be a quantized sequence. For example, the first sequence includes X bits.

In the following embodiments, the joint feedback amount is exemplified by taking bit overhead as an example, but is not limited in any way.

First of all, it should be noted that the input and output results of the AI model are fixed, so the input of the encoder is fixed to a precoding matrix of N simulated beam dimensions. Similarly, the output of the encoder outputs an output matrix of N simulated beam dimensions.

The following is a detailed description of the input of the encoder and the output of the decoder in this application in conjunction with the AI model design schematic diagram shown in Figure 8.

As shown in FIG8 , the input of the encoder is channel information of N beam dimensions. After compression by the encoder, a joint feedback amount of X bits of overhead is obtained. After the joint feedback amount is input into the decoder, channel information of N beam dimensions is reconstructed.

It should be noted that at the input end and output end of the encoder and the input end and output end of the decoder, the stacking method of the channel information can be predefined, or in other words, the stacking method of the input matrices corresponding to different analog beams can be predefined.

The stacking method can be understood as the analog beams corresponding to the channel information to be compressed are input into the input matrix of N analog beam dimensions in a certain order or arrangement. In other words, the input/output end of the encoder or decoder requires partial input or output, and the corresponding relationship between the input end and the output end can be guaranteed according to a certain arrangement rule or position rule, thereby ensuring the performance of joint compression and reconstruction.

For example, at the input end of the encoder, M analog beam precoding matrices are filled into the corresponding beam positions of the encoder input matrix, and the remaining unfilled positions can be filled into the input matrix by inputting a fixed amount to obtain the input matrix under N beam dimensions and send it to the encoder for joint compression to obtain the full feedback amount under X bits.

Exemplarily, as shown in FIG8 , at the input end of the encoder, N channel information define logical sequence numbers Beam1-Beam N and are bound to the positions of N analog beams in a physical sense, and the encoder input end defines the stacking arrangement of the N analog beam channel information; then, the N channel information is input into the encoder, and the decoder output end defines the stacking arrangement of the N analog beam channel information.

Fig. 9 is a schematic diagram showing the stacking mode of the channel information of N simulated beams at the input and output ends, wherein the arrangement order of the N simulated beams (from 1 to N) is not limited.

At 720, determine a second sequence according to the first sequence.

The second sequence is Y joint feedback quantities corresponding to M channel information.

It should be understood that the second sequence is a joint feedback amount of M channel information dimensions. In other words, the second sequence can indicate M channel information. In other words, the first sequence includes M channel information.

The second sequence may be a sequence before quantization. For example, the second sequence is a one-dimensional real number or complex number sequence.

The second sequence may be a quantized sequence. For example, the second sequence includes Y bits.

In one implementation, the correspondence between the stacking positions of N channel information at the encoder input end and the stacking positions of M channel information at the encoder input end is determined according to the first sequence, and Y joint feedback amounts corresponding to the M channel information are determined according to the correspondence.

For example, based on the relationship between the position corresponding to the input matrix under the N-beam dimension of the encoder input end and the corresponding beam position of the M analog beam precoding matrices filled into the N-beam input matrix, the positions of the M analog beam precoding matrices filled into the N-beam input matrix are determined, or in other words, the remaining unfilled positions are excluded to obtain Y partial joint feedback amounts.

In the present application, the first sequence is the joint feedback amount of channel information in N dimensions, and the second sequence is the joint feedback amount of channel information in M dimensions. The contents of the first sequence and the second sequence are described below in conjunction with FIG9 .

FIG10 shows a schematic diagram of a detachable joint feedback provided in an embodiment of the present application.

As shown in Figure 10, the joint feedback amount of N beams consists of N+1 parts, where the first N parts {X ₁ , X ₂ , ..., X _N } represent the specific characteristics of the N simulated beams, and the N+1 part X _com represents the common characteristics of the N simulated beams. If the terminal needs to report the channel information of some beams, it only needs to report the feedback amount corresponding to the unique characteristics of the partial beams and the common characteristics of the N simulated beams.

In the present application, the first sequence includes Xbits joint feedback amounts corresponding to N beams, and the Xbits joint feedback amount is composed of the first feature and the second feature corresponding to the N channel information, or in other words, the first sequence includes N first features and O second features. The first feature indicates a specific feature of each channel information, and the second feature indicates a common feature of the N channel information.

Among them, specific features refer to features unique to each channel information, and common features refer to features shared by multiple channel information. Specific features or common features are merely example terminology names, and this application does not limit them.

The second sequence includes Ybits of joint feedback corresponding to M beams, and the Ybits of joint feedback consists of the first feature and the second feature corresponding to the M channel information, or in other words, the first sequence includes M first features and P second features. The first feature indicates a specific feature of each channel information, and the second feature indicates a common feature of the M channel information. P is less than or equal to O, and O can be 1.

In one possible implementation, M first features are determined from N first features based on a correspondence between the stacking positions of N channel information at the encoder input end and the stacking positions of M channel information at the encoder input end, P second features corresponding to the M channel information are determined from O second features based on a correspondence between the stacking positions of N channel information at the encoder input end and the stacking positions of M channel information at the encoder input end, and a second sequence is determined based on the M first features and the P second features.

Among them, the positions of the N first features in the first sequence correspond to the positions of the M first features in the second sequence, and the positions of the O second features in the first sequence correspond to the positions of the P second features in the second sequence.

In other words, when M simulated beams are filled into an input matrix of N simulated beam dimensions, they are filled in a certain regular order, so The M simulated beams have a corresponding relationship in the input matrix of N simulated beam dimensions. Correspondingly, the first features and the second features corresponding to the M beams also have a corresponding relationship with the first features and the second features of the N beam dimensions.

In one possible implementation, the N first features and the O second features include a feature principal component and a feature supplement component, wherein the feature principal component is used to complete the reconstruction of the channel information, and the feature supplement component is used to supplement the accuracy of the channel information.

Therein, the feature supplement component for a first feature or a second feature may include multiple feature supplement components, and feature supplement components with different feedback numbers indicate different feedback accuracies.

In one possible implementation, each of the M first features includes a feature principal component, some or all of the M first features include feature supplementary components, each of the P second features includes a feature principal component, and some or all of the P second features include feature supplementary components.

It can be understood that the accuracies corresponding to the M channel information fed back can all be high precision, that is, the main component and supplementary component of the first feature and the main component and supplementary component of the second feature corresponding to the M channel information are fed back, or part of it can be high precision, that is, the main component and supplementary component of the first feature and the main component and supplementary component of the second feature corresponding to part of the channel information are fed back, and the other part of the channel information only feeds back the corresponding main component of the first feature and the main component of the second feature. The present application does not limit this.

Furthermore, high-precision feedback can also feed back different numbers of supplementary components for different channel information to achieve feedback at different precision levels.

Exemplarily, for the same channel information, the more supplementary components fed back, the higher the accuracy.

It should be noted that the accuracy levels of different channel information feedback may be the same or different, and this application does not limit this.

For example, in Figure 10, the feedback amount corresponding to each feature is composed of the main component of the feature and the supplementary components of Q features (Q ≥ 1) to support feedback of Q+1 accuracy levels. The main component can independently complete the reconstruction of the part of the channel information, and the supplementary component serves as a high-precision supplement to the part of the channel information.

It should be understood that if the terminal supports high-precision reporting, the main component of the feature and q supplementary components (Q≥q≥1) can be fed back at the same time; if the terminal only supports low-precision reporting, only the main component of the feature can be fed back to complete the reconstruction of the channel information. This feedback amount design can support the terminal to report different beam features with different accuracies.

In one implementation, the characteristic principal component of each of the N first features has a corresponding relationship with the characteristic principal components of some or all of the M first features; the supplementary component of each of the N first features has a corresponding relationship with the supplementary components of some or all of the M first features; the characteristic principal component of each of the O second features has a corresponding relationship with the characteristic principal component of each of the P second features, and the characteristic supplementary component of each of the O second features has a corresponding relationship with the characteristic supplementary component of each of the P second features.

Among them, the positions of the N first features in the first sequence correspond to the positions of the M first features in the second sequence, and the positions of the O second features in the first sequence correspond to the positions of the P second features in the second sequence. Accordingly, for the features in the first sequence (the first feature and the second feature) and the features in the second sequence (the first feature and the second feature) that have a corresponding relationship, the feature principal components and feature supplementary components included in each also have a corresponding relationship.

In the present application, the accuracy level corresponding to the M channel information can be determined by the network device or by the terminal device.

Exemplarily, the network device may determine the accuracy categories corresponding to the M channel information according to the priorities of the L channel information.

Exemplarily, the terminal device may determine the accuracy categories corresponding to the M channel information based on the measurement results of the L channel information and/or the priority information of the L channel information.

It should be understood that when the encoder reports different characteristics of M simulated beams with different accuracies, the terminal can give priority to reporting the unique characteristic principal components and common characteristic principal components of the M simulated beams to ensure that the decoder can complete the reconstruction of the complete channel information of the M simulated beams; then, the encoder can report the supplementary components of the simulated beams based on the different priorities of the simulated beams to achieve feedback with higher accuracy.

730. The encoder sends the second sequence to the decoder.

Accordingly, the decoder receives the second sequence.

At 740, the decoder determines the first sequence according to the second sequence.

It should be understood that the input and output of the encoder and decoder are matrices of fixed N beam dimensions, that is, at the input of the decoder, the joint feedback amount of M channel information needs to be restored to the joint feedback amount corresponding to N channel information.

In a possible implementation, a correspondence between stacking positions of M channel information at a decoder input and stacking positions of N channel information at a decoder input is determined, and X joint feedback amounts corresponding to the N channel information are determined according to the correspondence.

For example, according to the position corresponding to the input matrix under the N beam dimension of the encoder input end and the M simulated beam precoding matrices filled to N The corresponding beam position relationship of the beam input matrix is determined, and the corresponding relationship between the stacking position of the M channel information at the decoder input end and the stacking position of the N channel information is determined. The M analog beam coding matrices are filled to the position of the N beam input matrix, and the beam position corresponding to the non-feedback part is filled with a fixed amount, so that the full feedback amount of X can be obtained.

In one possible implementation, N first features and O second features are determined based on the correspondence between the stacking positions of N channel information at the encoder input end and the stacking positions of M channel information at the encoder input end, and X joint feedback amounts corresponding to the N channel information are determined based on the M first features and the P second features.

Among them, the positions of the N first features in the first sequence correspond to the positions of the M first features in the second sequence, and the positions of the O second features in the first sequence correspond to the positions of the P second features in the second sequence.

In other words, when M simulated beams are filled into an input matrix of N simulated beam dimensions, they are filled in a certain regular order. Therefore, the M simulated beams have a corresponding relationship in the input matrix of N simulated beam dimensions. Correspondingly, the first features and the second features corresponding to the M beams also have a corresponding relationship with the first features and the second features of the N beam dimensions.

In a possible implementation, the M first features and the P second features include a feature principal component and a feature supplement component, wherein the feature principal component is used to complete the reconstruction of the channel information, and the feature supplement component is used to supplement the accuracy of the channel information.

Therein, the feature supplement component for a first feature or a second feature may include multiple feature supplement components, and feature supplement components with different feedback numbers indicate different feedback accuracies.

In one possible implementation, each of the N first features includes a feature principal component, some or all of the N first features include a feature supplementary component, each of the O second features includes the feature principal component, and some or all of the O second features include the feature supplementary component.

It can be understood that the accuracies corresponding to the M channel information actually fed back can all be high-precision, that is, the main component and supplementary component of the first feature and the main component and supplementary component of the second feature corresponding to the M channel information are fed back, or part of it can be high-precision, that is, the main component and supplementary component of the first feature and the main component and supplementary component of the second feature corresponding to part of the channel information are fed back, and the other part of the channel information only feeds back the corresponding main component of the first feature and the main component of the second feature. The present application does not limit this.

In one implementation, the characteristic principal component of each first feature among the N first features has a corresponding relationship with the characteristic principal components of some or all of the first features among the M first features; the supplementary component of each first feature among the N first features has a corresponding relationship with the supplementary components of some or all of the first features among the M first features; the characteristic principal component of each second feature among the O second features has a corresponding relationship with the characteristic principal component of each second feature among the P second features, and the characteristic supplementary component of each second feature among the O second features has a corresponding relationship with the characteristic supplementary component of each second feature among the P second features.

Among them, the positions of the N first features in the first sequence correspond to the positions of the M first features in the second sequence, and the positions of the O second features in the first sequence correspond to the positions of the P second features in the second sequence. Accordingly, for the features in the first sequence (the first feature and the second feature) and the features in the second sequence (the first feature and the second feature) that have a corresponding relationship, the feature principal components and feature supplementary components included in each also have a corresponding relationship.

In the present application, the accuracy levels corresponding to the reported M channel information may be the same or different, and the present application does not limit this.

In the present application, the accuracy level corresponding to the reported M channel information may be determined by a network device or a terminal device.

For the reporting and determination of the accuracy level, please refer to the detailed description of the encoder side, which will not be repeated here.

It should be understood that when the encoder reports different characteristics of M simulated beams with different accuracies, the terminal can give priority to reporting the unique characteristic principal components and common characteristic principal components of the M simulated beams, and the decoder completes the reconstruction of the complete channel information of the M simulated beams based on the reported unique characteristic principal components and common characteristic principal components of the M simulated beams; then, the encoder reports the supplementary components of the simulated beams based on the different priorities of the simulated beams, and the decoder can further reconstruct the corresponding channel information based on the supplementary components corresponding to the M simulated beams, thereby achieving higher-precision reconstruction of the channel information.

At 750, the decoder reconstructs the first sequence to obtain M channel information.

The matrix of N simulated beam dimensions corresponding to the first sequence is input to the decoder, and the decoder reconstructs the first sequence to obtain an output matrix of N simulated beam dimensions.

Furthermore, the decoder selects information of beam positions corresponding to the M channel information from the output matrix according to the correspondence between the stacking positions of the M channel information at the decoder input end and the stacking positions of the N channel information at the decoder input end, thereby obtaining an output matrix of the M channel information.

In other words, the decoder reconstructs the input matrix of N analog beam dimensions and obtains the output matrix corresponding to N analog beam dimensions. The input matrix of N analog beam dimensions includes the input matrix of M analog beams and NM fixed quantities. Therefore, in order to obtain the output matrix of M analog beams, it is necessary to stack the M channel information at the decoder input end according to the stacking position of the M channel information and the N channel information. The M channel information is intercepted according to the corresponding relationship of the stacking position of the information at the decoder input end. It can also be said that a fixed amount of channel information is eliminated according to the corresponding relationship, so as to obtain the channel information corresponding to the M simulated beams.

According to the technical solution, the AI model can be used to jointly compress the channel information of N simulated beams of fixed dimension and feed it back to the decoder. The decoder uses the AI model to reconstruct the channel information of N simulated beams, wherein the encoder can carry M channel information through the input matrix corresponding to the N simulated beams of fixed dimension, thereby realizing the compression and feedback of partial channel information, avoiding the storage/switching overhead of multiple AI models and reducing the complexity of implementation; in addition, the priority of partial feedback is defined to ensure the efficiency and reliability of multi-beam reporting; further, for the M channel information of compressed feedback, the accuracy of the corresponding channel information can be fed back through the characteristic principal component and characteristic supplementary component corresponding to each channel information, thereby realizing that different simulated beams can be reported with different accuracies, increasing the flexibility of the feedback mechanism.

The feedback method proposed in this application is described in detail below in conjunction with multi-beam channel information measurement reporting.

Figure 11 is a schematic flow chart of a method for feeding back channel status provided by an embodiment of the present application. For ease of description, method 1100 is exemplarily illustrated by taking a network device and a terminal device as the execution subject of the interaction. The encoder and the decoder can be deployed on the terminal device and the network device, respectively. Among them, the encoder or decoder can also be an AI node or a component of an AI node (such as a chip or circuit), without limitation. The method 1100 shown in Figure 11 may include the following steps.

1110. The network device sends configuration information to the terminal device.

The configuration information may include reference signal configuration information and channel information reporting configuration information.

The reference signal configuration information may include information related to reference signal port grouping and information related to reference signal resource grouping.

Information related to reference signal port grouping, for example, the number of reference signal port groups K, the number of ports in each group is _PCSI-RS,k , k=0,1,...,K-1. Exemplarily, the number of ports in each port group is exactly the same, for example, the number of ports in each port group is _PCSI-RS .

Information related to reference signal resource grouping, for example, the number of reference signal resource groups K, the number of reference signal resources and/or ports in each group is _{PCSI-RS, k} , k = 0, 1, ..., K-1, exemplarily, the total number of ports in each resource group is exactly the same, for example, the total number of ports in each resource group is _PCSI-RS .

Exemplarily, the reference signal resource grouping may be CSI-RS port group #1, CSI-RS port group #2, ..., CSI-RS port group #K.

In this embodiment, the reference signal port group is used as an example to describe the reference signal. Similarly, this solution is also applicable to the scenario of reference signal resource grouping. This application does not limit this.

The channel information reporting configuration information may include the content of reporting and measurement and the number of reporting and measurement.

Exemplarily, the number of reports and measurements may be the number L of measured channel information, where L is less than or equal to N.

It should be noted that in this embodiment, N simulated beams are used as the maximum number of simulated beams for joint feedback, and X joint overhead is used as the maximum feedback amount for joint feedback. The determination of the maximum number of simulated beams and the maximum joint feedback amount can refer to step 710 in method 700, and this application does not limit this.

In a possible implementation, the network device determines the number of simulated beams M and the feedback overhead Y that need to be reported.

Exemplarily, the network device determines the reported number of simulated beams M and the feedback overhead Y based on the priority of the joint feedback of each simulated beam. In this case, L can be equal to M, and the network device can send the measured correspondence between M simulated beams and N simulated beams and the feedback overhead Y to the terminal device.

In another possible implementation, the terminal device determines the number of simulated beams M and the feedback overhead Y to be reported.

Exemplarily, the terminal device measures L channel information and determines M reported simulated beams and feedback overhead Y according to the priority of joint feedback (for example, based on CQI/RSRP measurement). In this case, L is less than or equal to the maximum number of simulated beams N, and M is less than or equal to L. The terminal device can report the correspondence between the M simulated beams and the N simulated beams determined by itself, as well as its feedback overhead Y to the network device.

The configuration information may also include a CSI-RS transmission method and/or a relationship between a CSI-RS port group and multi-analog beam channel information (see 1120 below for details).

The configuration information may also include other content, which is not limited in this application.

1120. The network device sends a reference signal to the terminal device.

The network device sends a reference signal to the terminal device through the resources configured by the reference signal configuration information.

In the following embodiments, the reference signal takes CSI-RS as an example, which is not limited in the present application.

The CSI-RS is sent on the resources configured by the resource configuration information.

In a possible implementation, different CSI-RS port groups are sent in a time division manner, that is, different CSI-RS port groups are sent on different time domain resources (eg, time slots or OFDM symbols).

The CSI-RS port group is sent in a time-division manner, which can facilitate the sending of multiple reference signals based on different simulated beams under the HBF architecture. number to realize the measurement of channel information.

In another possible implementation, different CSI-RS port groups may be sent in a frequency division manner, that is, different CSI-RS port groups are sent on different frequency domain resources (e.g., component carriers, resource blocks, or different subcarriers). For example, CSI-RS port group #1 is sent based on the first analog beam; and CSI-RS port group #2 is sent based on the second analog beam.

The CSI-RS port group is sent in a frequency division manner, so that the network device can quickly scan the channel information.

In another possible implementation, different CSI-RS port groups may be sent in a code division manner, for example, CSI-RS port group #1 is sent based on a first analog beam; and CSI-RS port group #2 is sent based on a second analog beam orthogonal to the first analog beam.

The CSI-RS port group is sent in a code division manner, which can be used for network devices in the HBF architecture to quickly scan channel information.

It should be noted that there is a timeliness requirement for the feedback of channel information. When multiple channel information is fed back jointly, the multiple channel information to be compressed must meet the timeliness requirement, thereby ensuring the performance of joint compression.

In a possible implementation manner, the time-frequency ranges of multiple CSI-RS port groups may be limited.

For example, the network equipment configures CSI-RS port groups #1 to K respectively, and multiple port groups need to be limited to the same frequency domain (but can still be located in different resource units of the same resource block) and occupy the same bandwidth; and multiple port groups are located in the same time slot or adjacent time slots, and the time slot interval of multiple CSI-RS port groups does not exceed t.

1130. The terminal device measures information of L simulated beam channels.

The terminal device receives K CSI-RS port groups, reports configuration information based on CSI-RS and channel information, and obtains the precoding matrix under L simulated beams.

Specifically, the following takes the precoding matrix as an example of channel information, which can be divided into the following two cases:

Case 1: L is equal to K. That is, K port groups are used to determine L=K groups of channel coefficients.

For example, the network device configures L port groups to the terminal, and each port group corresponds to an analog beam. The K port groups are used to measure the channel coefficients {H ₁ ,H ₂ ,H ₃ , _... } under L different analog beams (analog weights are {w ₁ ,w ₂ ,w ₃ ,...}) under the network device (such as base station) arrays A _{1 ,A 2 ,D 1 ,D 2 (horizontal and vertical array numbers, digital port numbers), and the terminal device then calculates the precoding matrices {v 1 , v 2} ,v ₃ ,...} under the L different analog beams through _SVD decomposition.

Case 2: L is greater than K. That is, K port groups are used to determine L groups of channel coefficients.

For example, K port groups are used to obtain channel coefficients (or channel responses) of the K port groups, which are recorded as h ₁ , h ₂ , h ₃ , ..., h _k . Based on the channel information of the K port groups and the channel combination coefficients The channel coefficients under L simulated beams can be obtained The terminal device then calculates the precoding matrices {v ₁ ,v ₂ ,v ₃ ,...} under L different simulated beams through SVD decomposition.

That is, when the L channel information are L precoding matrices, the L channel information are decomposed according to the channel coefficients of the L analog beams, or the L channel information are decomposed according to the channel information of the K port groups and the channel combination coefficients.

In the present application, the terminal device can measure L channel information and compress and feedback M of the channel information.

It should be noted that, for the HBF architecture (or analog beamforming architecture), case 2 can obtain more channel information with fewer reference signals. For example, the base station can use K groups of orthogonal analog weights {W ₁ ,W ₂ ,W ₃ ,...}, and send K CSI-RS port groups simultaneously through different antenna groups, so as to obtain the channel information corresponding to the K analog ports; and in the terminal device, by weighting the analog port channels (i.e., It can be equivalent to a simulated beam), so that the channel information of L>K simulated beams can be obtained. In this way, the terminal device measures the encrypted beam channel information.

1140. The terminal device jointly compresses the channel information of the M analog beams to obtain a precoding matrix of the M analog beams.

Specifically, the terminal device can determine the channel information of M simulated beams from the measured channel information of L simulated beams, that is, select the channel information of M simulated beams to be reported, and calculate the precoding matrix of the M simulated beams through SVD.

The channel information of the M simulated beams may be determined from the channel information of the L simulated beams in the following exemplary manner.

In a possible implementation, the reported M analog beams and their feedback overhead Y may be determined by the network device based on the priorities of the L analog beams. In this case, the network device may indicate the correspondence between the M channel information and the N channel information to the terminal device.

In a possible implementation, the terminal device report can determine M channel information and corresponding feedback overhead Y based on the priorities corresponding to L simulated beams configured based on the network device and the measurement results of the L simulated beams.

In this case, the terminal device may indicate the correspondence between the M channel information and the N channel information to the network device.

The measurement results of the L channel information include but are not limited to CQI, RSRP measurement, etc.

The terminal device jointly compresses the M analog beams to obtain channel information of the M analog beams.

Figure 12 shows a schematic diagram of a compression feedback process. As shown in Figure 12, at the input end of the encoder, the precoding matrix of the M simulated beams needs to be filled into the corresponding beam position of the input matrix of the N beam dimensions of the encoder. When M is less than N, the remaining unfilled positions can be filled with a fixed amount to obtain the input matrix of the N simulated beam dimensions, and the input matrix is input into the encoder for joint compression to obtain the full feedback amount of X bits of overhead.

At the input end of the encoder, the beam positions are filled according to the stacking arrangement of the defined N simulated beam channel information, for example, the N simulated beams are arranged in the stacking manner as shown in FIG. 8 .

1150. The terminal device sends a joint feedback amount of M channel information.

The encoder output end outputs an output matrix in N analog beam dimensions and X feedback quantities. The terminal device intercepts Y joint feedback quantities corresponding to M analog beams from the output matrix in N analog beam dimensions according to the correspondence between the stacking positions of the N analog beams and the M analog beams at the encoder input end, and feeds back the matrix corresponding to the M analog beams to the decoder, so that partial reporting can be performed.

It can be understood that, when the M channel information and the feedback overhead Y are determined by the terminal device according to the priority information and the measurement result, the terminal device can also send the correspondence between the M channel information and the N channel information.

1160. The network device jointly reconstructs the channel information of the M simulated beams to obtain M channel information.

As shown in Figure 12, the network reports the partial beam joint feedback amount received under the Y-bit overhead, and based on the corresponding relationship between the stacking positions of the N analog beams and the M analog beams, fills the corresponding beam positions of the non-feedback part with a fixed amount to obtain the full feedback amount under the X-bit overhead, and inputs it to the decoder for joint reconstruction to obtain the output matrix under the N-beam dimension.

Furthermore, the network device selects information of corresponding beam positions from the output matrix according to the correspondence between the stacking positions of the N simulated beams and the M simulated beams to obtain the precoding matrix of the reported M simulated beams.

It should be noted that, in step S1150, the terminal device may also determine the feedback accuracies corresponding to the M simulated beams. The feedback overheads corresponding to the M simulated beams are expressed as Z = {Z ₁ , Z ₂ , ..., Z _m }, where Z includes m feedback overheads corresponding to the M simulated beams, and the m feedback overheads correspond to m feedback accuracies.

It can be understood that the feedback accuracy is configured by the network device to the terminal device based on the priority information of the L simulated beams, or it can be determined by the terminal device according to the measurement results and priority information.

After obtaining the X-bit joint feedback amount, the terminal device determines a Z-bit partial feedback amount from the X-bit joint feedback amount based on the feedback overhead Z={Z ₁ , Z ₂ , …, Z _m } and the corresponding relationship between different precision features and feedback amount positions, wherein the Z-bit partial feedback amount may include m low-precision feedback amounts, may also include m high-precision feedback amounts, or may be a part of low-precision feedback and the other part of high-precision feedback amounts, which is not limited in the present application.

That is, the terminal device can feed back different accuracies for different analog beams, thereby achieving the purpose of flexible feedback.

Assuming that the Z-bit partial feedback amount includes m low-precision feedback amounts, the Z-bit feedback amount is sent to the decoder. At the input end of the decoder, according to the feedback overhead Z={Z ₁ , Z ₂ , ..., Z _m } and the corresponding relationship between different precision characteristics and feedback amount positions, the low-precision joint feedback amount is padded with a fixed amount at the corresponding supplementary component position to obtain X full feedback amounts and input them into the decoder for joint reconstruction to obtain a low-precision precoding matrix of M analog beams.

In this technical solution, the channel information of the partial beam is input on the encoder side according to the correspondence between the beam positions of the partial feedback amount and the full feedback amount, thereby realizing compression and feedback of the partial channel information, avoiding the storage/switching overhead of multiple AI models and reducing the complexity of implementation; in addition, the priority of partial feedback is defined to ensure the efficiency and reliability of multi-beam reporting; further, for the M channel information of compressed feedback, the accuracy of the corresponding channel information can be fed back through the characteristic principal component and characteristic supplementary component corresponding to each channel information, thereby realizing that different simulation beams can be reported with different accuracies, increasing the flexibility of the feedback mechanism.

It should be understood that other possible implementation methods of the embodiments of the present application are similar to the above-mentioned method 700 or method 1100. Please refer to the description in method 700 or method 1100, which will not be repeated here.

It should be understood that the sequence numbers of the above processes do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the interaction between various network elements. It can be understood that each network element, such as a transmitting end device or a receiving end device, includes a hardware structure and/or software module corresponding to the execution of each function in order to realize the above functions. Those skilled in the art should be aware that, in combination with the units and algorithm steps of each example described in the embodiments disclosed in this document, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

The embodiment of the present application can divide the functional modules of the transmitting end device or the receiving end device according to the above method example. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation. The following is an example of dividing each functional module corresponding to each function.

The method provided by the embodiment of the present application is described in detail above in conjunction with Figures 7 to 12. The device provided by the embodiment of the present application is described in detail below in conjunction with Figures 13 to 14. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment. Therefore, the content not described in detail can be referred to the method embodiment above, and for the sake of brevity, it will not be repeated here.

FIG13 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application.

The device 1300 includes a transceiver unit 1310 and a processing unit 1320, wherein the transceiver unit 1310 can be used to implement corresponding communication functions, and the processing unit 1320 can be used to perform data processing.

Optionally, the transceiver unit 1310 may also be referred to as a communication interface or a communication unit, including a sending unit and/or a receiving unit. The transceiver unit 1310 may be a transceiver (including a transmitter and/or a receiver), an input/output interface (including an input and/or output interface), a pin or a circuit, etc. The transceiver unit 1310 may be used to perform the steps of sending and/or receiving in the above method embodiment.

Optionally, the processing unit 1320 may be a processor (may include one or more), a processing circuit with a processor function, etc., and may be used to execute other steps except sending and receiving in the above method embodiment.

Optionally, the device 1300 further includes a storage unit, which may be a memory, an internal storage unit (e.g., a register, a cache, etc.), an external storage unit (e.g., a read-only memory, a random access memory, etc.), etc. The storage unit is used to store instructions, and the processing unit 1320 executes the instructions stored in the storage unit so that the communication device executes the above method.

In one design, the device 1300 may be used to perform the actions performed by the encoder in the above method embodiments, such as the device 1300 may be used to perform the actions performed by the encoder in the above method 700 or method 1100. In this case, the device 1300 may be a component of the encoder, the transceiver unit 1310 is used to perform the transceiver-related operations of the encoder in the above method embodiments, and the processing unit 1320 is used to perform the processing-related operations of the encoder in the above method embodiments.

For example, the processing unit 1320 is used to compress M channel information to obtain a first sequence, where the M channel information is part or all of L measured channel information, L is less than or equal to N, N is the number of channel information determined based on reference signals on K antenna port groups, N is a positive integer, and the first sequence is X joint feedback amounts corresponding to the N channel information; the processing unit 1320 is also used to determine a second sequence based on the first sequence, where the second sequence is Y joint feedback amounts corresponding to the M channel information; the transceiver unit 1310 is used to send the second sequence to the decoder.

Optionally, the processing unit 1320 is further used to determine the correspondence between the stacking positions of the N channel information at the encoder input end and the stacking positions of the M channel information at the encoder input end; the processing unit is also used to determine Y joint feedback amounts corresponding to the M channel information based on the correspondence.

Optionally, the processing unit 1320 is further configured to determine accuracy levels corresponding to the M channel information.

It should be understood that the transceiver unit 1310 and the processing unit 1320 may also perform other operations performed by the encoder in any of the above methods 700 or 1100, which will not be described in detail here.

In one design, the device 1300 may be used to perform the actions performed by the decoder in the above method embodiments, such as the device 1300 may be used to perform the actions performed by the decoder in the above method 700 or method 1100. In this case, the device 1300 may be a component of the decoder, the transceiver unit 1310 is used to perform the transceiver-related operations on the decoder side in the above method embodiments, and the processing unit 1320 is used to perform the processing-related operations on the decoder side in the above method embodiments.

For example, the transceiver unit 1310 is used to receive a second sequence, where the second sequence is Y joint feedback amounts corresponding to M channel information, where the M channel information is part or all of L measured channel information, where L is less than or equal to N, where N is the number of channel information determined based on reference signals on K antenna port groups, and N is a positive integer; the processing unit 1320 is used to determine a first sequence according to the second sequence, where the first sequence is X joint feedback amounts corresponding to the N channel information; and the processing unit 1320 is also used to reconstruct the first sequence to obtain the M channel information.

Optionally, the processing unit 1320 is further used to determine the correspondence between the stacking positions of the M channel information at the decoder input end and the stacking positions of the N channel information at the decoder input end; the processing unit is also used to determine X joint feedback amounts corresponding to the N channel information according to the correspondence.

Optionally, the processing unit 1320 is further configured to determine accuracy levels corresponding to the M channel information.

Optionally, the processing unit 1320 is further configured to determine the stacking position of the M channel information at the decoder input end and the N channel information at the decoder input end. The processing unit 1320 is further configured to determine the M channel information according to the corresponding relationship.

It should be understood that the transceiver unit 1310 and the processing unit 1320 may also execute other operations performed by the terminal device in any of the above-mentioned methods 700 or 1100, which are not described in detail here.

It should also be understood that the device 1300 here is embodied in the form of a functional unit. The term "unit" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor or a group processor, etc.) and a memory for executing one or more software or firmware programs, a combined logic circuit and/or other suitable components that support the described functions. In an optional example, those skilled in the art can understand that the device 1300 can be specifically a network device in the above-mentioned embodiments, and can be used to execute the various processes and/or steps corresponding to the network device in the above-mentioned method embodiments. To avoid repetition, it will not be repeated here.

The apparatus 1300 of each of the above-mentioned schemes has the function of implementing the corresponding steps executed by the device in the above-mentioned method, or the apparatus 1300 of each of the above-mentioned schemes has the function of implementing the corresponding steps executed by the network device in the above-mentioned method. The function can be implemented by hardware, or the corresponding software can be implemented by hardware. The hardware or software includes one or more modules corresponding to the above-mentioned functions; for example, the transceiver unit can be replaced by a transceiver (for example, the sending unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as the processing unit, can be replaced by a processor to respectively perform the sending and receiving operations and related processing operations in each method embodiment.

In addition, the transceiver unit 1310 may also be a transceiver circuit (for example, may include a receiving circuit and a sending circuit), and the processing unit may be a processing circuit.

It should be noted that the device in FIG. 13 may be a network element or device in the aforementioned embodiment, or may be a chip or a chip system, such as a system on chip (SoC). The transceiver unit may be an input and output circuit or a communication interface; the processing unit may be a processor or a microprocessor or an integrated circuit integrated on the chip. This is not limited here.

Figure 14 is a schematic diagram of a communication architecture provided by an embodiment of the present application. The communication device 1400 shown in Figure 14 includes: a processor 1410, a memory 1420 and a transceiver 1430. The processor 1410 is coupled to the memory 1420 and is used to execute instructions stored in the memory 1420 to control the transceiver 1430 to send and/or receive signals.

It should be understood that the processor 1410 and the memory 1420 can be combined into a processing device, and the processor 1410 is used to execute the program code stored in the memory 1420 to implement the above functions. In specific implementation, the memory 1420 can also be integrated into the processor 1410, or independent of the processor 1410. It should be understood that the processor 1410 can also correspond to each processing unit in the above communication device, and the transceiver 1430 can correspond to each receiving unit and sending unit in the above communication device.

It should also be understood that the transceiver 1430 may include a receiver (or receiver) and a transmitter (or transmitter). The transceiver may further include an antenna, and the number of antennas may be one or more. The transceiver may also be a communication interface or interface circuit.

Specifically, the communication device 1400 may correspond to the terminal device in the method 700 or the method 1100 according to the embodiment of the present application. The communication device 1400 may include a unit of the method performed by the encoder in the method 700 or the method 1100. It should be understood that the specific process of each unit performing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

When the communication device 1400 is a chip, the chip includes an interface unit and a processing unit, wherein the interface unit may be an input/output circuit or a communication interface; and the processing unit may be a processor or a microprocessor or an integrated circuit integrated on the chip.

In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

It should be noted that the processor in the embodiment of the present application can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by the hardware integrated logic circuit in the processor or the instructions in the form of software. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, The processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

The present application also provides a computer-readable medium on which a computer program is stored. When the computer program is executed by a computer, the functions of any of the above method embodiments are implemented.

The present application also provides a computer program product, which implements the functions of any of the above method embodiments when executed by a computer.

In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a high-density digital video disc (DVD)), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

In the embodiments of the present application, words such as "exemplary" and "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present concepts in a concrete way.

It should be understood that the "embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the various embodiments in the entire specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner.

It should be understood that in various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The names of all nodes and messages in this application are merely names set by this application for the convenience of description. The names in the actual network may be different. It should not be understood that this application limits the names of various nodes and messages. On the contrary, any name with the same or similar function as the node or message used in this application is regarded as the method or equivalent replacement of this application, and is within the scope of protection of this application.

It should also be understood that in the present application, "when", "if" and "if" all mean that the UE or base station will take corresponding actions under certain objective circumstances. It is not a time limit, and it does not require the UE or base station to make judgments when implementing it, nor does it mean that there are other limitations.

In addition, the terms "system" and "network" are often used interchangeably in this article. The term "and/or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and/or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

The term "at least one of..." or "at least one of..." herein refers to all or any combination of the listed items. For example, "at least one of A, B, and C" may refer to the following six situations: A exists alone, B exists alone, C exists alone, A and B exist at the same time, B and C exist at the same time, and A, B, and C exist at the same time. "At least one" herein refers to one or more. "More than one" refers to two or more.

It should be understood that in each embodiment of the present application, the terms “including”, “comprising”, “having” and their variations all mean “including but not limited to”, unless otherwise specifically emphasized.

It should be understood that in various embodiments of the present application, the first, second and various digital numbers are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application. For example, to distinguish different information.

Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. Implementation. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims (32)

A method for feeding back a channel state, characterized in that it is applied to an encoder and comprises: Compressing M channel information to obtain a first sequence, where the M channel information is part or all of L measured channel information, L is less than or equal to N, N is the number of channel information determined based on reference signals on K antenna port groups, the first sequence is X joint feedback amounts corresponding to the N channel information, and M, L, and N are positive integers; Determine a second sequence according to the first sequence, where the second sequence is Y joint feedback amounts corresponding to the M channel information; The second sequence is sent to a decoder. The method according to claim 1 is characterized in that when the first sequence or the second sequence is a sequence before quantization, the joint feedback amount is the length of the first sequence or the second sequence, or when the first sequence or the second sequence is a sequence after quantization, the joint feedback amount is the number of bits of the first sequence or the second sequence. The method according to claim 1 or 2, characterized in that determining the second sequence according to the first sequence comprises: Determine a corresponding relationship between a stacking position of the N channel information at the encoder input end and a stacking position of the M channel information at the encoder input end; Determine Y joint feedback amounts corresponding to the M channel information according to the corresponding relationship. The method according to claim 3 is characterized in that the first sequence includes N first features and O second features, the N first features correspond to the N channel information, the first feature indicates a specific feature of each channel information, and the O second features indicate a common feature of the N channel information, and the determining, according to the corresponding relationship, Y joint feedback amounts corresponding to the M channel information comprises: Determine, according to the corresponding relationship and the N first features, M first features corresponding to the M channel information; Determine P second features corresponding to the M channel information according to the corresponding relationship and the O second features, where P is less than or equal to O, and O and P are positive integers; Determine Y joint feedback amounts corresponding to the M channel information according to the M first features and the P second features. The method according to claim 4 is characterized in that the positions of the N first features in the first sequence correspond to the positions of the M first features in the second sequence, and the positions of the O second features in the first sequence correspond to the positions of the P second features in the second sequence. The method according to claim 5 is characterized in that the N first features and the O second features include feature principal components and feature supplementary components, the feature principal components are used to complete the reconstruction of the channel information, and the feature supplementary components are used to supplement the accuracy of the channel information. The method according to claim 6 is characterized in that each of the M first features includes the feature principal component, some or all of the M first features include the feature supplementary component, each of the P second features includes the feature principal component, and some or all of the P second features include the feature supplementary component. The method according to claim 7 is characterized in that the characteristic principal component of each first feature among the N first features has a corresponding relationship with the characteristic principal components of part or all of the first features among the M first features; the supplementary component of each first feature among the N first features has a corresponding relationship with the supplementary components of part or all of the first features among the M first features; the characteristic principal component of each second feature among the O second features has a corresponding relationship with the characteristic principal component of each second feature among the P second features, and the characteristic supplementary component of each second feature among the O second features has a corresponding relationship with the characteristic supplementary component of each second feature among the P second features. The method according to any one of claims 1 to 8, characterized in that the method further comprises: Determine the precision levels corresponding to the M channel information. The method according to any one of claims 1-9 is characterized in that the M channel information or the accuracy level corresponding to the M channel information is determined by a network device, or the M channel information or the accuracy level corresponding to the M channel information is determined by a terminal device. The method according to claim 10 is characterized in that the M channel information or the accuracy level corresponding to the M channel information is determined by the network device according to the priority information of the L channel information; or, the M channel information or the accuracy level corresponding to the M channel information is determined by the terminal device according to the measurement results of the L channel information and/or the priority information of the L channel information. The method according to claim 11, characterized in that the method further comprises: When the M channel information is determined by the network device, sending a correspondence between the M channel information and the L channel information; When the precision categories corresponding to the M channel information are determined by the network device, the precision categories respectively corresponding to the M channel information are sent. The method according to any one of claims 1-12 is characterized in that the encoder is used in a terminal device. A method for feeding back a channel state, characterized in that it is applied to a decoder, comprising: receiving a second sequence, where the second sequence is Y joint feedback amounts corresponding to M channel information, where the M channel information is part or all of L measured channel information, where L is less than or equal to N, where N is the number of channel information determined based on reference signals on K antenna port groups, and M, L, and N are positive integers; Determine a first sequence according to the second sequence, where the first sequence is X joint feedback amounts corresponding to the N channel information; The first sequence is reconstructed to obtain the M channel information. The method according to claim 14 is characterized in that when the first sequence or the second sequence is a sequence before quantization, the joint feedback amount is the length of the first sequence or the second sequence, or when the first sequence or the second sequence is a sequence after quantization, the joint feedback amount is the number of bits of the first sequence or the second sequence. The method according to claim 14 or 15, characterized in that determining the first sequence according to the second sequence comprises: Determine a corresponding relationship between a stacking position of the M channel information at the decoder input end and a stacking position of the N channel information at the decoder input end; X joint feedback amounts corresponding to the N channel information are determined according to the corresponding relationship. The method according to claim 16, characterized in that the second sequence includes M first features and P second features, the M first features correspond to the M channel information, the first feature indicates a specific feature of each channel information, and the second feature indicates a common feature of the M channel information, and the determining, according to the corresponding relationship, X joint feedback amounts corresponding to the N channel information comprises: Determine N first features corresponding to N channel information according to the corresponding relationship and the M first features; Determine O second features corresponding to the N channel information according to the corresponding relationship and the P second features, where P is less than or equal to O, and O and P are positive integers; Determine X joint feedback amounts corresponding to the N channel information according to the N first features and the O second features. The method according to claim 17 is characterized in that the positions of the M first features in the second sequence correspond to the positions of the N first features in the first sequence, and the positions of the P second features in the second sequence correspond to the positions of the O second features in the first sequence. The method according to claim 18 is characterized in that the M first features and the P second features include feature principal components and feature supplementary components, the feature principal components are used to complete the reconstruction of the channel information, and the feature supplementary components are used to supplement the accuracy of the channel information. The method according to claim 19 is characterized in that each of the N first features includes the feature principal component, some or all of the N first features include the feature supplementary component, each of the O second features includes the feature principal component, and some or all of the O second features include the feature supplementary component. The method according to claim 20 is characterized in that the characteristic principal component of each of the N first features has a corresponding relationship with the characteristic principal components of part or all of the M first features; the supplementary component of each of the N first features has a corresponding relationship with the supplementary components of part or all of the M first features; the characteristic principal component of each of the O second features has a corresponding relationship with the characteristic principal component of each of the P second features, and the characteristic supplementary component of each of the O second features has a corresponding relationship with the characteristic supplementary component of each of the P second features. The method according to any one of claims 14 to 21, characterized in that the method further comprises: Determine the precision levels corresponding to the M channel information. The method according to any one of claims 14-22 is characterized in that the M channel information or the accuracy level corresponding to the M channel information is determined by a network device, or the M channel information or the accuracy level corresponding to the M channel information is determined by a terminal device. The method according to claim 23, characterized in that the M channel information or the accuracy corresponding to the M channel information The level is determined by the network device based on the priority information of the L channel information; or, the M simulated beams or the accuracy level corresponding to the M simulated beams is determined by the terminal device based on the measurement results of the L channel information and/or the priority information of the L channel information. The method according to claim 24, characterized in that the method further comprises: When the M channel information is determined by the terminal device, sending a correspondence between the M channel information and the L channel information; When the precision categories corresponding to the M channel information are determined by the terminal device, the precision categories respectively corresponding to the M channel information are sent. The method according to any one of claims 14 to 25, characterized in that the reconstructing the first sequence to obtain the M channel information comprises: Determine a corresponding relationship between a stacking position of the M channel information at the decoder input end and a stacking position of the N channel information at the decoder input end; The M channel information is determined according to the corresponding relationship. The method according to any one of claims 14-26 is characterized in that the decoder is used in a network device. A communication device, characterized in that it comprises a unit for executing the method described in any one of claims 1 to 13 or 14 to 27. A communication device, characterized in that it includes a processor, the processor is coupled to a memory, the memory is used to store computer programs or instructions, and the processor is used to execute the computer program or instructions in the memory, so that the device executes the method as described in any one of claims 1 to 13, or executes the method as described in any one of claims 14 to 27. A computer-readable storage medium, characterized in that a computer program or instruction is stored on the computer-readable storage medium, and when the computer program or instruction is executed on a computer, the computer executes the method as described in any one of claims 1 to 13; or, the method as described in any one of claims 14 to 27. A chip system, characterized in that it includes: a processor, used to call and run a computer program from a memory, so that a communication device equipped with the chip system executes the method described in any one of claims 1 to 13, or executes the method described in any one of claims 14 to 27. A computer program product, characterized in that when the computer program product is run on a computer, the computer is caused to execute the steps of the method according to any one of claims 1 to 13, or execute the steps of the method according to any one of claims 14 to 27.