WO2024140578A1 - Csi feedback method based on ai model, terminal, and network side device - Google Patents

Abstract

The present application relates to the technical field of communications, and discloses a channel state information (CSI) feedback method based on an AI model, a terminal, and a network side device. The CSI feedback method based on the AI model in embodiments of the present application comprises: according to a priority, a terminal groups channel feature information of at least one layer after compression of the AI model so as to obtain N groups; and the terminal reports CSI to a network side device on the basis of the N groups. The priority of the channel feature information in each group is identical. The N groups satisfy at least one of the following: each group is obtained by performing grouping on the basis of target information, wherein the target information comprises the length or proportion of the channel feature information of each layer comprised in N-1 groups; each group is obtained by performing grouping on the basis of the priority ranking of the channel feature information; each group is obtained by performing grouping on the basis of layers; and each group is obtained by performing grouping on the basis of segmentation of the channel feature information in each layer.

Description

CSI feedback method, terminal and network side equipment based on AI model

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese Patent Application No. 202211690213.2 filed in China on December 27, 2022, the entire contents of which are incorporated herein by reference.

Technical Field

The present application belongs to the field of communication technology, and specifically relates to a CSI feedback method, terminal and network side equipment based on an AI model.

Background technique

Accurate channel state information (CSI) is crucial to improving channel capacity. Especially for multi-antenna systems, the transmitter can optimize the signal transmission based on CSI to make it more compatible with the channel status. For example, the Channel Quality Indicator (CQI) can be used to select the appropriate Modulation And Coding Scheme (MCS) to achieve link adaptation; the Precoding Matrix Indicator (PMI) can be used to achieve Eigen Beamforming to maximize the strength of the received signal, or to suppress interference (such as interference between cells, interference between multiple users, etc.).

In order to reduce the CSI feedback overhead, the CSI can be compressed and then fed back. For example, the base station can pre-code the Channel State Information-Reference Signal (CSI-RS) in advance and send the encoded CSI-RS to the terminal. The terminal monitors the channel corresponding to the encoded CSI-RS. The terminal only needs to select several ports with greater strength from the ports indicated by the network side device and report the coefficients corresponding to these ports. CSI (such as coefficients) can be mapped to the Physical Uplink Shared Channel (PUSCH) or the Physical Uplink Control Channel (PUCCH) for reporting. When resources are insufficient, some information needs to be discarded, such as discarding the low priority first. The CSI coefficients in the above scheme are obtained based on the codebook. Each coefficient has its own meaning, and the priority of the coefficient can be determined according to the corresponding port, subband and other information. Further, in order to better compress channel information, neural network or machine learning methods can be used. However, since all the information in the CSI compressed by the artificial intelligence (AI) model is compressed together, it is impossible to determine the priority according to the corresponding physical port or sub-band information. In the case of insufficient resources, it is impossible to discard based on priority. Therefore, how to better implement CSI feedback based on the AI model is a problem that needs to be solved.

Summary of the invention

The embodiments of the present application provide a CSI feedback method, terminal, and network-side device based on an AI model, which can solve the problem of how to better implement CSI feedback based on an AI model.

In a first aspect, a CSI feedback method based on an AI model is provided, including:

The terminal groups the channel characteristic information of at least one layer compressed by the AI model according to the priority to obtain N groups;

The terminal reports the channel state information to the network side device based on the N groups; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0;

The N groups satisfy at least one of the following conditions:

Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups;

Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information;

Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information;

Each of the groups is obtained by grouping based on layers;

Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

In the second aspect, a CSI feedback method based on an AI model is provided, including:

The network side device receives the channel state information reported by the terminal based on N groups; the N groups are obtained by grouping the channel characteristic information of at least one layer after the AI model is compressed according to the priority; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0;

The N groups satisfy at least one of the following conditions:

Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups;

Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information;

Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information;

Each of the groups is obtained by grouping based on layers;

Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

In a third aspect, a CSI feedback device based on an AI model is provided, comprising:

A processing module, used for grouping the channel feature information of at least one layer compressed by the AI model according to the priority to obtain N groups;

A sending module, used to report channel state information to a network side device based on the N groups; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0;

The N groups satisfy at least one of the following conditions:

Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups;

Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information;

Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information;

Each of the groups is obtained by grouping based on layers;

Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

In a fourth aspect, a CSI feedback device based on an AI model is provided, comprising:

A receiving module, configured to receive channel state information reported by the terminal based on N groups; the N groups are obtained by grouping the channel characteristic information of at least one layer compressed by the AI model according to priority; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0;

The N groups satisfy at least one of the following conditions:

Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups;

Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information;

Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information;

Each of the groups is obtained by grouping based on layers;

Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

In a fifth aspect, a terminal is provided, comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

In the sixth aspect, a terminal is provided, comprising a processor and a communication interface, wherein the processor is used to group the channel characteristic information of at least one layer after compression of the AI model according to priority to obtain N groups; the communication interface is used to report channel status information to the network side device based on the N groups; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0; the N groups satisfy at least one of the following conditions: each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 groups; or, the proportion of the channel characteristic information of each layer included in N-1 groups; each of the groups is grouped based on the priority sorting of the channel characteristic information; each of the groups is grouped based on the priority sorting of the channel characteristic information and based on the target information; each of the groups is grouped based on layers; each of the groups is grouped based on the segmentation of the channel characteristic information in each layer.

In the seventh aspect, a network side device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the second aspect are implemented.

In an eighth aspect, a network side device is provided, including a processor and a communication interface, wherein the communication interface is used to receive channel state information reported by the terminal based on N groups; the N groups are obtained by grouping the channel feature information of at least one layer after compression of the AI model according to priority; the priority of the channel feature information in each group is the same; N is an integer greater than 0; the N groups satisfy at least one of the following conditions: each of the groups is obtained by grouping based on target information; the target information includes: N-1 The length of the channel characteristic information of each layer included in the group; or, the ratio of the channel characteristic information of each layer included in N-1 groups; each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information; each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information and based on the target information; each of the groups is obtained by grouping based on layers; each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

In the ninth aspect, a communication system is provided, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the CSI feedback method based on the AI model as described in the first aspect, and the network side device can be used to execute the steps of the CSI feedback method based on the AI model as described in the second aspect.

In the tenth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented.

In the eleventh aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect, or to implement the method described in the second aspect.

In the twelfth aspect, a computer program/program product is provided, wherein the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the steps of the CSI feedback method based on the AI model as described in the first aspect or the CSI feedback method based on the AI model as described in the second aspect.

In an embodiment of the present application, the terminal groups the channel characteristic information of at least one layer after compression of the AI model according to priority to obtain N groups; the terminal reports channel status information to the network side device based on the N groups; the N groups satisfy at least one of the following conditions: each group is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 groups; or, the proportion of the channel characteristic information of each layer included in N-1 groups; each group is grouped after priority sorting based on the channel characteristic information; each group is grouped after priority sorting based on the channel characteristic information and based on the target information; each group is grouped based on layers; each group is grouped based on segmentation of the channel characteristic information in each layer. Since the priority of the channel characteristic information in each group is the same, if resources are insufficient during transmission, it can be discarded according to the group, thereby better realizing CSI feedback based on the AI model.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a structural diagram of a wireless communication system applicable to an embodiment of the present application;

FIG2 is a flow chart of a CSI feedback method based on an AI model provided in an embodiment of the present application;

FIG3 is a second flow chart of a CSI feedback method based on an AI model provided in an embodiment of the present application;

FIG4 is a schematic diagram of a structure of a CSI feedback device based on an AI model provided in an embodiment of the present application;

FIG5 is a second structural diagram of a CSI feedback device based on an AI model provided in an embodiment of the present application;

FIG6 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application;

FIG7 is a schematic diagram of the structure of a terminal provided in an embodiment of the present application;

FIG8 is a schematic diagram of the structure of a network side device according to an embodiment of the present application.

Detailed ways

The technical solution in the embodiment of the present application will be clearly described below in conjunction with the accompanying drawings in the embodiment of the present application. It is obvious that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the protection scope of the present application.

The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, but not to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and/or" in the specification and claims represents at least one of the connected objects, and the character "/" generally indicates that the objects associated with each other are in an "or" relationship. The term "indication" in the specification and claims of the present application can be either an explicit indication or an implicit indication. Among them, an explicit indication can be understood as the sender explicitly notifying the receiver of the operation or request result to be performed in the indication sent; an implicit indication can be understood as the receiver making a judgment based on the indication sent by the sender and determining the operation or request result to be performed based on the judgment result.

It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE)/LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used for the above-mentioned systems and radio technologies as well as other systems and radio technologies. The following description describes a new radio (NR) system for example purposes, and NR terms are used in most of the following descriptions, but these technologies can also be applied to applications other than NR system applications, such as the ^6th Generation (6G) communication system.

FIG1 shows a block diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes a terminal 11 and a network side device 12 . Among them, the terminal 11 can be a mobile phone, a tablet personal computer, a laptop computer or a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile Internet device (MID), an augmented reality (AR)/virtual reality (VR) device, a robot, a wearable device (Wearable Device), a vehicle-mounted device (VUE), a pedestrian terminal (PUE), a smart home (home appliances with wireless communication functions, such as refrigerators, televisions, washing machines or furniture, etc.), a game console, a personal computer (personal computer, PC), a teller machine or a self-service machine and other terminal side devices, and the wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing Etc. In addition to the above-mentioned terminal devices, it can also be a chip in the terminal, such as a modem chip, a system-on-chip (SoC). It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device 12 may also be referred to as a radio access network device, a radio access network (RAN), a radio access network function or a radio access network unit. The access network device 12 may include a base station, a WLAN access point or a WiFi node, etc. The base station may be referred to as a node B, an evolved node B (eNB), an access point, a base transceiver station (Base Transceiver Station, BTS), a radio base station, a radio transceiver, a basic service set (Basic Service Set, BSS), an extended service set (Extended Service Set, ESS), a home B node, a home evolved B node, a transmitting and receiving point (Transmitting Receiving Point, TRP) or some other suitable term in the field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited. The core network equipment may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (Mobility Management Entity, MME), access mobility management function (Access and Mobility Management Function, AMF), session management function (Session Management Function, SMF), user plane function (User Plane Function, UPF), policy control function (Policy Control Function, PCF), policy and charging rules function unit (Policy and Charging Rules Function, PCRF), edge application service discovery function (Edge Application Server Discovery Function, EASDF), unified data management (Unified Data Management, UDM), unified data storage (Unified Data Repository, UDR), home user server (Home Subscriber Server, HSS), centralized network configuration (CNC), network storage function (Network Repository Function, NRF), network exposure function (Network Exposure Function, NEF), local NEF (Local NEF, or L-NEF), binding support function (Binding Support Function, BSF), application function (Application Function, AF), etc. It should be noted that in the embodiments of the present application, only the core network device in the NR system is introduced as an example, and the specific type of the core network device is not limited.

In order to facilitate a clearer understanding of the embodiments of the present application, some relevant background knowledge is first introduced as follows.

Usually, the base station sends a CSI reference signal (CSI Reference Signal, CSI-RS) on certain time-frequency resources in a time slot. The terminal performs channel estimation based on the CSI-RS, calculates the channel information on this slot, and feeds back the PMI to the base station through the codebook. The base station combines the channel information based on the codebook information fed back by the terminal, and performs data precoding and multi-user scheduling before the next CSI report.

In order to further reduce the CSI feedback overhead, the terminal can change the PMI reported in each subband to reporting PMI according to delay. Since the channels in the delay domain are more concentrated, the PMI of all subbands can be approximately represented by PMIs with fewer delays, that is, the delay domain information is compressed before reporting.

Similarly, in order to reduce the overhead, the base station can pre-code the CSI-RS in advance and convert the coded CSI-RS When sent to the terminal, what the terminal sees is the channel corresponding to the encoded CSI-RS. The terminal only needs to select several ports with greater strength from the ports indicated by the network side and report the coefficients corresponding to these ports.

Furthermore, in order to better compress channel information, neural network or machine learning methods can be used.

Artificial intelligence has been widely used in various fields. There are many ways to implement AI modules, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. This application uses neural networks as an example for illustration, but does not limit the specific type of AI modules.

The process of compressing and recovering CSI is as follows: the terminal estimates CSI-RS, calculates channel information, obtains the encoding result through the calculated channel information or the original estimated channel information through the encoding network, and sends the encoding result to the base station. The base station receives the encoded result and inputs it into the decoding network to recover the channel information.

Specifically, the CSI compression feedback scheme based on the neural network (i.e., AI model) is: the terminal uses the coding network to compress and encode the channel information, sends the compressed content to the base station, and uses the decoding network at the base station to decode the compressed content to restore the channel information. At this time, the decoding network of the base station and the coding network of the terminal need to be jointly trained to achieve a reasonable match. The input of the coding model is the channel information, and the output is the coding information. The input of the decoding model is the coding information, and the output is the restored channel information.

The coding model can output quantized 01bit or floating point or complex number. The terminal uses other quantization methods for quantization. The dequantization process of the former is completed by the decoding model, and the dequantization process of the latter is completed before the decoding model. The base station decodes the floating point or complex number after dequantization through the AI model.

When the Physical Uplink Shared Channel (PUSCH) or Physical Uplink Control Channel (PUCCH) resources are insufficient, some CSI needs to be discarded to ensure that the remaining information can be transmitted correctly. The retained CSI needs to carry as much information as possible. There is a certain priority relationship between the various CSI coefficients, and the coefficients with low priority are discarded first.

In the related technology, CSI is divided into part 1 and part 2, and part 2 is divided into group 0, group 1 and group 2. During the discarding process, group 2 is discarded first, followed by group 1. The terminal will sort all coefficients that need to be reported according to certain rules, and put several coefficients with higher priority into group 1, and some coefficients with lower priority into group 2. This solution is for the codebook, without considering the AI model. The coefficients of the codebook usually have physical meanings, such as which ports are selected, which delays are selected, how many coefficients are reported, which coefficients are non-zero, and what the specific coefficients are. The so-called priority rules are mainly for specific coefficients, and other parameters will be directly agreed in the protocol to be in which part or which group.

For CSI feedback based on AI models, since the AI model outputs floating points or bit streams without specific physical meaning, the corresponding information can only be obtained through the decoding model. In other words, it cannot be split into what each coefficient represents, and the priority division rules of the code book cannot be used.

In the following, in combination with the accompanying drawings, the CSI feedback method based on the AI model provided in the embodiment of the present application is described in detail through some embodiments and their application scenarios.

FIG2 is a flow chart of a CSI feedback method based on an AI model provided in an embodiment of the present application. As shown in FIG2 , the method provided in this embodiment includes:

Step 101: The terminal groups the channel characteristic information of at least one layer compressed by the AI model according to the priority to obtain N groups; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0;

Specifically, an AI model is also called an AI unit, which can be an AI model, an AI module, or an operation rule with AI/machine learning (ML) functions.

The N groups satisfy at least one of the following conditions:

Each group is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in the N-1 groups; or, the proportion of the channel characteristic information of each layer included in the N-1 groups;

Each group is obtained by grouping based on the priority sorting of channel characteristic information;

Each group is obtained by sorting the priorities based on the channel characteristic information and grouping based on the target information;

Each group is obtained by grouping based on the layer;

Each group is obtained by grouping based on the segmentation of channel characteristic information in each layer.

Optionally, the channel characteristic information is a floating point number output by the AI model, a non-zero value output by the AI model, a coefficient greater than a first threshold value output by the AI model, or a quantized non-zero value.

Specifically, the target information may indicate the length of the channel characteristic information of a certain priority for each layer (for example, it may also be represented by the number of coefficients of the channel characteristic information, and the two metrics may be the same or different); or, it may indicate the length or ratio of the channel characteristic information of each layer corresponding to group 1, that is, the low priority information; or, N groups are more than 2 groups, in which case it is necessary to indicate the information of at least N-1 groups;

For example, rank = 4, each layer reports 80 floating point numbers, the target information indicates that the first 40 are the first priority and the rest are the second priority, then the terminal uses the first 40 coefficients of each of the four layers as group 0 and the remaining coefficients as group 1. If the resources are insufficient, group 1 is discarded first;

For example, rank = 4, layer1 and layer2 report 80 floating point numbers respectively, layer3 and layer4 report 40 floating point numbers respectively, and the length indicated by the target information is 40, then the first 40 coefficients of layer1 and layer2 and the 40 coefficients of layer3 and layer4 are taken as group0, and the other coefficients of layer1 and layer2 are taken as group1;

For example, rank = 4, each layer reports 80 floating point numbers, and the target information indication ratio is α = 0.7, then the first 56 coefficients of each layer are group 0, and the remaining coefficients are group 1;

For example, rank=4, layer1 and layer2 report 80 floating point numbers respectively, layer3 and layer4 report 40 floating point numbers respectively, and the target information indicates that the ratio is α=0.7, then 56 coefficients of layer1 and layer2 respectively and 28 coefficients of layer3 and layer4 respectively are used as group0, and the other coefficients are used as group1.

Exemplarily, each group is obtained by grouping based on priority sorting of the channel characteristic information. For example, the coefficients of the channel characteristic information may be prioritized based on a preset formula, and the coefficients may be directly grouped in the sorted order.

Alternatively, the channels may be prioritized first based on the channel characteristic information, and then grouped based on the target information;

Or, group by layer, for example, layer1 and layer2 are in group0, layer3 and layer4 are in group1;

Exemplarily, for the segmented quantized channel characteristic information, the above priority is for the segment, that is, the segment is grouped, each segment is discarded together, and the segments with the same priority are taken as a group;

For example, rank=4, each layer reports 80 coefficients, which are divided into two segments, each with 40 coefficients, and quantized using the corresponding codebook. Then, the first segment of each layer can be used as group 0, and the other segments can be used as group 1.

Optionally, the number of segments of each layer can be the same or different. For example, rank = 4, layer1 and layer2 have 80 coefficients respectively, layer3 and layer4 have 40 coefficients respectively, layer1 and layer2 are divided into two segments, the first segment has 50 coefficients, the second segment has 30 coefficients, and layer3 and layer4 have only one segment. In this case, the first segment of layer1 and layer2 and layer3 and layer4 can be used as group0, and the others as group1; or the first segment of layer1 and layer2 can be used as group0, and the others as group1.

Step 102: The terminal reports channel state information to a network-side device based on N packets.

Specifically, in step 101, the terminal prioritizes the coefficients of the channel characteristic information of each layer according to certain rules, and reports the coefficients with the same priority (i.e., importance level) as a group. When insufficient resources occur and some information needs to be discarded, it is discarded in groups according to priority.

In the method of this embodiment, the terminal groups the channel characteristic information of at least one layer after compression of the AI model according to priority to obtain N groups; the terminal reports the channel status information to the network side device based on the N groups; the N groups satisfy at least one of the following conditions: each group is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 groups; or, the proportion of the channel characteristic information of each layer included in N-1 groups; each group is obtained by grouping based on priority sorting of the channel characteristic information; each group is obtained by grouping based on priority sorting of the channel characteristic information and based on target information; each group is obtained by grouping based on layers; each group is obtained by grouping based on segmentation of the channel characteristic information in each layer. Since the priority of the channel characteristic information in each group is the same, if resources are insufficient during transmission, they can be discarded according to the groups, thereby better realizing CSI feedback based on the AI model.

Optionally, the channel state information includes a first part and a second part, the first part is used to determine the length of the second part, and the second part is obtained by mapping the N groups.

Specifically, the first part is part1, and the second part is part2. For example, part2 includes groups group0, group1, group2, and the like.

Optionally, the first part includes at least one of the following: rank RI, channel quality indication (Channel Quality Indication, CQI), the total number of coefficients, quantization segment information, and quantization parameters of each segment.

The rank can be used to determine the number of data streams that can be sent simultaneously, that is, the number of layers. The quantization segment information includes, for example, the number of quantization segments, the number of coefficients included in each segment, etc. The quantization parameter includes: the number of quantization bits for scalar quantization, the quantization codebook for vector quantization, or the quantization parameter ID.

Optionally, the length or ratio of the channel characteristic information of each layer included in each group is different.

For example, the number of coefficients of layer1 and layer2 is 80 respectively, the corresponding length is 40, the number of coefficients of layer3 and layer4 is 40 and the corresponding length is 20, then the first 40 coefficients of layer1 and layer2 and the first 20 coefficients of layer3 and layer4 are group0, and the others are group1;

For example, layer1 and layer2 have 80 coefficients respectively, the corresponding ratio is α = 0.7, layer3 and layer4 have 40 coefficients respectively, the corresponding ratio is α = 0.5, then the first 56 coefficients of layer1 and layer2 and the first 20 coefficients of layer3 and layer4 are group0, and the others are group1;

Optionally, the target information is configured by a network-side device or agreed upon by a protocol.

Optionally, the target information is configured by the network side device alone, or configured together with other CSI parameters.

In the above implementation, grouping is performed based on target information, that is, the channel characteristic information included in each group is determined according to the fixed length or ratio of the channel characteristic information of each layer, and the channel characteristic information in each group has the same priority. When resources are insufficient, coefficients with the same priority can be discarded together, that is, coefficients with low priority are discarded first, to ensure that in the process of discarding coefficients, not all information of a layer is discarded, and reliability is high.

Optionally, in the case where the channel characteristic information is unsegmented scalar quantized channel characteristic information, each group is obtained by grouping based on target information, or each group is obtained by grouping based on priority sorting of the channel characteristic information.

Specifically, since there is no segmentation process in quantization, the channel characteristic information can be grouped based on the target information, or grouped after sorting, and then quantized.

Optionally, when the channel characteristic information is channel characteristic information after unsegmented scalar quantization, unsegmented vector quantization, segmented scalar quantization or segmented vector quantization, each group is obtained by grouping based on layers.

Optionally, in the case where the channel characteristic information is segmented scalar quantized or vector quantized channel characteristic information, each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

Specifically, for the quantization of segments, the priority is for the segments, that is, the segments are grouped as units, each segment is discarded together, and the segments with the same priority are taken as a group to ensure that the segments in each group are complete.

Among them, quantization can be done after grouping, but the segmentation information needs to be included in the grouping.

In the above implementation, for the segmented quantization operation, it is ensured that each segment is complete, that is, completely discarded or completely retained, which can prevent the overall dequantization failure caused by the loss of some segment information.

Optionally, step 102 may be implemented in the following manner:

The terminal sends channel state information to the network side device based on the transmission resources and N packets; the priority of the target packet included in the channel state information is greater than the priority of the remaining packets in the N packets except the target packet; or, the channel state information only includes the first part.

Specifically, the terminal treats the coefficients of the channel characteristic information with the same priority as a group according to the priority. When insufficient resources occur and some information needs to be discarded, the information is discarded in groups according to the priority, that is, reported. A higher priority group.

Optionally, when the transmission resources do not meet the transmission requirement of N packets, the channel state information only includes the first part.

For example, for unsegmented vector quantization, when the transmission resources do not meet the transmission requirement of N packets, the second part is directly discarded and only the first part is transmitted.

In the above implementation manner, the terminal reports the channel characteristic information based on the priority and transmission resources of the packets, and reports the packets with higher priority first, thereby improving the reliability of communication.

FIG3 is a second flow chart of the CSI feedback method based on the AI model provided in an embodiment of the present application. As shown in FIG3 , the method provided in this embodiment includes:

Step 201: The network side device receives channel state information reported by the terminal based on N groups; the N groups are obtained by grouping the channel characteristic information of at least one layer after the AI model is compressed according to the priority; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0;

The N groups satisfy at least one of the following conditions:

Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups;

Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information;

Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information;

Each of the groups is obtained by grouping based on layers;

Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

Optionally, the network side device can also use the AI model to decode, decompress and other operations on the received channel state information to obtain channel information.

Optionally, the length or proportion of the channel characteristic information of each layer included in each of the groups is different.

Optionally, the target information is configured by a network-side device or agreed upon by a protocol.

Optionally, the target information is configured by the network side device alone, or configured together with other CSI parameters.

Optionally, in the case where the channel characteristic information is unsegmented scalar quantized channel characteristic information, each of the groups is obtained by grouping based on target information, or each of the groups is obtained by grouping based on priority sorting of the channel characteristic information.

Optionally, when the channel characteristic information is channel characteristic information after unsegmented scalar quantization, unsegmented vector quantization, segmented scalar quantization or segmented vector quantization, each of the groups is obtained by grouping based on layers.

Optionally, the channel characteristic information is segmented scalar quantized or vector quantized channel characteristic information. In this case, each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

Optionally, the channel state information includes a first part and a second part, the first part is used to determine the length of the second part, and the second part is obtained by mapping the N groups.

Optionally, the priority of the target packet included in the channel state information is greater than the priority of the remaining packets in the N packets except the target packet; or, the channel state information only includes the first part.

Optionally, when the transmission resources do not meet the transmission requirements of the N packets, the channel state information only includes the first part.

Optionally, the channel characteristic information is a floating point number output by the AI model, a non-zero value output by the AI model, a coefficient greater than a first threshold value output by the AI model, or a quantized non-zero value.

Optionally, the first part includes at least one of the following: rank RI, channel quality indication CQI, total number of coefficients, quantization segment information, and quantization parameter of each segment.

The specific implementation process and technical effects of the method in this embodiment are the same as those in the terminal side method embodiment. For details, please refer to the detailed introduction in the terminal side method embodiment, and no further details will be given here.

The CSI feedback method based on the AI model provided in the embodiment of the present application can be executed by a CSI feedback device based on the AI model. In the embodiment of the present application, the CSI feedback method based on the AI model is executed by a CSI feedback device based on the AI model as an example to illustrate the CSI feedback device based on the AI model provided in the embodiment of the present application.

FIG4 is a schematic diagram of a structure of a CSI feedback device based on an AI model provided in an embodiment of the present application. As shown in FIG4 , the CSI feedback device based on an AI model provided in this embodiment includes:

A processing module 210 is used to group the channel feature information of at least one layer compressed by the AI model according to the priority to obtain N groups;

The sending module 220 is used to report the channel state information to the network side device based on the N groups; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0;

The N groups satisfy at least one of the following conditions:

Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups;

Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information;

Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information;

Each of the groups is obtained by grouping based on layers;

Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

Optionally, the length or proportion of the channel characteristic information of each layer included in each of the groups is different.

Optionally, the target information is configured by a network-side device or agreed upon by a protocol.

Optionally, the target information is configured by the network side device alone, or configured in conjunction with other CSI parameters. of.

Optionally, in the case where the channel characteristic information is unsegmented scalar quantized channel characteristic information, each of the groups is obtained by grouping based on target information, or each of the groups is obtained by grouping based on priority sorting of the channel characteristic information.

Optionally, when the channel characteristic information is channel characteristic information after unsegmented scalar quantization, unsegmented vector quantization, segmented scalar quantization or segmented vector quantization, each of the groups is obtained by grouping based on layers.

Optionally, in the case where the channel characteristic information is segmented scalar quantized or vector quantized channel characteristic information, each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

Optionally, the channel state information includes a first part and a second part, the first part is used to determine the length of the second part, and the second part is obtained by mapping the N groups.

Optionally, the sending module 220 is specifically configured to:

Based on the transmission resources and the N packets, the channel state information is sent to the network side device; the priority of the target packet included in the channel state information is greater than the priority of the remaining packets in the N packets except the target packet; or the channel state information only includes the first part.

Optionally, when the transmission resources do not meet the transmission requirements of the N packets, the channel state information only includes the first part.

Optionally, the channel characteristic information is a floating point number output by the AI model, a non-zero value output by the AI model, a coefficient greater than a first threshold value output by the AI model, or a quantized non-zero value.

Optionally, the first part includes at least one of the following: rank RI, channel quality indication CQI, total number of coefficients, quantization segment information, and quantization parameter of each segment.

The device of this embodiment can be used to execute the method of any of the embodiments in the aforementioned terminal side method embodiments. Its specific implementation process and technical effects are the same as those in the terminal side method embodiments. For details, please refer to the detailed introduction in the terminal side method embodiments, which will not be repeated here.

FIG5 is a second structural diagram of a CSI feedback device based on an AI model provided in an embodiment of the present application. As shown in FIG5 , the CSI feedback device based on an AI model provided in this embodiment includes:

The receiving module 310 is used to receive the channel state information reported by the terminal based on N groups; the N groups are obtained by grouping the channel characteristic information of at least one layer after the AI model is compressed according to the priority; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0;

The N groups satisfy at least one of the following conditions:

Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups;

Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information;

Each of the groups is prioritized based on the channel characteristic information and sorted based on the target information. The rows are grouped;

Each of the groups is obtained by grouping based on layers;

Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

Optionally, the length or proportion of the channel characteristic information of each layer included in each of the groups is different.

Optionally, the target information is configured by a network-side device or agreed upon by a protocol.

Optionally, the target information is configured by the network side device alone, or configured together with other CSI parameters.

Optionally, in the case where the channel characteristic information is unsegmented scalar quantized channel characteristic information, each of the groups is obtained by grouping based on target information, or each of the groups is obtained by grouping based on priority sorting of the channel characteristic information.

Optionally, when the channel characteristic information is channel characteristic information after unsegmented scalar quantization, unsegmented vector quantization, segmented scalar quantization or segmented vector quantization, each of the groups is obtained by grouping based on layers.

Optionally, in the case where the channel characteristic information is segmented scalar quantized or vector quantized channel characteristic information, each of the groups is obtained by grouping based on the segments of the channel characteristic information in each layer.

Optionally, the channel state information includes a first part and a second part, the first part is used to determine the length of the second part, and the second part is obtained by mapping the N groups.

Optionally, the priority of the target packet included in the channel state information is greater than the priority of the remaining packets in the N packets except the target packet; or, the channel state information only includes the first part.

Optionally, when the transmission resources do not meet the transmission requirements of the N packets, the channel state information only includes the first part.

Optionally, the channel characteristic information is a floating point number output by the AI model, a non-zero value output by the AI model, a coefficient greater than a first threshold value output by the AI model, or a quantized non-zero value.

Optionally, the first part includes at least one of the following: rank RI, channel quality indication CQI, total number of coefficients, quantization segment information, and quantization parameter of each segment.

The device of this embodiment can be used to execute the method of any of the embodiments in the aforementioned network side device side method embodiments. Its specific implementation process and technical effects are the same as those in the network side device side method embodiments. For details, please refer to the detailed introduction in the network side device side method embodiments, which will not be repeated here.

The AI model-based CSI feedback device in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than a terminal. Exemplarily, the terminal can include but is not limited to the types of terminals 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

The AI model-based CSI feedback device provided in the embodiment of the present application can implement the various processes implemented in the method embodiments of Figures 2 to 3 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

Optionally, as shown in FIG6 , the embodiment of the present application further provides a communication device 600, including a processor 601 and a memory 602, wherein the memory 602 stores a program or instruction that can be run on the processor 601. For example, when the communication device 600 is a terminal, the program or instruction is executed by the processor 601 to implement the various steps of the above-mentioned CSI feedback method embodiment based on the AI model, and can achieve the same technical effect. When the communication device 600 is a network side device, the program or instruction is executed by the processor 601 to implement the various steps of the above-mentioned CSI feedback method embodiment based on the AI model, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

The embodiment of the present application further provides a terminal, including a processor and a communication interface, wherein the processor is used to group the channel characteristic information of at least one layer compressed by the AI model according to the priority to obtain N groups; the communication interface is used to report the channel state information to the network side device based on the N groups; the priority of the channel characteristic information in each of the groups is the same; N is an integer greater than 0; the N groups satisfy at least one of the following conditions:

Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups;

Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information;

Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information;

Each of the groups is obtained by grouping based on layers;

Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

This terminal embodiment corresponds to the above-mentioned terminal side method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to this terminal embodiment, and can achieve the same technical effect. Specifically, Figure 7 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application. The terminal 1000 includes but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and at least some of the components in the processor 1010.

Those skilled in the art will appreciate that the terminal 1000 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 1010 through a power management system, so as to manage charging, discharging, and power consumption management through the power management system. The terminal structure shown in FIG7 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently, which will not be described in detail here.

It should be understood that in the embodiment of the present application, the input unit 1004 may include a graphics processing unit (GPU) 10041 and a microphone 10042, and the graphics processor 10041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 1006 may include a display panel 10061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1007 includes a touch panel 10071 and at least one of other input devices 10072. Touch panel 10071 is also called a touch screen. Touch panel 10071 may include two parts: a touch detection device and a touch controller. Other input devices 10072 may include but are not limited to a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

In the embodiment of the present application, after receiving the downlink data from the network side device, the RF unit 1001 can transmit it to the processor 1010 for processing; in addition, the RF unit 1001 can send the uplink data to the network side device. Generally, the RF unit 1001 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

The memory 1009 can be used to store software programs or instructions and various data. The memory 1009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 1009 may include a volatile memory or a non-volatile memory, or the memory 1009 may include a transient and non-transient memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 1009 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

The processor 1010 may include one or more processing units; optionally, the processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs or instructions, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 1010.

The processor 1010 is used to group the channel feature information of at least one layer compressed by the AI model according to the priority to obtain N groups;

The radio frequency unit 1001 is used to report the channel state information to the network side device based on the N groups; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0;

The N groups satisfy at least one of the following conditions:

Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups;

Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information;

Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information;

Each of the groups is obtained by grouping based on layers;

Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer.

Optionally, the length or proportion of the channel characteristic information of each layer included in each of the groups is different.

Optionally, the target information is configured by a network-side device or agreed upon by a protocol.

Optionally, the target information is configured by the network side device alone, or configured together with other CSI parameters.

Optionally, in the case where the channel characteristic information is unsegmented scalar quantized channel characteristic information, each of the groups is obtained by grouping based on target information, or each of the groups is obtained by grouping based on priority sorting of the channel characteristic information.

Optionally, when the channel characteristic information is channel characteristic information after unsegmented scalar quantization, unsegmented vector quantization, segmented scalar quantization or segmented vector quantization, each of the groups is obtained by grouping based on layers.

Optionally, in the case where the channel characteristic information is segmented scalar quantized or vector quantized channel characteristic information, each of the groups is obtained by grouping based on the segments of the channel characteristic information in each layer.

Optionally, the channel state information includes a first part and a second part, the first part is used to determine the length of the second part, and the second part is obtained by mapping the N groups.

Optionally, the radio frequency unit 1001 is specifically configured to:

Based on the transmission resources and the N packets, the channel state information is sent to the network side device; the priority of the target packet included in the channel state information is greater than the priority of the remaining packets in the N packets except the target packet; or the channel state information only includes the first part.

Optionally, when the transmission resources do not meet the transmission requirements of the N packets, the channel state information only includes the first part.

Optionally, the channel characteristic information is a floating point number output by the AI model, a non-zero value output by the AI model, a coefficient greater than a first threshold value output by the AI model, or a quantized non-zero value.

Optionally, the first part includes at least one of the following: rank RI, channel quality indication CQI, total number of coefficients, quantization segment information, and quantization parameter of each segment.

The terminal of this embodiment can be used to execute the CSI feedback method based on the AI model in the aforementioned terminal side embodiment. Its specific implementation process and technical effects are similar to those in the terminal side method embodiment. For details, please refer to the detailed description in the terminal side method embodiment, which will not be repeated here.

The embodiment of the present application also provides a network side device, including a processor and a communication interface, the communication interface is used to receive the channel state information reported by the terminal based on N groups; the N groups are obtained by grouping the channel feature information of at least one layer after the AI model is compressed according to the priority; the channel feature information in each group The information has the same priority; N is an integer greater than 0; and the N groups satisfy at least one of the following conditions:

Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups;

Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information;

Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information;

Each of the groups is obtained by grouping based on layers;

Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer. This network side device embodiment corresponds to the above network side device method embodiment, and each implementation process and implementation method of the above method embodiment can be applied to the network side device embodiment and can achieve the same technical effect, which will not be repeated here.

Specifically, the embodiment of the present application also provides a network side device. As shown in FIG8 , the network side device 700 includes: an antenna 71, a radio frequency device 72, a baseband device 73, a processor 75, and a memory 75. The antenna 71 is connected to the radio frequency device 72. In the uplink direction, the radio frequency device 72 receives information through the antenna 71 and sends the received information to the baseband device 73 for processing. In the downlink direction, the baseband device 73 processes the information to be sent and sends it to the radio frequency device 72. The radio frequency device 72 processes the received information and sends it out through the antenna 71.

The frequency band processing device mentioned above may be located in the baseband device 73 . The method executed by the network-side device in the above embodiment may be implemented in the baseband device 73 . The baseband device 73 includes a baseband processor 75 and a memory 75 .

The baseband device 73 may include, for example, at least one baseband board, on which a plurality of chips are arranged, as shown in FIG8 , wherein one of the chips is, for example, a baseband processor 75, which is connected to the memory 75 via a bus interface to call a program in the memory 75 and execute the network device operations shown in the above method embodiment.

The network side device of the baseband device 73 may also include a network interface 76 for exchanging information with the radio frequency device 72. The interface may be, for example, a common public radio interface (CPRI).

Specifically, the network side device 700 of the embodiment of the present application also includes: instructions or programs stored in the memory 75 and executable on the processor 75. The processor 75 calls the instructions or programs in the memory 75 to execute the method of module execution shown in Figure 5 and achieves the same technical effect. To avoid repetition, it will not be repeated here.

An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned AI model-based CSI feedback method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

The present application also provides a chip, the chip comprising a processor and a communication interface, the communication interface The port is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned AI model-based CSI feedback method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

The embodiment of the present application further provides a computer program/program product, which is stored in a storage medium, and is executed by at least one processor to implement the various processes of the above-mentioned AI model-based CSI feedback method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

An embodiment of the present application also provides a communication system, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the CSI feedback method based on the AI model as described above, and the network side device can be used to execute the steps of the CSI feedback method based on the AI model as described above.

It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims (29)

A channel state information (CSI) feedback method based on an artificial intelligence (AI) model, comprising: The terminal groups the channel characteristic information of at least one layer compressed by the AI model according to the priority to obtain N groups; The terminal reports the channel state information to the network side device based on the N groups; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0; The N groups satisfy at least one of the following conditions: Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups; Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information; Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information; Each of the groups is obtained by grouping based on layers; Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer. The CSI feedback method based on the AI model according to claim 1, wherein: The length or ratio of the channel characteristic information of each layer included in each of the groups is different. The CSI feedback method based on the AI model according to claim 1, wherein: The target information is configured by the network side device or agreed upon by the protocol. The CSI feedback method based on the AI model according to claim 1, wherein: The target information is configured by the network side device alone, or configured in conjunction with other CSI parameters. The CSI feedback method based on the AI model according to claim 1, wherein: In the case where the channel characteristic information is unsegmented scalar quantized channel characteristic information, each of the groups is obtained by grouping based on target information, or each of the groups is obtained by grouping based on priority sorting of the channel characteristic information. The CSI feedback method based on the AI model according to claim 1, wherein: In the case where the channel characteristic information is channel characteristic information after unsegmented scalar quantization, unsegmented vector quantization, segmented scalar quantization or segmented vector quantization, each of the groups is obtained by grouping based on layers. The CSI feedback method based on the AI model according to claim 1, wherein: In the case where the channel characteristic information is segmented scalar quantized or vector quantized channel characteristic information, each of the groups is obtained by grouping based on the segments of the channel characteristic information in each layer. The CSI feedback method based on the AI model according to any one of claims 1 to 7, wherein: The channel state information includes a first part and a second part, the first part is used to determine the length of the second part, and the second part is obtained by mapping the N groups. The CSI feedback method based on the AI model according to claim 8, wherein the terminal reports the channel state information to the network side device based on the N packets, comprising: The terminal sends the channel state information to the network side device based on the transmission resources and the N packets; the priority of the target packet included in the channel state information is greater than the priority of the remaining packets in the N packets except the target packet; or the channel state information only includes the first part. The CSI feedback method based on the AI model according to claim 9, wherein: In a case where the transmission resources do not meet the transmission requirement of the N packets, the channel state information only includes the first part. The CSI feedback method based on the AI model according to any one of claims 1 to 7, wherein: The channel characteristic information is a floating point number output by the AI model, a non-zero value output by the AI model, a coefficient greater than a first threshold value output by the AI model, or a quantized non-zero value. The CSI feedback method based on the AI model according to claim 8, wherein: The first part includes at least one of the following: rank RI, channel quality indication CQI, the total number of coefficients, quantization segment information, and quantization parameter of each segment. A CSI feedback method based on an AI model, comprising: The network side device receives the channel state information reported by the terminal based on N groups; the N groups are obtained by grouping the channel characteristic information of at least one layer after the AI model is compressed according to the priority; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0; The N groups satisfy at least one of the following conditions: Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups; Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information; Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information; Each of the groups is obtained by grouping based on layers; Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer. The CSI feedback method based on the AI model according to claim 13, wherein: The length or ratio of the channel characteristic information of each layer included in each of the groups is different. The CSI feedback method based on the AI model according to claim 13, wherein: The target information is configured by the network side device or agreed upon by the protocol. The CSI feedback method based on the AI model according to claim 13, wherein: The target information is configured by the network side device alone, or configured together with other CSI parameters. The CSI feedback method based on the AI model according to any one of claims 13 to 16, wherein: In the case where the channel characteristic information is unsegmented scalar quantized channel characteristic information, each of the groups is obtained by grouping based on target information, or each of the groups is obtained by grouping based on priority sorting of the channel characteristic information. The CSI feedback method based on the AI model according to any one of claims 13 to 16, wherein: In the case where the channel characteristic information is channel characteristic information after unsegmented scalar quantization, unsegmented vector quantization, segmented scalar quantization or segmented vector quantization, each of the groups is obtained by grouping based on layers. The CSI feedback method based on the AI model according to any one of claims 13 to 16, wherein: In the case where the channel characteristic information is segmented scalar quantized or vector quantized channel characteristic information, each of the groups is obtained by grouping based on the segments of the channel characteristic information in each layer. The CSI feedback method based on the AI model according to any one of claims 13 to 16, wherein: The channel state information includes a first part and a second part, the first part is used to determine the length of the second part, and the second part is obtained by mapping the N groups. The AI model-based CSI feedback method according to claim 20, wherein: The priority of the target packet included in the channel state information is greater than the priorities of the remaining packets among the N packets except the target packet; or, the channel state information only includes the first part. The CSI feedback method based on the AI model according to claim 21, wherein: In a case where the transmission resources do not meet the transmission requirement of the N packets, the channel state information only includes the first part. The CSI feedback method based on the AI model according to any one of claims 13 to 16, wherein: The channel characteristic information is a floating point number output by the AI model, a non-zero value output by the AI model, a coefficient greater than a first threshold value output by the AI model, or a quantized non-zero value. The AI model-based CSI feedback method according to claim 20, wherein: The first part includes at least one of the following: rank RI, channel quality indication CQI, the total number of coefficients, quantization segment information, and quantization parameter of each segment. A CSI feedback device based on an AI model, comprising: A processing module, used for grouping the channel feature information of at least one layer compressed by the AI model according to the priority to obtain N groups; A sending module, used to report channel state information to a network side device based on the N groups; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0; The N groups satisfy at least one of the following conditions: Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups; Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information; Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information; Each of the groups is obtained by grouping based on layers; Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer. A CSI feedback device based on an AI model, comprising: A receiving module, configured to receive channel state information reported by a terminal based on N groups; the N groups are obtained by grouping the channel characteristic information of at least one layer after compression of the AI model according to priority; the priority of the channel characteristic information in each group is the same; N is an integer greater than 0; The N groups satisfy at least one of the following conditions: Each of the groups is obtained by grouping based on target information; the target information includes: the length of the channel characteristic information of each layer included in N-1 of the groups; or, the ratio of the channel characteristic information of each layer included in N-1 of the groups; Each of the groups is obtained by grouping based on the priority sorting of the channel characteristic information; Each of the groups is obtained by sorting the priority of the channel characteristic information and grouping based on the target information; Each of the groups is obtained by grouping based on layers; Each of the groups is obtained by grouping based on the segmentation of the channel characteristic information in each layer. A terminal comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the CSI feedback method based on the AI model as described in any one of claims 1 to 12 are implemented. A network side device comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the CSI feedback method based on the AI model as described in any one of claims 13 to 24 are implemented. A readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the CSI feedback method based on the AI model as described in any one of claims 1 to 12, or implements the steps of the CSI feedback method based on the AI model as described in any one of claims 13 to 24.