[go: up one dir, main page]

WO2024207367A1 - 信道状态信息的上报方法和装置 - Google Patents

信道状态信息的上报方法和装置 Download PDF

Info

Publication number
WO2024207367A1
WO2024207367A1 PCT/CN2023/086721 CN2023086721W WO2024207367A1 WO 2024207367 A1 WO2024207367 A1 WO 2024207367A1 CN 2023086721 W CN2023086721 W CN 2023086721W WO 2024207367 A1 WO2024207367 A1 WO 2024207367A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
model
terminal device
csi
network side
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2023/086721
Other languages
English (en)
French (fr)
Inventor
刘正宣
刘敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Xiaomi Mobile Software Co Ltd
Original Assignee
Beijing Xiaomi Mobile Software Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Xiaomi Mobile Software Co Ltd filed Critical Beijing Xiaomi Mobile Software Co Ltd
Priority to CN202380008963.3A priority Critical patent/CN119096583A/zh
Priority to PCT/CN2023/086721 priority patent/WO2024207367A1/zh
Publication of WO2024207367A1 publication Critical patent/WO2024207367A1/zh
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/10Scheduling measurement reports ; Arrangements for measurement reports

Definitions

  • the present disclosure relates to the field of communication technology, and in particular to a method and device for reporting channel state information.
  • the disclosed embodiments provide a method and apparatus for reporting channel state information, which can enable a terminal device to report CSI including quantized information obtained by processing downlink channel information by a first model corresponding to each layer or a specific rank, so that a network side device can obtain accurate CSI.
  • an embodiment of the present disclosure provides a method for reporting channel state information, which is executed by a terminal device.
  • the method includes: the terminal device reports CSI to a network side device, wherein the CSI includes quantized information obtained by processing the downlink channel information by a first model corresponding to each layer or a specific rank.
  • the terminal device reports CSI to the network side device, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the terminal device can report CSI including quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information, so that the network side device can obtain accurate CSI.
  • an embodiment of the present disclosure provides another method for reporting channel state information, which is executed by a network side device, and the method includes: receiving CSI reported by a terminal device, wherein the CSI includes quantized information obtained by processing the downlink channel information by a first model corresponding to each layer or a specific rank.
  • an embodiment of the present disclosure provides a communication device, which has some or all of the functions of the terminal device in the method described in the first aspect above.
  • the functions of the communication device may have some or all of the functions in the embodiments of the present disclosure, or may have the functions of implementing any one of the embodiments of the present disclosure alone.
  • the functions may be implemented by hardware, or by hardware executing corresponding software.
  • the hardware or software includes one or more units or modules corresponding to the above functions.
  • the structure of the communication device may include a transceiver module and a processing module, and the processing module is configured to support the communication device to perform the corresponding functions in the above method.
  • the transceiver module is used to support communication between the communication device and other devices.
  • the communication device may also include a storage module, which is coupled to the transceiver module and the processing module, and stores computer programs and data necessary for the communication device.
  • the communication device includes: a transceiver module configured to report CSI to a network side device, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or a specific rank processes the downlink channel information.
  • an embodiment of the present disclosure provides another communication device, which has some or all of the functions of the network side device in the method example described in the second aspect above, such as the functions of the communication device may have some or all of the functions in the embodiments of the present disclosure, or may have the functions of implementing any one of the embodiments of the present disclosure alone.
  • the functions may be implemented by hardware, or may be implemented by hardware executing corresponding software.
  • the hardware or software includes one or more units or modules corresponding to the above functions.
  • the structure of the communication device may include a transceiver module and a processing module, and the processing module is configured to support the communication device to perform the corresponding functions in the above method.
  • the transceiver module is used to support communication between the communication device and other devices.
  • the communication device may also include a storage module, which is coupled to the transceiver module and the processing module, and stores computer programs and data necessary for the communication device.
  • the communication device includes: a transceiver module configured to receive CSI reported by a terminal device, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or a specific rank processes the downlink channel information.
  • an embodiment of the present disclosure provides a communication device, which includes a processor.
  • the processor calls a computer program in a memory, the method described in the first aspect is executed.
  • an embodiment of the present disclosure provides a communication device, which includes a processor.
  • the processor calls a computer program in a memory, the method described in the second aspect is executed.
  • an embodiment of the present disclosure provides a communication device, which includes a processor and a memory, in which a computer program is stored; the processor executes the computer program stored in the memory so that the communication device executes the method described in the first aspect above.
  • an embodiment of the present disclosure provides a communication device, the communication device comprising a processor and a memory, wherein a computer program is stored in the memory; the processor executes the computer program stored in the memory, so that the communication device executes the second aspect described above. method.
  • an embodiment of the present disclosure provides a communication device, which includes a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to run the code instructions to enable the device to execute the method described in the first aspect above.
  • an embodiment of the present disclosure provides a communication device, which includes a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to run the code instructions to enable the device to execute the method described in the second aspect above.
  • an embodiment of the present disclosure provides a channel state information reporting system, the system comprising the communication device described in the third aspect and the communication device described in the fourth aspect, or the system comprising the communication device described in the fifth aspect and the communication device described in the sixth aspect, or the system comprising the communication device described in the seventh aspect and the communication device described in the eighth aspect, or the system comprising the communication device described in the ninth aspect and the communication device described in the tenth aspect.
  • an embodiment of the present invention provides a computer-readable storage medium for storing instructions for the above-mentioned terminal device, and when the instructions are executed, the terminal device executes the method described in the first aspect.
  • an embodiment of the present invention provides a readable storage medium for storing instructions used by the above-mentioned network side device, and when the instructions are executed, the network side device executes the method described in the above-mentioned second aspect.
  • the present disclosure further provides a computer program product comprising a computer program, which, when executed on a computer, enables the computer to execute the method described in the first aspect above.
  • the present disclosure further provides a computer program product comprising a computer program, which, when executed on a computer, enables the computer to execute the method described in the second aspect above.
  • the present disclosure provides a chip system, which includes at least one processor and an interface, and is used to support a terminal device to implement the functions involved in the first aspect, for example, determining or processing at least one of the data and information involved in the above method.
  • the chip system also includes a memory, and the memory is used to store computer programs and data necessary for the terminal device.
  • the chip system can be composed of a chip, or it can include a chip and other discrete devices.
  • the present disclosure provides a chip system, which includes at least one processor and an interface, and is used to support a network-side device to implement the functions involved in the second aspect, for example, determining or processing at least one of the data and information involved in the above method.
  • the chip system also includes a memory, and the memory is used to store computer programs and data necessary for the network-side device.
  • the chip system can be composed of a chip, or it can include a chip and other discrete devices.
  • the present disclosure provides a computer program, which, when executed on a computer, enables the computer to execute the method described in the first aspect.
  • the present disclosure provides a computer program which, when executed on a computer, enables the computer to execute the method described in the second aspect.
  • FIG1 is an architecture diagram of a communication system provided by an embodiment of the present disclosure.
  • FIG2 is a schematic diagram of implementing CSI compression feedback and recovery based on a bilateral AI/ML model provided by an embodiment of the present disclosure
  • FIG3 is a flow chart of a method for reporting channel state information provided by an embodiment of the present disclosure
  • FIG4 is a flow chart of another method for reporting channel state information provided by an embodiment of the present disclosure.
  • FIG5 is a flow chart of a load determination method provided by an embodiment of the present disclosure.
  • FIG6 is a flow chart of a method for sending model indication information provided by an embodiment of the present disclosure.
  • FIG7 is a flow chart of a method for reporting auxiliary information provided by an embodiment of the present disclosure.
  • FIG8 is a flowchart of another method for reporting channel state information provided by an embodiment of the present disclosure.
  • FIG9 is a flowchart of another method for reporting channel state information provided by an embodiment of the present disclosure.
  • FIG. 10 is a flowchart of another method for sending model indication information provided by an embodiment of the present disclosure.
  • FIG11 is a flowchart of another auxiliary information reporting method provided by an embodiment of the present disclosure.
  • FIG12 is a structural diagram of a communication device provided in an embodiment of the present disclosure.
  • FIG13 is a structural diagram of another communication device provided in an embodiment of the present disclosure.
  • FIG. 14 is a schematic diagram of the structure of a chip provided in an embodiment of the present disclosure.
  • the spatial domain may include a transmitting side spatial domain and a receiving side spatial domain, and the spatial domain basis vector may be determined based on the transmitting side spatial domain basis vector.
  • Each transmitting side spatial domain basis vector may correspond to a transmitting beam of a transmitting end device.
  • Each receiving side spatial domain basis vector may correspond to a receiving beam of a receiving end device.
  • the transmitting side spatial domain basis vector is usually associated with the transmitting side antenna array.
  • many parameters involved in the transmitting side spatial domain basis vector expression can be understood as being used to characterize different properties of the transmitting side antenna array.
  • the transmitting side spatial domain basis vectors involved in the embodiments of the present disclosure are not limited to specific antenna arrays. In the specific implementation process, a suitable antenna array can be selected according to specific needs, and based on the selected antenna array, various parameters involved in the transmitting side spatial domain basis vectors involved in the embodiments of the present disclosure are set.
  • the frequency domain basis vectors are used to characterize the variation of the channel in the frequency domain.
  • the frequency domain basis vectors can be used to specifically represent the variation of the weighted coefficients of each spatial domain basis vector in each frequency domain unit.
  • the variation represented by the frequency domain basis vectors is related to factors such as multipath delay. It is understandable that when a signal is transmitted through a wireless channel, there may be different transmission delays on different transmission paths.
  • the variation of the channel in the frequency domain caused by different transmission delays can be represented by different frequency domain basis vectors.
  • the dimension of the frequency domain basis vector is Nf, that is, one frequency domain basis vector contains Nf elements.
  • the dimension of the frequency domain basis vector may be equal to the number of frequency domain units that need to perform channel status information (CSI) measurement. Since the number of frequency domain units that need to perform CSI measurement may be different at different times, the dimension of the frequency domain basis vector may also be different. In other words, the dimension of the frequency domain basis vector is variable.
  • CSI channel status information
  • the dimension of the frequency domain basis vector may also be equal to the number of frequency domain units included in the available bandwidth of the terminal device.
  • the available bandwidth of the terminal device may be configured by the network device.
  • the available bandwidth of the terminal device is part or all of the system bandwidth.
  • the available bandwidth of the terminal device may also be referred to as a partial bandwidth (bandwidth part, BWP), which is not limited in the embodiments of the present disclosure.
  • the length of the frequency domain basis vector may also be equal to the length of the signaling used to indicate the position and number of frequency domain units to be reported, for example, the length of the frequency domain basis vector may be equal to the number of bits of the signaling, etc.
  • the signaling used to indicate the position and number of frequency domain units to be reported may be the signaling used to report the bandwidth (reporting band).
  • the signaling may indicate the position and number of frequency domain units to be reported, for example, in the form of a bitmap. Therefore, the dimension of the frequency domain basis vector may be the number of bits of the bitmap.
  • TD Time Domain basis vectors or Doppler domain DD basis vectors
  • TD basis vectors or DD basis vectors are used to characterize the changing law of the channel in the time domain. That is, TD basis vectors or DD basis vectors are used to characterize the time-varying property of the channel.
  • the time-varying property of the channel means that the transfer function of the channel changes over time.
  • the time-varying property of the channel is related to factors such as Doppler shift.
  • the dimension of the TD basis vector or the DD basis vector is Nt, that is, one TD basis vector or DD basis vector contains Nt elements.
  • the dimension of the TD basis vector or the DD basis vector may be equal to the number of time units for which CSI measurement is required. It is understandable that, since the number of time units for which CSI measurement is required may be different in different scenarios, the dimension of the TD basis vector or the DD basis vector may also be different. In other words, the dimension of the TD basis vector or the DD basis vector is variable.
  • FIG. 1 is a schematic diagram of the architecture of a communication system provided by an embodiment of the present disclosure.
  • the communication system may include, but is not limited to, a network-side device and a terminal device.
  • the number and form of devices shown in FIG. 1 are only used as examples and do not constitute a limitation on the embodiments of the present disclosure. In actual applications, two or more network-side devices and two or more terminal devices may be included.
  • the communication system 10 shown in FIG. 1 includes, for example, a network-side device 101 and a terminal device 102.
  • LTE long term evolution
  • 5G fifth generation
  • NR 5G new radio
  • the network side device 101 in the embodiment of the present disclosure may be an entity on the network side for transmitting or receiving signals.
  • the network side device 101 may be an access network device, including an evolved NodeB (eNB), a transmission reception point (TRP), a next generation NodeB (gNB) in an NR system, a base station in other future mobile communication systems, or an access node in a wireless fidelity (WiFi) system.
  • eNB evolved NodeB
  • TRP transmission reception point
  • gNB next generation NodeB
  • WiFi wireless fidelity
  • the embodiment of the present disclosure does not limit the specific technology and specific device form adopted by the network side device 101.
  • the network side device 101 provided in the embodiment of the present disclosure may be a centralized unit.
  • the network side device 101 is composed of a central unit (CU) and a distributed unit (DU), wherein the CU can also be called a control unit.
  • CU central unit
  • DU distributed unit
  • the CU-DU structure can be used to split the network side device 101, such as the protocol layer of the network side device 101, and the functions of some protocol layers are centrally controlled by the CU, and the functions of the remaining part or all of the protocol layers are distributed in the DU, and the DU is centrally controlled by the CU.
  • the terminal device 102 in the disclosed embodiment is an entity on the user side for receiving or transmitting signals, such as a mobile phone.
  • the terminal device may also be referred to as a user equipment (UE), a terminal (terminal), a mobile station (MS), a mobile terminal (MT), etc.
  • UE user equipment
  • terminal terminal
  • MS mobile station
  • MT mobile terminal
  • the terminal device may be a car with communication function, a smart car, a mobile phone, a wearable device, a tablet computer (Pad), a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control (industrial control), a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in smart grid (smart grid), a wireless terminal device in transportation safety (transportation safety), a wireless terminal device in a smart city (smart city), a wireless terminal device in a smart home (smart home), etc.
  • the embodiments of the present disclosure do not limit the specific technology and specific device form adopted by the terminal device.
  • the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution provided by the embodiment of the present disclosure.
  • a person skilled in the art can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution provided by the embodiment of the present disclosure is also applicable to similar technical problems.
  • used to indicate may include being used to indicate directly or indirectly.
  • the information may include that the information carries A, or it may also include that the information directly indicates A or indirectly indicates A, but it does not mean that the information must carry A.
  • the information indicated by the information is called the information to be indicated.
  • the information to be indicated there are many ways to indicate the information to be indicated, such as but not limited to, directly indicating the information to be indicated, such as the information to be indicated itself or the index of the information to be indicated.
  • the information to be indicated can also be indirectly indicated by indicating other information, wherein there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance.
  • the indication of specific information can also be achieved by means of the arrangement order of each information agreed in advance (such as specified by the protocol), thereby reducing the indication overhead to a certain extent.
  • the information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately, and the sending period and/or sending time of these sub-information can be the same or different.
  • the specific sending method is not limited in this disclosure. Among them, the sending period and/or sending time of these sub-information can be pre-defined, for example, pre-defined according to a protocol.
  • the first, second and various numerical numbers are only used for the convenience of description and are not used to limit the scope of the embodiments of the present disclosure. For example, to distinguish different information.
  • the embodiments of the present disclosure list multiple implementation methods to clearly illustrate the technical solutions of the embodiments of the present disclosure.
  • the multiple embodiments provided by the embodiments of the present disclosure can be executed separately, or can be executed together with the methods of other embodiments of the embodiments of the present disclosure, or can be executed together with some methods in other related technologies separately or in combination; the embodiments of the present disclosure do not limit this.
  • the network side device while the terminal device sends information to the network side device on a certain frequency band, the network side device needs to send information to the terminal device on another frequency band.
  • the terminal device needs to send and receive on multiple frequency bands at the same time. This will cause transmission and reception interference between the multiple frequency bands that are sending and receiving at the same time. This is a problem that needs to be solved urgently.
  • a paired (bilateral) AI/ML model was developed in the CSI generation part model of the terminal device and the CSI recovery part model of the network side device to realize the compression feedback and recovery of CSI respectively.
  • FIG. 2 a schematic diagram of implementing CSI compression feedback and recovery based on a bilateral AI/ML model is shown.
  • the terminal device UE
  • the network side device recovers H’ which is similar to the original downlink channel information through the CSI recovery part model.
  • the terminal device can also directly compress and quantize the downlink channel information H into a binary bit stream through the CSI generation model.
  • the methods of training the bilateral model of the CSI generation part model and the CSI recovery part model include the following:
  • Rank-specific approach For each rank, a bilateral model consisting of a CSI generation model and a CSI recovery model is trained;
  • Layer-specific approach For each layer, a bilateral model consisting of a CSI generation model and a CSI recovery model is trained;
  • Layer common approach Only one bilateral model consisting of a CSI generation part model and a CSI recovery part model is trained for all layers.
  • the CSI feedback method adopts the CSI feedback of the version 16 (Rel-16) type two (Type II) codebook method or the version 17 (Rel-17) type two (Type II) codebook method.
  • the CSI feedback of Rel-16 Type II codebook mode or Rel-17 Type II codebook mode divides the CSI into the first part (Part 1) and the second part (Part 2) for reporting.
  • the reporting content is shown in Table 1.
  • a method for reporting channel state information is proposed in an embodiment of the present disclosure, where a terminal device reports CSI to a network side device, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or a specific rank processes the downlink channel information.
  • the terminal device can report CSI including quantized information obtained after the first model corresponding to each layer or a specific rank processes the downlink channel information, so that the network side device can obtain accurate CSI.
  • Figure 3 is a flow chart of a method for reporting channel state information provided by an embodiment of the present disclosure. As shown in Figure 3, the method is executed by a terminal device, and the method may include but is not limited to the following steps:
  • S31 Reporting CSI to a network side device, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or a specific rank processes the downlink channel information.
  • the terminal device may report CSI to the network side device, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the terminal device may use the first model to process the downlink channel information to obtain quantized information.
  • the first model may be a CSI generation partial model on the terminal device side.
  • the first model may infer and/or predict the downlink channel information to obtain quantitative information.
  • first models which are related to the data used in training, the training method, the basic model adopted, etc.
  • the terminal device processes the downlink channel information using the first model and then performs vector quantization to obtain quantization information.
  • the terminal device processes the downlink channel information using the first model and can directly obtain the quantization information after performing vector quantization.
  • the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the CSI reported by the terminal device to the network side device includes quantized information obtained after the first model corresponding to each layer processes the downlink channel information.
  • the terminal device can report to the network side device the quantized information obtained after the first model corresponding to each layer processes the downlink channel information.
  • the CSI reported by the terminal device to the network side device includes quantized information obtained after the first model corresponding to the specific rank processes the downlink channel information.
  • the network side device can indicate the maximum transmission rank of the terminal device for uplink transmission.
  • the rank ⁇ 1 the first models corresponding to different ranks may be the same or different.
  • the terminal device can select one of the ranks as a specific rank and report to the network side device the quantization information obtained after processing the downlink channel information with the first model corresponding to the specific rank.
  • the terminal device sends model indication information to the network side device, wherein the model indication information is used to indicate at least one of the following:
  • the second model is used to process the quantized information to restore predicted downlink channel information that is similar to the downlink channel information.
  • the terminal device may send model indication information to the network side device, and the model indication information may include indication information of the first model.
  • the indication information of the first model can be used to indicate the first model, and can be used to tell the network side device the information of the first model used by the terminal device.
  • a terminal device may send model indication information to a network side device, and the model indication information may include indication information of a second model used to match the first model, wherein the second model is used to process the quantization information to recover predicted downlink channel information that is approximately the downlink channel information.
  • the second model used to match the first model can be a CSI recovery partial model of the network side device, and the first model and the second model can be trained using the rank-specific method, rank-common method, layer-specific method or layer-common method in the above examples.
  • the indication information of the second model used to match the first model can be used to indicate the second model, used to tell the network side device that the information of the second model that should be used to match the first model can inform the network side device to use the corresponding second model for processing.
  • a terminal device may send model indication information to a network side device, and the model indication information may include indication information of a model pair of a first model and a second model used for matching, wherein the second model is used to process the quantization information to recover predicted downlink channel information that is approximately the downlink channel information.
  • the indication information of the model pair of the first model and the matching second model can be used to indicate the information of the model pair of the first model and the second model, and can be used to tell the network side device the information of the first model used by the terminal device and the information of the second model used to match the first model, which can inform the network side device to use the corresponding second model for processing.
  • one or more candidate first models may be configured at the terminal device, and the terminal device may select one as the first model.
  • the terminal device may receive configuration information of the network side device, where the configuration information is used to indicate one or more candidate first models. Wherein, when the configuration information indicates one candidate first model, the terminal device may determine that the candidate first model is the first model; and when the configuration information indicates multiple candidate first models, the terminal device may select one of them to be determined as the first model.
  • the terminal device will inevitably select the candidate first model as the first model.
  • the network side device can know the first model selected by the terminal device. Based on this, the terminal device does not need to report the indication information of the first model.
  • the CSI further includes at least one of the following:
  • the second model is used to process the quantized information to restore predicted downlink channel information that is similar to the downlink channel information.
  • the CSI may also include RI, wherein the terminal device may determine the RI according to the constraints configured by the network side device, and then report it to the network side device.
  • CSI may also include CQI.
  • the CSI may also include indication information of the first model.
  • the indication information of the first model can be used to indicate the first model, and can be used to tell the network side device the information of the first model used by the terminal device.
  • the CSI may further include indication information of a second model used to match the first model; wherein the second model is used to process the quantized information to recover predicted downlink channel information that is similar to the downlink channel information.
  • the second model used to match the first model can be a CSI recovery model of the network side device.
  • the model can be trained using the rank-specific method, rank-common method, layer-specific method, or layer-common method in the above examples.
  • the CSI also includes indication information of the second model used to match the first model, which can be used to indicate the second model, to tell the network side device the information of the second model that should be used to match the first model, and to inform the network side device to use the corresponding second model for processing.
  • the CSI may also include indication information of a model pair of a first model and a second model used for matching; wherein the second model is used to process the quantized information to recover predicted downlink channel information that is similar to the downlink channel information.
  • the terminal device can report the indication information of the model pair to tell the network side device the information of the first model used by the terminal device and the information of the second model used to match the first model, which can inform the network side device to use the corresponding second model for processing.
  • the terminal device when a terminal device reports CSI to a network-side device, the terminal device may report the content of the CSI as a whole, or may split the content of the CSI and report it separately in multiple times.
  • the terminal device can report it separately in multiple times at different times to report CSI to the network side device.
  • the terminal device reports CSI to the network side device, including: reporting a first part of information and a second part of information to the network side device at different times, wherein the CSI includes the first part of information and the second part of information.
  • the terminal device reports CSI to the network side device, and may report the first part of information and the second part of information to the network side device at different times.
  • the CSI includes a first part of information and a second part of information.
  • the terminal device reports the first part of information and the second part of information to the network side device, including: using a physical uplink shared channel (Physical Uplink Shared Channel, PUSCH) or a physical uplink control channel (Physical Uplink Control Channel, PUCCH) to report the first part of information to the network side device, and using PUSCH or PUCCH to report the second part of information to the network side device.
  • PUSCH Physical Uplink Shared Channel
  • PUCCH Physical Uplink Control Channel
  • the terminal device may use PUSCH or PUCCH to report the first part of information to the network side device, and use PUSCH or PUCCH to report the second part of information to the network side device.
  • the terminal device reports the first part of information and the second part of information to the network side device, including:
  • the first part of information is associated with the second part of information that is adjacent thereto.
  • the terminal device may periodically report the first portion of information and the second portion of information to the network side device, wherein the first portion of information is associated with the subsequent adjacent second portion of information.
  • the terminal device may non-periodically report the first portion of information and the second portion of information to the network side device, wherein the first portion of information is associated with the subsequent adjacent second portion of information.
  • the terminal device may semi-continuously report the first portion of information and the second portion of information to the network side device, wherein the first portion of information is associated with the subsequent adjacent second portion of information.
  • the content of the first part of information reported by the terminal device corresponds to the content of the second part reported most immediately thereafter, and the first part of information has an associated relationship with the second part of information that is immediately thereafter.
  • the reported second part of information can be determined to which reported first part of information corresponds by predefining or reporting the association relationship of the identifier.
  • the first part of information corresponds to the first identifier
  • the second part of information corresponds to the second identifier.
  • the first identifier and the second identifier can be reported to have an association relationship to determine the first part of information corresponding to the second part of information.
  • the first portion of information includes at least one of the following:
  • the second part of the information includes at least one of the following:
  • the length of quantized information of all layers obtained after the first model corresponding to all layers processes the downlink channel information
  • the number of codewords of all layers obtained after the first model corresponding to all layers processes the downlink channel information
  • Quantized information obtained after the first model corresponding to the specific rank processes the downlink channel information
  • the first part of information may include at least one of the following:
  • Indicative information of the first model and indicative information of the second model used to match the first model.
  • the second part of the information may include at least one of the following:
  • the length of quantized information of all layers obtained after the first model corresponding to all layers processes the downlink channel information
  • the number of codewords of all layers obtained after the first model corresponding to all layers processes the downlink channel information
  • Quantized information obtained after the first model corresponding to the specific rank processes the downlink channel information
  • the second part of information may include the indication information of the first model.
  • the network-side device when the network-side device only configures a first model for the terminal device, the first part of information and the second part of information may not include indication information of the first model.
  • the first model and the second model are obtained by training according to layer correspondence; or the first model and the second model are obtained by training according to rank correspondence.
  • the first model and the second model are obtained by training according to the layer correspondence, wherein the first model and the second model can be trained in a layer-specific manner, or can also be trained in a layer-common manner.
  • the first model and the second model are obtained by training according to layer correspondence, wherein the first model and the second model can be trained in a rank-specific manner, or can also be trained in a rank-common manner.
  • the first model and the second model are obtained by training according to the layer correspondence.
  • a layer-specific method may be adopted, or a layer-common method may be adopted to train the first model and the second model.
  • the first model and the second model are obtained by training in a layer-specific manner, and a bilateral model including the first model and the second model can be trained for each layer.
  • the first model and the second model are obtained by training in a layer-common manner, and only one bilateral model including the first model and the second model may be trained for all layers.
  • the first part of information includes at least one of the following:
  • the length of quantized information obtained after the first model corresponding to each layer processes the downlink channel information
  • the number of codewords obtained after the first model corresponding to each layer processes the downlink channel information.
  • the second part of information includes quantized information obtained after the first model corresponding to each layer processes the downlink channel information.
  • the first model and the second model are obtained by training according to rank correspondence.
  • a rank-specific method may be adopted, or a rank-common method may be adopted to train the first model and the second model.
  • the first model and the second model are obtained by training in a rank-specific manner, and a bilateral model including the first model and the second model can be trained for each rank.
  • the first model and the second model are trained in a rank-common manner, and only one bilateral model including the first model and the second model can be trained for all ranks.
  • the first part of information includes at least one of the following:
  • the number of codewords obtained after the first model corresponding to the specific rank processes the downlink channel information.
  • the second part of information includes quantized information obtained after the first model corresponding to the specific rank processes the downlink channel information.
  • the data type input into the first model may include two types, one is a precoding matrix in the space-frequency domain, and the other is a precoding matrix in the angle and delay domain.
  • the information included in the first partial model and the second partial model may be the same as the content included in the first partial information and the second partial information described in some of the above embodiments.
  • the first part of the information includes indication information of the first model, and the length of the quantization information obtained after the first model corresponding to each layer or each rank processes the downlink channel information can also be directly determined.
  • the terminal device does not need to report the length of the quantization information obtained after the first model corresponding to each layer or each rank processes the downlink channel information, thereby reducing the feedback overhead of the terminal device.
  • the data type input to the first model includes a precoding matrix in the space-frequency domain, or a precoding matrix in the angle and delay domain.
  • the second part of the information also includes indication information of the space-domain basis vectors and the frequency-domain basis vectors selected by the terminal device.
  • the data type input into the first model may include two types, one is a precoding matrix in the space-frequency domain, and the other is a precoding matrix in the angle and delay domain.
  • the information included in the first part model and the second part model can be the same as the content included in the first part information and the second part information described in some of the above embodiments.
  • the content included in the first part of the information may be the same as the content included in the first part of the information described in some of the above embodiments, and the second part of the information, in addition to the content included in the second part of the information described in some of the above embodiments, may also include indication information of the spatial domain basis vectors and frequency domain basis vectors selected by the terminal device.
  • the terminal device can determine the indication information of the spatial domain basis vectors and the frequency domain basis vectors based on the configuration of the network side device. In this case, the terminal device may not need to report the indication information of the spatial domain basis vectors and the frequency domain basis vectors. If the terminal device selects the indication information of the spatial domain basis vectors and the frequency domain basis vectors, the terminal device needs to report the indication information of the spatial domain basis vectors and the frequency domain basis vectors.
  • the CSI also includes vector quantized codeword indication information, wherein the first model processes the downlink channel information and then further performs vector quantization processing to obtain quantized information.
  • the CSI may also include codeword indication information of the vector quantization.
  • the terminal device reports auxiliary information to the network side device, wherein the first model processes the downlink channel information and further performs vector quantization processing to obtain quantization information, and the auxiliary information includes codeword indication information of the vector quantization.
  • the terminal device may report auxiliary information to the network side device, where the auxiliary information includes codeword indication information of the vector quantization.
  • each step can be independent, arbitrarily combined or exchanged in order, and the optional methods or optional examples can be arbitrarily combined and can be arbitrarily combined with other implementation modes or examples.
  • the terminal device reports CSI to the network side device, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the CSI reporting of the terminal device including the quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information, so that the network side device can obtain accurate CSI.
  • Figure 4 is a flow chart of another method for reporting channel state information provided by an embodiment of the present disclosure. As shown in Figure 4, the method is executed by a terminal device, and the method may include but is not limited to the following steps:
  • S41 Report CSI to the network side device according to the determined maximum load, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the terminal device may report CSI to the network side device according to the determined maximum load.
  • the relevant description of the terminal device reporting CSI to the network side device can be found in the relevant description in the above embodiment, and will not be repeated here.
  • the terminal device can determine the maximum load based on the configuration of the network side device, or the terminal device can also determine the maximum load based on other information, and the embodiments of the present disclosure do not impose specific restrictions on this.
  • the terminal device determines the maximum load based on the adopted first model and/or the received first configuration information sent by the network side device, wherein the first configuration information is used to indicate the rank constraint condition.
  • the terminal device can determine the maximum load according to the adopted first model.
  • the terminal device can determine the maximum load based on the first configuration information sent by the network side device.
  • the first configuration information is used to indicate the rank constraint condition.
  • the terminal device can determine the maximum load according to the rank constraint condition sent by the network side device.
  • the terminal device determines the maximum load based on the adopted first model and/or the first configuration information sent by the received network side device. There is no need for the network side device to configure the maximum load for the terminal device, which can reduce signaling overhead.
  • the terminal device reports CSI to the network side device according to the determined maximum load.
  • the CSI is less than the maximum load, the remaining part is filled with zeros and the CSI is reported to the network side device.
  • the CSI When the CSI is equal to the maximum load, the CSI can be directly reported to the network side device.
  • all CSI can be discarded, or part of the information in the CSI can be discarded, and the remaining CSI information can be reported to the network side device; in which, part of the information in the CSI report can be discarded according to the CSI discarding criteria or method.
  • each step can be independent, arbitrarily combined or exchanged in order, and the optional methods or optional examples can be arbitrarily combined and can be arbitrarily combined with other implementation modes or examples.
  • S41 can be implemented alone or in combination with any other step in the embodiment of the present disclosure, for example, in combination with S31 in the embodiment of the present disclosure, and the embodiment of the present disclosure is not limited to this.
  • the terminal device reports CSI to the network side device according to the determined maximum load, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the terminal device reporting CSI including quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information according to the determined maximum load, so that the network side device can obtain accurate CSI.
  • Figure 5 is a flow chart of a load determination method provided by an embodiment of the present disclosure. As shown in Figure 5, the method is executed by a terminal device, and the method may include but is not limited to the following steps:
  • S51 Determine a maximum load according to the adopted first model and/or first configuration information received and sent by a network-side device, wherein the first configuration information is used to indicate a rank constraint condition.
  • the terminal device can determine the maximum load according to the adopted first model.
  • the terminal device can determine the maximum load based on the first configuration information sent by the network side device.
  • the first configuration information is used to indicate the rank constraint condition.
  • the terminal device can determine the maximum load according to the rank constraint condition sent by the network side device.
  • the terminal device determines the maximum load based on the adopted first model and/or the first configuration information sent by the received network side device. There is no need for the network side device to configure the maximum load for the terminal device, which can reduce signaling overhead.
  • the terminal device determines the first model to be adopted.
  • the first model to be adopted may be determined based on the implementation of the terminal device, or may be determined based on a protocol agreement, or may be determined based on the configuration of a network-side device.
  • the configuration of the network side device can indicate one or more candidate first models, and the terminal device can determine one of them as the adopted first model.
  • the terminal device receives second configuration information sent by the network side device, wherein the second configuration information is used to indicate multiple candidate first models; and determines one from the candidate first models as the adopted first model.
  • a terminal device may receive second configuration information sent by a network side device, wherein the second configuration information is used to indicate a plurality of candidate first models; thereby, the terminal device may determine one of the candidate first models as the adopted first model.
  • each step can be independent, arbitrarily combined or exchanged in order, and the optional methods or optional examples can be arbitrarily combined and can be arbitrarily combined with other implementation modes or examples.
  • S51 can be implemented alone or in combination with any other step in the embodiments of the present disclosure, for example, in combination with S31 and/or S41 in the embodiments of the present disclosure, and the embodiments of the present disclosure are not limited to this.
  • the terminal device determines the maximum load according to the adopted first model and/or the received first configuration information sent by the network side device, wherein the first configuration information is used to indicate the rank constraint condition.
  • the terminal device can determine the maximum load and reduce signaling overhead.
  • Figure 6 is a flow chart of a method for sending model indication information provided by an embodiment of the present disclosure. As shown in Figure 6, the method is executed by a terminal device, and the method may include but is not limited to the following steps:
  • S61 Send model indication information to the network side device.
  • the model indication information is used to indicate at least one of the following:
  • the second model is used to process the quantized information to restore predicted downlink channel information that is similar to the downlink channel information.
  • the terminal device may send model indication information to the network side device, and the model indication information may include indication information of the first model.
  • the indication information of the first model can be used to indicate the first model, which can be used to tell the network side device that the terminal device uses the first model. Information about a model.
  • a terminal device may send model indication information to a network side device, and the model indication information may include indication information of a second model used to match the first model, wherein the second model is used to process the quantization information to recover predicted downlink channel information that is approximately the downlink channel information.
  • the second model used to match the first model can be a CSI recovery partial model of the network side device, and the first model and the second model can be trained using the rank-specific method, rank-common method, layer-specific method or layer-common method in the above examples.
  • the indication information of the second model used to match the first model can be used to indicate the second model, used to tell the network side device that the information of the second model that should be used to match the first model can inform the network side device to use the corresponding second model for processing.
  • a terminal device may send model indication information to a network side device, and the model indication information may include indication information of a model pair of a first model and a second model used for matching, wherein the second model is used to process the quantization information to recover predicted downlink channel information that is approximately the downlink channel information.
  • the indication information of the model pair of the first model and the matching second model can be used to indicate the information of the model pair of the first model and the second model, and can be used to tell the network side device the information of the first model used by the terminal device and the information of the second model used to match the first model, which can inform the network side device to use the corresponding second model for processing.
  • one or more candidate first models may be configured at the terminal device, and the terminal device may select one as the first model.
  • the terminal device may receive configuration information of the network side device, where the configuration information is used to indicate one or more candidate first models. Wherein, when the configuration information indicates one candidate first model, the terminal device may determine that the candidate first model is the first model; and when the configuration information indicates multiple candidate first models, the terminal device may select one of them to be determined as the first model.
  • the terminal device will inevitably select the candidate first model as the first model.
  • the network side device can know the first model selected by the terminal device. Based on this, the terminal device does not need to report the indication information of the first model.
  • each step can be independent, arbitrarily combined or exchanged in order, and the optional methods or optional examples can be arbitrarily combined and can be arbitrarily combined with other implementation modes or examples.
  • S61 can be implemented alone or in combination with any other step in the embodiments of the present disclosure, for example, in combination with S31 and/or S41 and/or S51 in the embodiments of the present disclosure, and the embodiments of the present disclosure are not limited to this.
  • the terminal device sends the model indication information to the network side device. Therefore, the terminal device can send the model indication information to the network side device.
  • Figure 7 is a flow chart of a method for reporting auxiliary information provided by an embodiment of the present disclosure. As shown in Figure 7, the method is executed by a terminal device, and the method may include but is not limited to the following steps:
  • S71 reporting auxiliary information to a network side device, wherein the first model processes the downlink channel information and then further performs vector quantization processing to obtain quantized information, and the auxiliary information includes codeword indication information of the vector quantization.
  • the terminal device may report auxiliary information to the network side device, where the auxiliary information includes codeword indication information of the vector quantization.
  • the terminal device may report the auxiliary information to the network side device separately or simultaneously with other information, and the embodiment of the present disclosure does not impose any specific limitation on this.
  • the terminal device may reuse existing signaling or messages to report auxiliary information to the network side device, or may also use new signaling or messages, and the embodiment of the present disclosure does not impose specific restrictions on this.
  • each step can be independent, arbitrarily combined or exchanged in order, and the optional methods or optional examples can be arbitrarily combined and can be arbitrarily combined with other implementation modes or examples.
  • S71 can be implemented alone or in combination with any other steps in the embodiments of the present disclosure, for example, in combination with S31 and/or S41 and/or S51 and/or S61 in the embodiments of the present disclosure, and the embodiments of the present disclosure are not limited to this.
  • the terminal device reports auxiliary information to the network side device, wherein the first model processes the downlink channel information and further performs vector quantization processing to obtain quantization information, and the auxiliary information includes vector quantization codeword indication information.
  • the terminal device can report vector quantization codeword indication information to the network side device.
  • FIG8 is a flow chart of another method for reporting channel state information provided by an embodiment of the present disclosure. As shown in FIG8, The method is performed by a network side device, and the method may include but is not limited to the following steps:
  • S81 Receive CSI reported by the terminal device, where the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • a network side device may receive CSI reported by a terminal device, wherein the CSI includes quantized information obtained after a first model corresponding to each layer or a specific rank processes downlink channel information.
  • the terminal device may use the first model to process the downlink channel information to obtain quantized information.
  • the first model may be a CSI generation partial model on the terminal device side.
  • first models which are related to the data used in training, the training method, the basic model adopted, etc.
  • the terminal device processes the downlink channel information using the first model and then performs vector quantization to obtain quantization information.
  • the terminal device processes the downlink channel information using the first model and can directly obtain the quantization information after performing vector quantization.
  • the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the CSI reported by the terminal device and received by the network side device includes quantized information obtained after the first model corresponding to each layer processes the downlink channel information.
  • the network side device can receive the quantized information obtained by processing the downlink channel information using the first model corresponding to each layer reported by the terminal device.
  • the CSI reported by the terminal device and received by the network side device includes quantized information obtained after the first model corresponding to the specific rank processes the downlink channel information.
  • the network side device can indicate the maximum transmission rank of the terminal device for uplink transmission.
  • the rank ⁇ 1 the first models corresponding to different ranks may be the same or different, and the terminal device can select one of the ranks as a specific rank. Based on this, the network side device can receive the first model corresponding to the specific rank reported by the terminal device and process the downlink channel information to obtain quantization information.
  • the network side device receives model indication information sent by the terminal device, wherein the model indication information is used to indicate at least one of the following:
  • the second model is used to process the quantized information to restore predicted downlink channel information that is similar to the downlink channel information.
  • the network side device may receive the model indication information sent by the terminal device, and the model indication information may include indication information of the first model.
  • the indication information of the first model can be used to indicate the first model
  • the network side device can determine the first model used by the terminal device.
  • a network side device may receive model indication information sent by a terminal device, and the model indication information may include indication information of a second model used to match the first model, wherein the second model is used to process the quantization information to recover predicted downlink channel information that is approximately the downlink channel information.
  • the second model used to match the first model can be a CSI recovery partial model of the network side device, and the first model and the second model can be trained using the rank-specific method, rank-common method, layer-specific method or layer-common method in the above examples.
  • the indication information of the second model used to match the first model can be used to indicate the second model.
  • the network side device can determine the second model that should be matched with the first model, and then use the second model for processing.
  • a network side device may receive model indication information sent by a terminal device, and the model indication information may include indication information of a model pair of a first model and a second model used for matching, wherein the second model is used to process the quantization information to recover predicted downlink channel information that is approximately the downlink channel information.
  • the indication information of the model pair of the first model and the second model used to match it can be used to indicate the information of the model pair of the first model and the second model.
  • the network side device can determine the information of the first model used by the terminal device and the second model used to match the first model, and then use the second model for processing.
  • one or more candidate first models may be configured at the terminal device, and the terminal device may select one as the first model.
  • the network side device may send configuration information to the terminal device, where the configuration information is used to indicate one or more candidate first models.
  • the terminal device may determine that the candidate first model is the first model. A model; when the configuration information indicates multiple candidate first models, the terminal device can select one of them as the first model.
  • the terminal device will inevitably select the candidate first model as the first model.
  • the network side device can know the first model selected by the terminal device. Based on this, the terminal device does not need to report the indication information of the first model.
  • the CSI further includes at least one of the following:
  • the second model is used to process the quantized information to restore predicted downlink channel information that is similar to the downlink channel information.
  • the CSI may also include RI, wherein the terminal device may determine the RI according to the constraints configured by the network side device, and then report it to the network side device.
  • CSI may also include CQI.
  • the CSI may also include indication information of the first model.
  • the indication information of the first model can be used to indicate the first model
  • the network side device can determine the first model used by the terminal device.
  • the CSI may further include indication information of a second model used to match the first model, wherein the second model is used to process the quantized information to recover predicted downlink channel information that is similar to the downlink channel information.
  • the second model used to match the first model can be a CSI recovery partial model of the network side device, and the first model and the second model can be trained using the rank-specific method, rank-common method, layer-specific method or layer-common method in the above examples.
  • the CSI also includes indication information of the second model used to match the first model, which can be used to indicate the second model.
  • the network side device can determine the second model that should be used to match the first model, and then use the second model for processing.
  • the CSI may further include indication information of a model pair of a first model and a second model used for matching, wherein the second model is used to process the quantized information to recover predicted downlink channel information that is similar to the downlink channel information.
  • the network side device can receive the indication information of the model pair reported by the terminal device, the network side device can determine the information of the first model used by the terminal device, and the information of the second model used to match the first model, and then can use the second model for processing.
  • the terminal device when a terminal device reports CSI to a network-side device, the terminal device may report the content of the CSI as a whole, or may split the content of the CSI and report it separately in multiple times.
  • the terminal device can report it separately in multiple times at different times to report CSI to the network side device.
  • the network side device receives the CSI reported by the terminal device, including: receiving the first part of information and the second part of information reported by the terminal device at different times, wherein the CSI includes the first part of information and the second part of information
  • the network side device receives the CSI reported by the terminal device, and may receive the first part of information and the second part of information reported by the terminal device at different times.
  • the CSI includes a first part of information and a second part of information.
  • the network side device receives the first part of information and the second part of information reported by the terminal device, including: receiving the first part of information reported by the terminal device using PUSCH or PUCCH, and the second part of information reported using PUSCH or PUCCH.
  • the network side device may receive the first part of information reported by the terminal device using PUSCH or PUCCH, and the second part of information reported by the terminal device using PUSCH or PUCCH.
  • the network side device receives the first part of information and the second part of information reported by the terminal device, including:
  • the first part of information is associated with the second part of information that is adjacent thereto.
  • the network side device may receive the first part of information and the second part of information periodically reported by the terminal device, wherein the first part of information is associated with the subsequent adjacent second part of information.
  • the network side device may receive the first part of information and the second part of information reported aperiodically by the terminal device, wherein the first part of information is associated with the subsequent adjacent second part of information.
  • the network side device may receive the first part of information and the second part of information semi-continuously reported by the terminal device, wherein the first part of information is associated with the subsequent adjacent second part of information.
  • the content of the first part of information reported by the terminal device corresponds to the content of the second part reported most immediately thereafter, and the first part of information has an associated relationship with the second part of information that is immediately thereafter.
  • the reported second part of information can be determined to which reported first part of information corresponds by predefining or reporting the association relationship of the identifier.
  • the first part of information corresponds to the first identifier
  • the second part of information corresponds to the second identifier.
  • the first identifier and the second identifier can be reported to have an association relationship to determine the first part of information corresponding to the second part of information.
  • the first portion of information includes at least one of the following:
  • the second part of the information includes at least one of the following:
  • the length of quantized information of all layers obtained after the first model corresponding to all layers processes the downlink channel information
  • the number of codewords of all layers obtained after the first model corresponding to all layers processes the downlink channel information
  • Quantized information obtained after the first model corresponding to the specific rank processes the downlink channel information
  • the first part of information may include at least one of the following:
  • Indicative information of the first model and indicative information of the second model used to match the first model.
  • the second part of the information may include at least one of the following:
  • the length of quantized information of all layers obtained after the first model corresponding to all layers processes the downlink channel information
  • the number of codewords of all layers obtained after the first model corresponding to all layers processes the downlink channel information
  • Quantized information obtained after the first model corresponding to the specific rank processes the downlink channel information
  • the second part of information may include the indication information of the first model.
  • the network-side device when the network-side device only configures a first model for the terminal device, the first part of information and the second part of information may not include indication information of the first model.
  • the first model and the second model are obtained by training according to layer correspondence; or the first model and the second model are obtained by training according to rank correspondence.
  • the first model and the second model are obtained by training according to the layer correspondence, wherein the first model and the second model can be trained in a layer-specific manner, or can also be trained in a layer-common manner.
  • the first model and the second model are obtained by training according to layer correspondence, wherein the first model and the second model can be trained in a rank-specific manner, or can also be trained in a rank-common manner.
  • the first model and the second model are obtained by training according to the layer correspondence.
  • a layer-specific method may be adopted, or a layer-common method may be adopted to train the first model and the second model.
  • the first model and the second model are obtained by training in a layer-specific manner, and a bilateral model including the first model and the second model can be trained for each layer.
  • the first model and the second model are obtained by training in a layer-common manner, and only one bilateral model including the first model and the second model may be trained for all layers.
  • the first part of information includes at least one of the following:
  • the length of quantized information obtained after the first model corresponding to each layer processes the downlink channel information
  • the number of codewords obtained after the first model corresponding to each layer processes the downlink channel information.
  • the second part of information includes quantized information obtained after the first model corresponding to each layer processes the downlink channel information.
  • the first model and the second model are obtained by training according to rank correspondence.
  • a rank-specific method may be adopted, or a rank-common method may be adopted to train the first model and the second model.
  • the first model and the second model are obtained by training in a rank-specific manner, and a bilateral model including the first model and the second model can be trained for each rank.
  • the first model and the second model are trained in a rank-common manner, and only one bilateral model including the first model and the second model can be trained for all ranks.
  • the first part of information includes at least one of the following:
  • the number of codewords obtained after the first model corresponding to the specific rank processes the downlink channel information.
  • the second part of information includes quantized information obtained after the first model corresponding to the specific rank processes the downlink channel information.
  • the data type input into the first model may include two types, one is a precoding matrix in the space-frequency domain, and the other is a precoding matrix in the angle and delay domain.
  • the information included in the first partial model and the second partial model may be the same as the content included in the first partial information and the second partial information described in some of the above embodiments.
  • the first part of the information includes indication information of the first model, and the length of the quantization information obtained after the first model corresponding to each layer or each rank processes the downlink channel information can also be directly determined.
  • the terminal device does not need to report the length of the quantization information obtained after the first model corresponding to each layer or each rank processes the downlink channel information, thereby reducing the feedback overhead of the terminal device.
  • the data type input to the first model includes a precoding matrix in the space-frequency domain or a precoding matrix in the angle and delay domain, wherein, when the data type input to the first model is a precoding matrix in the angle and delay domain, the second part of the information also includes indication information of the space-domain basis vectors and the frequency-domain basis vectors selected by the terminal device.
  • the information included in the first part model and the second part model can be the same as the content included in the first part information and the second part information described in some of the above embodiments.
  • the content included in the first part of the information may be the same as the content included in the first part of the information described in some of the above embodiments, and the second part of the information, in addition to the content included in the second part of the information described in some of the above embodiments, may also include indication information of the spatial domain basis vectors and frequency domain basis vectors selected by the terminal device.
  • the terminal device can determine the indication information of the spatial domain basis vectors and the frequency domain basis vectors based on the configuration of the network side device. In this case, the terminal device may not need to report the indication information of the spatial domain basis vectors and the frequency domain basis vectors. If the terminal device selects the indication information of the spatial domain basis vectors and the frequency domain basis vectors, the terminal device needs to report the indication information of the spatial domain basis vectors and the frequency domain basis vectors.
  • the CSI also includes vector quantized codeword indication information, wherein the first model processes the downlink channel information and then further performs vector quantization processing to obtain quantized information.
  • a network side device receives auxiliary information reported by a terminal device, wherein the auxiliary information includes codeword indication information of vector quantization, and after the first model processes the downlink channel information, the quantization information is further obtained through vector quantization processing.
  • the network side device may receive auxiliary information reported by the terminal device, wherein the auxiliary information includes codeword indication information of the vector quantization.
  • each step can be independent, arbitrarily combined or exchanged in order, and the optional methods or optional examples can be arbitrarily combined and can be arbitrarily combined with other implementation modes or examples.
  • the network side device receives the CSI reported by the terminal device, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the network side device can receive the CSI reported by the terminal device, including the quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information, so that the network side device can obtain accurate CSI.
  • Figure 9 is a flow chart of another method for reporting channel state information provided by an embodiment of the present disclosure. As shown in Figure 9, the method is executed by a network side device, and the method may include but is not limited to the following steps:
  • S91 Receive CSI reported by the terminal device according to the determined maximum load, where the CSI includes the first A model processes the downlink channel information and obtains quantized information.
  • the network side device may receive the CSI reported by the terminal device according to the determined maximum load.
  • the terminal device can determine the maximum load based on the configuration of the network side device, or the terminal device can also determine the maximum load based on other information, and the embodiments of the present disclosure do not impose specific restrictions on this.
  • the terminal device determines the maximum load based on the adopted first model and/or the received first configuration information sent by the network side device, wherein the first configuration information is used to indicate the rank constraint condition.
  • the terminal device can determine the maximum load according to the adopted first model.
  • the terminal device can determine the maximum load based on the first configuration information sent by the network side device.
  • the first configuration information is used to indicate the rank constraint condition.
  • the terminal device can determine the maximum load according to the rank constraint condition sent by the network side device.
  • the terminal device determines the maximum load based on the adopted first model and/or the first configuration information sent by the received network side device. There is no need for the network side device to configure the maximum load for the terminal device, which can reduce signaling overhead.
  • the network side device sends first configuration information to the terminal device, wherein the first configuration information is used by the terminal device to determine the maximum load, and the first configuration information is used to indicate a rank constraint condition.
  • the network side device may send first configuration information to the terminal device, wherein the first configuration information is used by the terminal device to determine the maximum load, and the first configuration information is used to indicate the rank constraint condition.
  • the terminal device may determine the maximum load according to the rank constraint condition indicated by the first configuration information.
  • the terminal device reports CSI to the network side device according to the determined maximum load.
  • the CSI is less than the maximum load, the remaining part is filled with zeros and the CSI is reported to the network side device.
  • the CSI When the CSI is equal to the maximum load, the CSI can be directly reported to the network side device.
  • all CSI can be discarded, or part of the information in the CSI can be discarded, and the remaining CSI information can be reported to the network side device; in which, part of the information in the CSI report can be discarded according to the CSI discarding criteria or method.
  • each step can be independent, arbitrarily combined or exchanged in order, and the optional methods or optional examples can be arbitrarily combined and can be arbitrarily combined with other implementation modes or examples.
  • S91 can be implemented alone or in combination with any other step in the embodiment of the present disclosure, for example, in combination with S81 in the embodiment of the present disclosure, and the embodiment of the present disclosure is not limited to this.
  • the network side device receives the CSI reported by the terminal device according to the determined maximum load, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the network side device receives the CSI reported by the terminal device according to the determined maximum load, including quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information, so that the network side device can obtain accurate CSI.
  • Figure 10 is a flowchart of another method for sending model indication information provided by an embodiment of the present disclosure. As shown in Figure 10, the method is executed by a network side device, and the method may include but is not limited to the following steps:
  • S101 Receive model indication information sent by a terminal device.
  • the model indication information is used to indicate at least one of the following:
  • the second model is used to process the quantized information to restore predicted downlink channel information that is similar to the downlink channel information.
  • the network side device may receive the model indication information sent by the terminal device, and the model indication information may include indication information of the first model.
  • the indication information of the first model can be used to indicate the first model
  • the network side device can determine the first model used by the terminal device.
  • a network side device may receive model indication information sent by a terminal device, and the model indication information may include indication information of a second model used to match the first model; wherein the second model is used to process the quantization information to recover predicted downlink channel information that is approximately the downlink channel information.
  • the second model used to match the first model can be a CSI recovery partial model of the network side device, and the first model and the second model can be trained using the rank-specific method, rank-common method, layer-specific method or layer-common method in the above examples.
  • the indication information of the second model used to match the first model can be used to indicate the second model.
  • the network side device can determine the second model that should be matched with the first model, and then use the second model for processing.
  • a network side device may receive model indication information sent by a terminal device, and the model indication information may include indication information of a model pair of a first model and a second model used for matching; wherein the second model is used to process the quantized information to recover predicted downlink channel information that is approximately the downlink channel information.
  • the indication information of the model pair of the first model and the second model used for matching can be used to indicate the information of the model pair of the first model and the second model.
  • the network side device can determine the information of the first model used by the terminal device and the second model used for matching the first model, and then use the second model for processing.
  • one or more candidate first models may be configured at the terminal device, and the terminal device may select one as the first model.
  • the terminal device may receive configuration information of the network side device, where the configuration information is used to indicate one or more candidate first models. Wherein, when the configuration information indicates one candidate first model, the terminal device may determine that the candidate first model is the first model; and when the configuration information indicates multiple candidate first models, the terminal device may select one of them to be determined as the first model.
  • the terminal device will inevitably select the candidate first model as the first model.
  • the network side device can know the first model selected by the terminal device. Based on this, the terminal device does not need to report the indication information of the first model.
  • each step can be independent, arbitrarily combined or exchanged in order, and the optional methods or optional examples can be arbitrarily combined and can be arbitrarily combined with other implementation modes or examples.
  • S101 can be implemented alone or in combination with any other step in the embodiments of the present disclosure, for example, in combination with S81 and/or S91 in the embodiments of the present disclosure, and the embodiments of the present disclosure are not limited to this.
  • the network side device receives the model indication information sent by the terminal device, thereby enabling the network side device to receive the model indication information sent by the terminal device.
  • Figure 11 is a flow chart of another auxiliary information reporting method provided by an embodiment of the present disclosure. As shown in Figure 11, the method is executed by a terminal device, and the method may include but is not limited to the following steps:
  • S111 receiving auxiliary information reported by a terminal device, wherein the first model processes the downlink channel information and then further performs vector quantization processing to obtain quantized information, and the auxiliary information includes codeword indication information of the vector quantization.
  • the network side device may receive auxiliary information reported by the terminal device, wherein the auxiliary information includes codeword indication information of the vector quantization.
  • the network side device may receive the auxiliary information reported by the terminal device separately or simultaneously with other information, and the embodiment of the present disclosure does not impose any specific limitation on this.
  • the network side device may reuse existing signaling or messages to receive the auxiliary information reported by the terminal device, or may also use new signaling or messages, and the embodiment of the present disclosure does not impose any specific limitation on this.
  • each step can be independent, arbitrarily combined or exchanged in order, and the optional methods or optional examples can be arbitrarily combined and can be arbitrarily combined with other implementation modes or examples.
  • S111 can be implemented alone or in combination with any other step in the embodiments of the present disclosure, for example, in combination with S81 and/or S91 and/or S101 in the embodiments of the present disclosure, and the embodiments of the present disclosure are not limited to this.
  • the network side device receives the auxiliary information reported by the terminal device, wherein the first model processes the downlink channel information and further performs vector quantization processing to obtain quantization information, and the auxiliary information includes vector quantization codeword indication information.
  • the network side device can receive the vector quantization codeword indication information reported by the terminal device.
  • the method for reporting channel state information provided by the embodiments of the present disclosure is described by taking the first model as a CSI generation partial model and the second model as a CSI recovery partial model as an example.
  • a method for determining the maximum CSI payload size and the content of CSI reporting to the network side device are proposed for bilateral AI/ML model compression CSI feedback, so that the network side device (gNB) can obtain accurate CSI feedback information as input information of the CSI recovery model on the gNB side.
  • the maximum CSI load size (also referred to as maximum load, the same below) reported by the terminal device is determined in the following manner:
  • the terminal device can be determined based on the CSI generation part AI/ML Model (CSI generation part model) adopted by the terminal and/or the rank constraints configured by the network side device.
  • CSI generation part AI/ML Model CSI generation part model
  • the CSI generates part of the AI/ML Model determination method:
  • the CSI generation part AI/ML Model adopted by the terminal device is determined by the following Option 1 and/or Option 2. Different CSI reporting methods are given for Option 1 and Option 2 respectively.
  • the CSI generation part AI/ML Model is configured with one or more CSI generation part AI/ML models by the network side device, and the terminal determines a CSI generation part AI/ML Model from them.
  • Option1-1 CSI reporting is divided into Part 1 (the first part of information) and Part 2 (the data type of the AI/ML Model input into the CSI generation part is Alt1, that is, the precoding matrix in the space-frequency domain).
  • Part 1 includes: one or more of RI, CQI, and indication information of the CSI generation part AI/ML Model/CSI recovery part AI/ML Model (if only one CSI generation part AI/ML is configured, the UE (terminal device) does not need to report the AI/ML Model indication information);
  • Part 2 includes: the quantization information output by the CSI generation part AI/ML Model corresponding to each layer (For layer specific/common model), or the quantization information output by the CSI generation part AI/ML Model corresponding to a certain rank (for rank specific/common model).
  • CSI generates some indication information of the AI/ML Model and reports it in Part 2.
  • Alt1-2 (Layer specific/common model): Part 1 includes: RI, CQI, CSI generation part AI/ML Model/CSI recovery model, the quantization information length of the CSI generation part AI/ML Model output corresponding to each layer or the number of codewords output by the CSI generation AI/ML model (UE indicates the AI/ML model information to NW), and some candidate parameter values configured by the UE according to the network side equipment. Part 2 includes: the quantization information output by the CSI generation AI/ML model corresponding to each layer.
  • the data type of the input CSI generation part model is Alt2, that is, the precoding matrix of the angle and delay domains, and Part2 may also include indication information of the spatial domain basis vectors and the frequency domain basis vectors.
  • the vector quantization codeword indication information can be reported through Part 1 and Part 2 mentioned above, or it can be reported separately from Part 1 and Part 2 as auxiliary information.
  • Option1-2 Do not split CSI, that is, CSI is reported as a whole. If the reported CSI is less than the maximum CSI load configured by the network side device, the remaining part is filled with zero.
  • CSI includes: CQI, quantization information output by the AI/ML model generated by the CSI corresponding to each layer, or quantization information output by the AI/ML model generated by the CSI corresponding to each rank.
  • the RI information is determined by the configuration constraints of the network side device.
  • Option 1-3 The contents of Part 1 and Part 2 contained in the CSI are reported through PUCCH and/or PUSCH at different reporting times, or Part 1 and Part 2 are carried on PUCCH and PUSCH for reporting respectively.
  • the reporting time domain behavior can be periodic, semi-continuous or non-periodic. Note that the content of the reported Part 2 corresponds to the content of the previous and most adjacent reported Part 1, or the reported Part 2 corresponds to which reported Part 1 through the association of predefined or reporting IDs.
  • RI, CQI and CSI generate part of the quantitative information output by the AI/ML Model and send it to the network side device through two CSI reports.
  • Option 2 CSI generates an AI/ML Model which is selected and reported by the terminal device (considering that multiple models have been deployed on the UE).
  • Option2-1 CSI generates some AI/ML Model indication information, which is independently indicated and reported by the terminal device.
  • the indication information may be information indicating the function ID or Model ID of the AI/ML model.
  • the CSI generates some AI/ML Model indication information and reports it together with other CSI information, such as putting the CSI generated AI/ML Model indication information in the above-mentioned CSI Part 1 or Part 2 and reporting it to the network side device.
  • the network side device instructs the terminal device (UE) to use a CSI to generate a partial AI/ML Model and a maximum transmission rank through signaling such as RRC, MAC-CE or DCI.
  • the UE can determine the maximum payload length of the uplink transmission based on the configuration information.
  • the gNB directly indicates the maximum payload length and/or the maximum transmission rank of the UE uplink transmission through signaling.
  • the UE reports CSI according to the parameter information configured by the gNB and the estimated channel information.
  • the CSI report is divided into Part 1 (the first part of information) and Part 2 (the second part of information):
  • Part 1 includes: RI, CQI, CSI generation part AI/ML Model/CSI recovery part AI/ML Model indication information.
  • the RI and CQI indication information is the same as the traditional codebook-based CSI reporting indication method.
  • bits indicate the AI/ML Model selected by the UE, where X represents the number of AI/ML Models deployed on the UE side.
  • Part 2 includes: for Layer specific/common model, Part 2 contains the quantitative information of the CSI generation part AI/ML Model output corresponding to each layer; for Rank specific/common model, Part 2 contains the quantitative information of the CSI generation part AI/ML Model output.
  • Part 1 includes the AI/ML Model of the CSI generation part
  • the length of the compressed quantized information corresponding to each layer or each rank is also determined accordingly.
  • the UE does not need to indicate the length of the information in the feedback, thereby reducing the UE's feedback overhead.
  • the contents of Part 1 and Part 2 included in the CSI are respectively transmitted at different reporting times via PUCCH and/or PUSCH. Reporting:
  • the RI and CQI information included in Part 1 is reported via PUCCH or PUSCH at time T.
  • the quantization information output by the AI/ML Model of the CSI generation part included in Part 2 is reported through PUCCH or PUSCH at time T’, where T ⁇ T’.
  • the quantization information output by the AI/ML Model of the CSI generation part can be the quantization information corresponding to each transmission layer or a certain transmission rank.
  • the UE determines and selects one of the bilateral CSI models according to the current channel conditions and the subband size or CSI-RS port number configured by the network side device.
  • the UE reports the indication information of the selected model to the network side device (gNB) through a non-periodic CSI report.
  • the size of the indication information is bits. Or the indication information is reported to the gNB together with Part 1 described in the above embodiment 1.
  • the UE indicates the selected AI/ML model to the gNB, and the channel length corresponding to each AI/ML model is fixed. Therefore, when the rank is fixed, this indirectly reflects the load size required by the UE to feedback CSI. If the UE and gNB negotiate to predefine the CSI feedback load size based on the model, the gNB does not need to configure the CSI load size separately, thereby reducing the gNB configuration signaling overhead.
  • the CSI load size or the CSI reporting size is determined according to the AI/ML model adopted by the UE, so as to reduce the configuration signaling overhead or the UE feedback overhead.
  • the communication device 1 shown in Figure 12 may include a transceiver module 11 and a processing module.
  • the transceiver module may include a sending module and/or a receiving module, the sending module is used to implement a sending function, the receiving module is used to implement a receiving function, and the transceiver module may implement a sending function and/or a receiving function.
  • the communication device 1 may be a terminal device, a device in a terminal device, or a device that can be used in conjunction with a terminal device.
  • the communication device 1 may be a network side device, a device in a network side device, or a device that can be used in conjunction with a network side device.
  • the communication device 1 is configured on the terminal device side:
  • the device includes: a transceiver module 11.
  • the transceiver module 11 is configured to report channel state information CSI to the network side device, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the transceiver module 11 is further configured to report CSI to the network side device according to the determined maximum load.
  • the device includes: a processing module 12.
  • the processing module 12 is configured to determine the maximum load according to the adopted first model and/or the received first configuration information sent by the network side device, wherein the first configuration information is used to indicate the rank constraint condition.
  • the transceiver module 11 is further configured to receive second configuration information sent by a network side device, wherein the second configuration information is used to indicate multiple candidate first models; the processing module 12 is further configured to determine one of the candidate first models as the adopted first model.
  • the CSI further includes at least one of the following:
  • the second model is used to process the quantized information to restore predicted downlink channel information that is similar to the downlink channel information.
  • the transceiver module 11 is further configured to send model indication information to the network side device, wherein the model indication information is used to indicate at least one of the following:
  • the second model is used to process the quantized information to restore predicted downlink channel information that is similar to the downlink channel information.
  • the transceiver module 11 is further configured to report the first part of information and the second part of information to the network side device at different times, wherein the CSI includes the first part of information and the second part of information.
  • the transceiver module 11 is further configured to report the first part to the network side device using PUSCH or PUCCH. Information, and use PUSCH or PUCCH to report the second part of information to the network side device.
  • the transceiver module 11 is further configured to periodically report the first part of information and the second part of information to the network side device; or
  • the first part of information is associated with the second part of information that is adjacent thereto.
  • the first portion of information includes at least one of the following:
  • the second part of the information includes at least one of the following:
  • the length of quantized information of all layers obtained after the first model corresponding to all layers processes the downlink channel information
  • the number of codewords of all layers obtained after the first model corresponding to all layers processes the downlink channel information
  • Quantized information obtained after the first model corresponding to the specific rank processes the downlink channel information
  • the first model and the second model are obtained by training according to layer correspondence; or the first model and the second model are obtained by training according to rank correspondence.
  • the data type input to the first model includes a precoding matrix in the space-frequency domain, or a precoding matrix in the angle and delay domain.
  • the second part of the information also includes indication information of the space-domain basis vectors and the frequency-domain basis vectors selected by the terminal device.
  • the CSI also includes vector quantized codeword indication information, wherein the first model processes the downlink channel information and then further performs vector quantization processing to obtain quantized information.
  • the transceiver module 11 is further configured to report auxiliary information to the network side device, wherein the first model processes the downlink channel information and further performs vector quantization processing to obtain quantized information, and the auxiliary information includes vector quantization codeword indication information.
  • Communication device 1 configured on the network side device side:
  • the device includes: a transceiver module 11.
  • the transceiver module 11 is configured to receive CSI reported by the terminal device, wherein the CSI includes quantized information obtained after the first model corresponding to each layer or specific rank processes the downlink channel information.
  • the transceiver module 11 is further configured to receive CSI reported by the terminal device according to the determined maximum load.
  • the transceiver module 11 is further configured to send first configuration information to the terminal device, wherein the first configuration information is used by the terminal device to determine the maximum load, and the first configuration information is used to indicate a rank constraint condition.
  • the CSI further includes at least one of the following:
  • the second model is used to process the quantized information to restore predicted downlink channel information that is similar to the downlink channel information.
  • the transceiver module 11 is further configured to receive model indication information sent by the terminal device, wherein the model indication information is used to indicate at least one of the following:
  • the second model is used to process the quantized information to restore predicted downlink channel information that is similar to the downlink channel information.
  • the transceiver module 11 is further configured to receive the first part of information and the second part of information reported by the terminal device at different times, wherein the CSI includes the first part of information and the second part of information.
  • the transceiver module 11 is further configured to receive the first part of information reported by the terminal device using PUSCH or PUCCH, and the second part of information reported using PUSCH or PUCCH.
  • the transceiver module 11 is further configured to receive the first part of information and the second part of information periodically reported by the terminal device. information; or
  • the first part of information is associated with the second part of information that is adjacent thereto.
  • the first portion of information includes at least one of the following:
  • the second part of the information includes at least one of the following:
  • the first model and the second model are obtained by training according to layer correspondence; or the first model and the second model are obtained by training according to rank correspondence.
  • the data type input to the first model includes a precoding matrix in the space-frequency domain or a precoding matrix in the angle and delay domain, wherein, when the data type input to the first model is a precoding matrix in the angle and delay domain, the second part of the information also includes indication information of the space-domain basis vectors and the frequency-domain basis vectors selected by the terminal device.
  • the CSI also includes vector quantized codeword indication information, wherein the first model processes the downlink channel information and then further performs vector quantization processing to obtain quantized information.
  • the transceiver module 11 is further configured to receive auxiliary information reported by the terminal device, wherein the auxiliary information includes vector quantization codeword indication information. After the first model processes the downlink channel information, the quantization information is further obtained through vector quantization processing.
  • the communication device 1 provided in the above embodiments of the present disclosure achieves the same or similar beneficial effects as the channel state information reporting methods provided in some of the above embodiments, which will not be described in detail here.
  • FIG. 13 is a schematic diagram of the structure of another communication device 1000 provided in an embodiment of the present disclosure.
  • the communication device 1000 can be a terminal device, or a network side device, or a chip, a chip system, or a processor that supports the terminal device to implement the above method, or a chip, a chip system, or a processor that supports the network side device to implement the above method.
  • the communication device 1000 can be used to implement the method described in the above method embodiment, and the details can be referred to the description in the above method embodiment.
  • the communication device 1000 may include one or more processors 1001.
  • the processor 1001 may be a general-purpose processor or a dedicated processor, etc. For example, it may be a baseband processor or a central processing unit.
  • the baseband processor may be used to process the communication protocol and the communication data
  • the central processing unit may be used to control the communication device (such as a network side device, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute a computer program, and process the data of the computer program.
  • the communication device 1000 may further include one or more memories 1002, on which a computer program 1004 may be stored, and the memory 1002 executes the computer program 1004 so that the communication device 1000 executes the method described in the above method embodiment.
  • data may also be stored in the memory 1002.
  • the communication device 1000 and the memory 1002 may be provided separately or integrated together.
  • the communication device 1000 may further include a transceiver 1005 and an antenna 1006.
  • the transceiver 1005 may be referred to as a transceiver unit, a transceiver, or a transceiver circuit, etc., for implementing a transceiver function.
  • the transceiver 1005 may include a receiver and a transmitter, the receiver may be referred to as a receiver or a receiving circuit, etc., for implementing a receiving function; the transmitter may be referred to as a transmitter or a transmitting circuit, etc., for implementing a transmitting function.
  • the communication device 1000 may further include one or more interface circuits 1007.
  • the interface circuit 1007 is used to receive code instructions and transmit them to the processor 1001.
  • the processor 1001 executes the code instructions to enable the communication device 1000 to execute the method described in the above method embodiment.
  • the communication device 1000 is a terminal device: the transceiver 1005 is used to execute S31 in FIG. 3 ; S41 in FIG. 4 ; S51 in FIG. 5 ; S61 in FIG. 6 ; S71 in FIG. 7 ; and the processor 1001 is used to execute S51 in FIG. 5 .
  • the communication device 1000 is a network side device: the transceiver 1005 is used to execute S81 in FIG. 8 ; S91 in FIG. 9 ; S101 in FIG. 10 ; and S111 in FIG. 11 .
  • the processor 1001 may include a transceiver for implementing the receiving and sending functions.
  • the transceiver may be a transceiver circuit, or an interface, or an interface circuit.
  • the transceiver circuit, interface, or interface circuit for implementing the receiving and sending functions may be separate or integrated.
  • the transceiver circuit, interface, or interface circuit may be used for reading and writing code/data, or,
  • the above-mentioned transceiver circuit, interface or interface circuit can be used for transmission or transfer of signals.
  • the processor 1001 may store a computer program 1003, which runs on the processor 1001 and enables the communication device 1000 to perform the method described in the above method embodiment.
  • the computer program 1003 may be fixed in the processor 1001, in which case the processor 1001 may be implemented by hardware.
  • the communication device 1000 may include a circuit that can implement the functions of sending or receiving or communicating in the aforementioned method embodiments.
  • the processor and transceiver described in the present disclosure may be implemented in an integrated circuit (IC), an analog IC, a radio frequency integrated circuit RFIC, a mixed signal IC, an application specific integrated circuit (ASIC), a printed circuit board (PCB), an electronic device, etc.
  • the processor and transceiver may also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (NMOS), P-type metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.
  • CMOS complementary metal oxide semiconductor
  • NMOS N-type metal oxide semiconductor
  • PMOS P-type metal oxide semiconductor
  • BJT bipolar junction transistor
  • BiCMOS bipolar CMOS
  • SiGe silicon germanium
  • GaAs gallium arsenide
  • the communication device described in the above embodiments may be a terminal device or a network side device, but the scope of the communication device described in the present disclosure is not limited thereto, and the structure of the communication device may not be limited by FIG. 13.
  • the communication device may be an independent device or may be part of a larger device.
  • the communication device may be:
  • the IC set may also include a storage component for storing data and computer programs;
  • ASIC such as modem
  • FIG. 14 is a structural diagram of a chip provided in an embodiment of the present disclosure.
  • the chip 1100 includes a processor 1101 and an interface 1103.
  • the number of the processor 1101 may be one or more, and the number of the interface 1103 may be multiple.
  • the interface 1103 is used to receive code instructions and transmit them to the processor.
  • the processor 1101 is configured to run code instructions to execute the channel state information reporting method as described in some of the above embodiments.
  • the interface 1103 is used to receive code instructions and transmit them to the processor.
  • the processor 1101 is configured to run code instructions to execute the channel state information reporting method as described in some of the above embodiments.
  • the chip 1100 further includes a memory 1102, and the memory 1102 is used to store necessary computer programs and data.
  • the embodiments of the present disclosure also provide a channel status information reporting system, which includes the communication device as a terminal device and the communication device as a network side device in the embodiment of FIG. 12 above, or the communication device as a terminal device and the communication device as a network side device in the embodiment of FIG. 13 above.
  • the present disclosure also provides a readable storage medium having instructions stored thereon, which implement the functions of any of the above method embodiments when executed by a computer.
  • the present disclosure also provides a computer program product, which implements the functions of any of the above method embodiments when executed by a computer.
  • the computer program product includes one or more computer programs.
  • the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
  • the computer program can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • the computer program can be transmitted from one website, computer, server or data center to another website via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.)
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media.
  • 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)).
  • 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)
  • SSD solid state disk
  • At least one in the present disclosure may also be described as one or more, and a plurality may be two, three, four or more, which is not limited in the present disclosure.
  • the technical features in the technical feature are distinguished by “first”, “second”, “third”, “A”, “B”, “C” and “D”, etc., and there is no order of precedence or size between the technical features described by the "first”, “second”, “third”, “A”, “B”, “C” and “D”.
  • the corresponding relationships shown in the tables in the present disclosure can be configured or predefined.
  • the values of the information in each table are only examples and can be configured as other values, which are not limited by the present disclosure.
  • the corresponding relationships shown in some rows may not be configured.
  • appropriate deformation adjustments can be made based on the above table, such as splitting, merging, etc.
  • the names of the parameters shown in the titles of the above tables can also use other names that can be understood by the communication device, and the values or representations of the parameters can also be other values or representations that can be understood by the communication device.
  • other data structures can also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables or hash tables.
  • the predefined in the present disclosure may be understood as defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本公开实施例公开了一种信道状态信息的上报方法和装置,可应用于通信技术领域,由终端设备执行的方法包括:向网络侧设备上报CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。由此,可以实现终端设备上报包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息的CSI,以使网络侧设备能够获取准确的CSI。

Description

信道状态信息的上报方法和装置 技术领域
本公开涉及通信技术领域,尤其涉及一种信道状态信息的上报方法和装置。
背景技术
相关技术中,通过研究和仿真结果表明,采用人工智能(Artificial Intelligence,AI)/机器学习(Machine Learning,ML)等技术能够实现减少终端设备的反馈开销或提升信道状态信息(channel stateinformation,CSI)反馈精度。
发明内容
本公开实施例提供一种信道状态信息的上报方法和装置,可以实现终端设备上报包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息的CSI,以使网络侧设备能够获取准确的CSI。
第一方面,本公开实施例提供一种信道状态信息的上报方法,该方法由终端设备执行,该方法包括:终端设备向网络侧设备上报CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
在该技术方案中,终端设备向网络侧设备上报CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。由此,可以实现终端设备上报包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息的CSI,以使网络侧设备能够获取准确的CSI。
第二方面,本公开实施例提供另一种信道状态信息的上报方法,该方法由网络侧设备执行,该方法包括:接收终端设备上报的CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
第三方面,本公开实施例提供一种通信装置,该通信装置具有实现上述第一方面所述的方法中终端设备的部分或全部功能,比如通信装置的功能可具备本公开中的部分或全部实施例中的功能,也可以具备单独实施本公开中的任一个实施例的功能。所述功能可以通过硬件实现,也可以通过硬件执行相应的软件实现。所述硬件或软件包括一个或多个与上述功能相对应的单元或模块。
在一种实现方式中,该通信装置的结构中可包括收发模块和处理模块,所述处理模块被配置为支持通信装置执行上述方法中相应的功能。所述收发模块用于支持通信装置与其他设备之间的通信。所述通信装置还可以包括存储模块,所述存储模块用于与收发模块和处理模块耦合,其保存通信装置必要的计算机程序和数据。
在一种实现方式中,所述通信装置包括:收发模块,被配置为向网络侧设备上报CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
第四方面,本公开实施例提供另一种通信装置,该通信装置具有实现上述第二方面所述的方法示例中网络侧设备的部分或全部功能,比如通信装置的功能可具备本公开中的部分或全部实施例中的功能,也可以具备单独实施本公开中的任一个实施例的功能。所述功能可以通过硬件实现,也可以通过硬件执行相应的软件实现。所述硬件或软件包括一个或多个与上述功能相对应的单元或模块。
在一种实现方式中,该通信装置的结构中可包括收发模块和处理模块,该处理模块被配置为支持通信装置执行上述方法中相应的功能。收发模块用于支持通信装置与其他设备之间的通信。所述通信装置还可以包括存储模块,所述存储模块用于与收发模块和处理模块耦合,其保存通信装置必要的计算机程序和数据。
在一种实现方式中,所述通信装置包括:收发模块,被配置为接收终端设备上报的CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
第五方面,本公开实施例提供一种通信装置,该通信装置包括处理器,当该处理器调用存储器中的计算机程序时,执行上述第一方面所述的方法。
第六方面,本公开实施例提供一种通信装置,该通信装置包括处理器,当该处理器调用存储器中的计算机程序时,执行上述第二方面所述的方法。
第七方面,本公开实施例提供一种通信装置,该通信装置包括处理器和存储器,该存储器中存储有计算机程序;所述处理器执行该存储器所存储的计算机程序,以使该通信装置执行上述第一方面所述的方法。
第八方面,本公开实施例提供一种通信装置,该通信装置包括处理器和存储器,该存储器中存储有计算机程序;所述处理器执行该存储器所存储的计算机程序,以使该通信装置执行上述第二方面所述的 方法。
第九方面,本公开实施例提供一种通信装置,该装置包括处理器和接口电路,该接口电路用于接收代码指令并传输至该处理器,该处理器用于运行所述代码指令以使该装置执行上述第一方面所述的方法。
第十方面,本公开实施例提供一种通信装置,该装置包括处理器和接口电路,该接口电路用于接收代码指令并传输至该处理器,该处理器用于运行所述代码指令以使该装置执行上述第二方面所述的方法。
第十一方面,本公开实施例提供一种信道状态信息的上报系统,该系统包括第三方面所述的通信装置以及第四方面所述的通信装置,或者,该系统包括第五方面所述的通信装置以及第六方面所述的通信装置,或者,该系统包括第七方面所述的通信装置以及第八方面所述的通信装置,或者,该系统包括第九方面所述的通信装置以及第十方面所述的通信装置。
第十二方面,本发明实施例提供一种计算机可读存储介质,用于储存为上述终端设备所用的指令,当所述指令被执行时,使所述终端设备执行上述第一方面所述的方法。
第十三方面,本发明实施例提供一种可读存储介质,用于储存为上述网络侧设备所用的指令,当所述指令被执行时,使所述网络侧设备执行上述第二方面所述的方法。
第十四方面,本公开还提供一种包括计算机程序的计算机程序产品,当其在计算机上运行时,使得计算机执行上述第一方面所述的方法。
第十五方面,本公开还提供一种包括计算机程序的计算机程序产品,当其在计算机上运行时,使得计算机执行上述第二方面所述的方法。
第十六方面,本公开提供一种芯片系统,该芯片系统包括至少一个处理器和接口,用于支持终端设备实现第一方面所涉及的功能,例如,确定或处理上述方法中所涉及的数据和信息中的至少一种。在一种可能的设计中,所述芯片系统还包括存储器,所述存储器,用于保存终端设备必要的计算机程序和数据。该芯片系统,可以由芯片构成,也可以包括芯片和其他分立器件。
第十七方面,本公开提供一种芯片系统,该芯片系统包括至少一个处理器和接口,用于支持网络侧设备实现第二方面所涉及的功能,例如,确定或处理上述方法中所涉及的数据和信息中的至少一种。在一种可能的设计中,所述芯片系统还包括存储器,所述存储器,用于保存网络侧设备必要的计算机程序和数据。该芯片系统,可以由芯片构成,也可以包括芯片和其他分立器件。
第十八方面,本公开提供一种计算机程序,当其在计算机上运行时,使得计算机执行上述第一方面所述的方法。
第十九方面,本公开提供一种计算机程序,当其在计算机上运行时,使得计算机执行上述第二方面所述的方法。
附图说明
为了更清楚地说明本公开实施例或背景技术中的技术方案,下面将对本公开实施例或背景技术中所需要使用的附图进行说明。
图1是本公开实施例提供的一种通信系统的架构图;
图2是本公开实施例提供的一种基于双边AI/ML模型实现CSI压缩反馈和恢复的示意图;
图3是本公开实施例提供的一种信道状态信息的上报方法的流程图;
图4是本公开实施例提供的另一种信道状态信息的上报方法的流程图;
图5是本公开实施例提供的一种负载确定方法的流程图;
图6是本公开实施例提供的一种模型指示信息发送方法的流程图;
图7是本公开实施例提供的一种辅助信息上报方法的流程图;
图8是本公开实施例提供的又一种信道状态信息的上报方法的流程图;
图9是本公开实施例提供的又一种信道状态信息的上报方法的流程图;
图10是本公开实施例提供的另一种模型指示信息发送方法的流程图;
图11是本公开实施例提供的另一种辅助信息上报方法的流程图;
图12是本公开实施例提供的一种通信装置的结构图;
图13是本公开实施例提供的另一种通信装置的结构图;
图14是本公开实施例提供的一种芯片的结构示意图。
具体实施方式
为了更好的理解本公开实施例公开的一种信道状态信息的上报方法和装置,下面首先对本公开实施例适用的通信系统进行描述。
下面详细描述本公开的实施例,所述实施例的示例在附图中示出,其中自始至终相同或类似的标号 表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的,旨在用于解释本公开,而不能理解为对本公开的限制。其中,在本公开的描述中,除非另有说明,“/”表示或的意思,例如,A/B可以表示A或B;本文中的“和/或”仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。
为了便于理解本公开的技术方案,下面简单介绍本公开实施例涉及的一些术语。
1、SD(Spatial Domain,空域)基向量
本公开实施例中,空域可以包括发送侧空域和接收侧空域,空域基向量可以根据发送侧空域基向量确定。每个发送侧空域基向量可以对应发射端设备的一个发射波束(beam)。每个接收侧空域基向量可以对应接收端设备的一个接收波束(beam)。
下面以发送侧空域基向量为例进行说明,接收侧空域基向量与发送侧空域基向量类似。发送侧空域基向量通常与发送侧天线阵列相关联,举例来说,发送侧空域基向量表达式所涉及的许多参数可以理解为用于表征发送侧天线阵列的不同属性。尽管如此,本领域的技术人员应当明白,本公开实施例所涉及的发送侧空域基向量并非仅限于特定的天线阵列。在具体实现过程中,可以按照具体的需要,选择合适的天线阵列,并基于所选的天线阵列,设置本公开实施例所涉及的发送侧空域基向量中涉及的各种参数。
2、FD(Frequency Domain,频域)基向量
频域基向量用于表征信道在频域上的变化规律。频域基向量具体可用于表示各空域基向量的加权系数在各个频域单元上的变化规律。频域基向量所表征的变化规律与多径时延等因素相关。可以理解的是,由于信号在经过无线信道传输时,信号在不同的传输路径上可能存在不同的传输时延。不同的传输时延所导致的信道在频域上的变化规律可以由不同的频域基向量来表征。
在本公开实施例,频域基向量的维度是Nf,即一个频域基向量包含Nf个元素。
可选的,频域基向量的维度可以等于需要进行信道状态信息(Channel Status Information,CSI)测量的频域单元的数量。由于在不同的时刻需要进行CSI测量的频域单元的数量可能不同,因此频域基向量的维度也可能不同。换句话说,频域基向量的维度是可变的。
可选的,频域基向量的维度还可以等于终端设备的可用带宽所包括的频域单元的数目。其中,终端设备的可用带宽可以是网络设备配置的。终端设备的可用带宽是系统带宽的一部分或者全部。终端设备的可用带宽又可以称为部分带宽(bandwidth part,BWP),本公开实施例对此不作限定。
可选的,频域基向量的长度还可以等于用于指示待上报的频域单元的位置及个数的信令的长度,例如,频域基向量的长度可以等于信令的比特数等等。例如,在新无线(new radio,NR)中,用于指示待上报的频域单元的位置及个数的信令可以是用于上报带宽(reporting band)的信令。该信令例如可以通过位图的形式来指示待上报的频域单元的位置及个数。因此,频域基向量的维度可以为该位图的比特数。
3、TD(Time Domain,时域)基向量或Doppler域DD基向量
TD基向量或DD基向量用于表征信道在时域上的变化规律。也即,TD基向量或DD基向量用于表征信道的时变性。信道的时变性是指信道的传递函数随时间而变化。信道的时变性与多普勒频移(Doppler shift)等因素有关。
在本公开实施例,TD基向量或DD基向量的维度是Nt,即一个TD基向量或DD基向量包含Nt个元素。
可选的,TD基向量或DD基向量的维度可以等于需要进行CSI测量的时间单元的数量。可以理解的是,由于在不同的场景下,需要进行CSI测量的时间单元的数量可能不同,因此TD基向量或DD基向量的维度也可能不同。换句话说,TD基向量或DD基向量的维度是可变的。
请参见图1,图1为本公开实施例提供的一种通信系统的架构示意图。该通信系统可包括但不限于一个网络侧设备和一个终端设备,图1所示的设备数量和形态仅用于举例并不构成对本公开实施例的限定,实际应用中可以包括两个或两个以上的网络侧设备,两个或两个以上的终端设备。图1所示的通信系统10以包括一个网络侧设备101和一个终端设备102为例。
需要说明的是,本公开实施例的技术方案可以应用于各种通信系统。例如:长期演进(long term evolution,LTE)系统、第五代(5th generation,5G)移动通信系统、5G新空口(new radio,NR)系统,或者其他未来的新型移动通信系统等。
本公开实施例中的网络侧设备101可以是网络侧的一种用于发射或接收信号的实体。例如,网络侧设备101可以为接入网设备,包括演进型基站(evolved NodeB,eNB)、传输点(transmission reception point,TRP)、NR系统中的下一代基站(next generation NodeB,gNB)、其他未来移动通信系统中的基站或无线保真(wireless fidelity,WiFi)系统中的接入节点等。本公开的实施例对网络侧设备101所采用的具体技术和具体设备形态不做限定。本公开实施例提供的网络侧设备101可以是由集中单元 (central unit,CU)与分布式单元(distributed unit,DU)组成的,其中,CU也可以称为控制单元(control unit),采用CU-DU的结构可以将网络侧设备101,例如网络侧设备101的协议层拆分开,部分协议层的功能放在CU集中控制,剩下部分或全部协议层的功能分布在DU中,由CU集中控制DU。
本公开实施例中的终端设备102是用户侧的一种用于接收或发射信号的实体,如手机。终端设备也可以称为用户设备(user equipment,UE)终端(terminal)、移动台(mobile station,MS)、移动终端设备(mobile terminal,MT)等。终端设备可以是具备通信功能的汽车、智能汽车、手机(mobile phone)、穿戴式设备、平板电脑(Pad)、带无线收发功能的电脑、虚拟现实(virtual reality,VR)终端设备、增强现实(augmented reality,AR)终端设备、工业控制(industrial control)中的无线终端设备、无人驾驶(self-driving)中的无线终端设备、远程手术(remote medical surgery)中的无线终端设备、智能电网(smart grid)中的无线终端设备、运输安全(transportation safety)中的无线终端设备、智慧城市(smart city)中的无线终端设备、智慧家庭(smart home)中的无线终端设备等等。本公开的实施例对终端设备所采用的具体技术和具体设备形态不做限定。
可以理解的是,本公开实施例描述的通信系统是为了更加清楚的说明本公开实施例的技术方案,并不构成对于本公开实施例提供的技术方案的限定,本领域普通技术人员可知,随着系统架构的演变和新业务场景的出现,本公开实施例提供的技术方案对于类似的技术问题,同样适用。
此外,为了便于理解本公开实施例,做出以下几点说明。
第一,本公开实施例中,“用于指示”可以包括用于直接指示和用于间接指示。当描述某一信息用于指示A时,可以包括该信息携带有A,或者还可以包括该信息直接指示A或间接指示A,而并不代表该信息中一定携带有A。
将信息所指示的信息称为待指示信息,则具体实现过程中,对待指示信息进行指示的方式有很多种,例如但不限于,可以直接指示待指示信息,如待指示信息本身或者该待指示信息的索引等。也可以通过指示其他信息来间接指示待指示信息,其中该其他信息与待指示信息之间存在关联关系。还可以仅仅指示待指示信息的一部分,而待指示信息的其他部分则是已知的或者提前约定的。例如,还可以借助预先约定(例如协议规定)的各个信息的排列顺序来实现对特定信息的指示,从而在一定程度上降低指示开销。
待指示信息可以作为一个整体一起发送,也可以分成多个子信息分开发送,而且这些子信息的发送周期和/或发送时机可以相同,也可以不同。具体发送方法本公开不进行限定。其中,这些子信息的发送周期和/或发送时机可以是预先定义的,例如根据协议预先定义的。
第二,在本公开中第一、第二以及各种数字编号(例如,“#1”、“#2”)仅为描述方便进行的区分,并不用来限制本公开实施例的范围。例如,区分不同的信息等。
第三,本公开实施例列举了多个实施方式以对本公开实施例的技术方案进行清晰地说明。当然,本领域内技术人员可以理解,本公开实施例提供的多个实施例,可以被单独执行,也可以与本公开实施例中其他实施例的方法结合后一起被执行,还可以单独或结合后与其他相关技术中的一些方法一起被执行;本公开实施例并不对此进行限定。
相关技术中,终端设备在某一个频段上向网络侧设备发送信息的同时,网络侧设备在另一个频段上需要向终端设备发送信息,终端设备在多个频段上需要同时进行收发,此时会导致同时进行收发的多个频段之间存在收发干扰,这是亟需解决的问题。
相关技术中,通过研究和仿真结果表明,采用AI/ML等技术能够实现减少终端设备的反馈开销或提升信道状态信息(channel stateinformation,CSI)反馈精度。
其中,在第三代合伙项目(3rd Generation Partnership Project,3GPP)的研究中开展了在终端设备的CSI生成部分模型和网络侧设备的CSI恢复部分模型的成对(双边)AI/ML模型分别实现CSI的压缩反馈和恢复。
如图2所示,一种基于双边AI/ML模型实现CSI压缩反馈和恢复的示意图,终端设备(UE)通过CSI生成部分模型把下行信道信息H压缩后通过量化为二进制比特流发送给网络侧设备(gNB),网络侧设备通过CSI恢复部分模型恢复出与原来下行信道信息近似的H’。
需要说明的是,CSI生成部分模型的类型可以有很多种,与其训练时使用的数据、训练方式以及所采用的基础模型等有关,终端设备还可以通过CSI生成部分模型直接把下行信道信息H压缩量化为二进制比特流。
其中,训练CSI生成部分模型和CSI恢复部分模型的双边模型的方式包括以下几种:
秩特定(rank specific)的方式:针对每一个秩训练一个包含CSI生成部分模型和CSI恢复部分模型的双边模型;
秩共同(rank common)的方式:对所有秩只训练一个包含CSI生成部分模型和CSI恢复部分模型的双边模型;
层特定(layer specific)的方式:针对每一个层训练一个包含CSI生成部分模型和CSI恢复部分模型的双边模型;
层共同(layer common)的方式:对所有层只训练一个包含CSI生成部分模型和CSI恢复部分模型的双边模型。
相关技术中,CSI反馈方法采用版本16(Rel-16)类型二(Type II)码本方式或版本17(Rel-17)类型二(Type II)码本方式的CSI反馈。
Rel-16Type II码本方式或Rel-17Type II码本方式的CSI反馈,把CSI分为第一部分(Part1)和第二部分(Part2)上报,上报内容如表1所示。
表1
但是对于双边AI/ML模型,训练CSI生成部分模型和CSI恢复部分模型的双边模型的方式有多种,终端设备如何进行CSI的上报,是亟需解决的问题。
基于此,本公开实施例中提出一种信道状态信息的上报方法,终端设备向网络侧设备上报CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。由此,可以实现终端设备上报包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息的CSI,以使网络侧设备能够获取准确的CSI。
下面结合附图对本公开所提供的一种信道状态信息的上报方法和装置进行详细地介绍。
请参见图3,图3是本公开实施例提供的一种信道状态信息的上报方法的流程图。如图3所示,该方法由终端设备执行,该方法可以包括但不限于如下步骤:
S31:向网络侧设备上报CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
本公开实施例中,终端设备可以向网络侧设备上报CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
本公开实施例中,终端设备可以使用第一模型对下行信道信息进行处理得到量化信息。第一模型可以为终端设备侧的CSI生成部分模型。
其中,第一模型可以对下行信道信息进行推理和/或预测,进而得到量化信息。
可以理解的是,第一模型的类型可以有很多种,与其训练时使用的数据、训练方式以及所采用的基础模型等有关。
在一种可能的实现方式中,终端设备使用第一模型对下行信道信息进行处理之后进行矢量量化后可以得到量化信息。
在另一种可能的实现方式中,终端设备使用第一模型对下行信道信息进行处理以及矢量量化之后可以直接得到量化信息。
本公开实施例中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
其中,终端设备向网络侧设备上报的CSI中,包括每个层对应的第一模型对下行信道信息进行处理后得到的量化信息。
可以理解的是,在存在多个层的情况下,不同层对应的第一模型可以相同或不同,基于此,终端设备可以向网络侧设备上报每个层对应的第一模型对下行信道信息进行处理后得到的量化信息。
其中,终端设备向网络侧设备上报的CSI中,包括特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
可以理解的是,网络侧设备可以指示终端设备上行传输的最大传输秩,在秩≥1的情况下,不同秩对应的第一模型可以相同或不同,终端设备可以选择其中的一个秩为特定秩,向网络侧设备上报特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
在一些实施例中,终端设备向网络侧设备发送模型指示信息,其中,模型指示信息用于指示以下至少一项:
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第一模型和匹配使用的第二模型的模型对的指示信息;
其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
本公开实施例中,终端设备可以向网络侧设备发送模型指示信息,模型指示信息可以包括第一模型的指示信息。
其中,第一模型的指示信息可以用于指示第一模型,可以用来告诉网络侧设备,终端设备使用的第一模型的信息。
本公开实施例中,终端设备可以向网络侧设备发送模型指示信息,模型指示信息可以包括与第一模型匹配使用的第二模型的指示信息,其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,与第一模型匹配使用的第二模型可以为网络侧设备的CSI恢复部分模型,第一模型和第二模型可以采用上述示例的秩特定的方式、秩共同的方式、层特定的方式或层共同的方式进行训练得到。
其中,与第一模型匹配使用的第二模型的指示信息,可以用来指示第二模型,用来告诉网络侧设备,其应该与第一模型匹配使用的第二模型的信息,可以告知网络侧设备使用相应的第二模型进行处理。
本公开实施例中,终端设备可以向网络侧设备发送模型指示信息,模型指示信息可以包括第一模型和匹配使用的第二模型的模型对的指示信息,其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,第一模型和匹配使用的第二模型的模型对的指示信息,可以用于指示第一模型和第二模型的模型对的信息,可以用来告诉网络侧设备,终端设备使用的第一模型的信息,以及与第一模型匹配使用的第二模型的信息,可以告知网络侧设备使用相应的第二模型进行处理。
需要说明的是,上述实施例并没有穷举,仅为部分实施例的示意,并且上述实施例可以单独被实施,也可以多个进行组合被实施,上述实施例仅作为示意,不作为对本公开实施例保护范围的具体限制。
在一些实施例中,终端设备处可以配置一个或多个候选第一模型,终端设备可以自行选择一个作为第一模型。
在另一些实施例中,终端设备可以接收网络侧设备的配置信息,配置信息用于指示一个或多个候选第一模型。其中,在配置信息指示一个候选第一模型的情况下,终端设备可以确定该候选第一模型为第一模型;在配置信息指示多个候选第一模型的情况下,终端设备可以选择其中一个确定为第一模型。
需要说明的是,若网络侧设备的配置信息仅指示一个候选第一模型的情况下,由于仅有一个候选第一模型,终端设备必然会选择该候选第一模型为第一模型,网络侧设备可以知晓终端设备选择的第一模型,基于此,终端设备可以不用上报第一模型的指示信息。
在一些实施例中,CSI中还包括以下至少一项:
RI;
CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第一模型和匹配使用的第二模型的模型对的指示信息;
其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
本公开实施例中,CSI中还可以包括RI。其中,终端设备可以根据网络侧设备配置的约束确定RI,进而上报给网络侧设备。
本公开实施例中,CSI中还可以包括CQI。
本公开实施例中,CSI中还可以包括第一模型的指示信息。
其中,第一模型的指示信息可以用于指示第一模型,可以用来告诉网络侧设备,终端设备使用的第一模型的信息。
本公开实施例中,CSI中还可以包括与第一模型匹配使用的第二模型的指示信息;其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,与第一模型匹配使用的第二模型可以为网络侧设备的CSI恢复部分模型,第一模型和第二 模型可以采用上述示例的秩特定的方式、秩共同的方式、层特定的方式或层共同的方式进行训练得到。
其中,CSI中还包括与第一模型匹配使用的第二模型的指示信息,可以用来指示第二模型,用来告诉网络侧设备,其应该与第一模型匹配使用的第二模型的信息,可以告知网络侧设备使用相应的第二模型进行处理。
本公开实施例中,CSI中还可以包括第一模型和匹配使用的第二模型的模型对的指示信息;其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,终端设备可以上报模型对的指示信息,用来告诉网络侧设备,终端设备使用的第一模型的信息,以及与第一模型匹配使用的第二模型的信息,可以告知网络侧设备使用相应的第二模型进行处理。
需要说明的是,上述实施例并没有穷举,仅为部分实施例的示意,并且上述实施例可以单独被实施,也可以多个进行组合被实施,上述实施例仅作为示意,不作为对本公开实施例保护范围的具体限制。
在一些实施例中,终端设备向网络侧设备上报CSI,可以将CSI的内容作为整体一起上报,或者还可以将CSI的内容进行拆分,分多次分别上报。
在一些实施例中,若终端设备选择将CSI的内容进行拆分,分多次分别上报的情况下,终端设备可以在不同时间,分多次分别上报,以实现向网络侧设备上报CSI。
在一些实施例中,终端设备向网络侧设备上报CSI,包括:在不同时刻,向网络侧设备上报第一部分信息和第二部分信息,其中,CSI包括第一部分信息和第二部分信息。
本公开实施例中,终端设备向网络侧设备上报CSI,可以在不同时刻,向网络侧设备上报第一部分信息和第二部分信息。
其中,CSI包括第一部分信息和第二部分信息。
在一些实施例中,终端设备向网络侧设备上报第一部分信息和第二部分信息,包括:使用物理上行共享信道(Physical Uplink Shared Channel,PUSCH)或物理上行控制信道(Physical Uplink Control Channel,PUCCH),向网络侧设备上报第一部分信息,以及使用PUSCH或PUCCH,向网络侧设备上报第二部分信息。
本公开实施例中,终端设备可以使用PUSCH或PUCCH,向网络侧设备上报第一部分信息,以及使用PUSCH或PUCCH,向网络侧设备上报第二部分信息。
在一些实施例中,终端设备向网络侧设备上报第一部分信息和第二部分信息,包括:
周期性地向网络侧设备上报第一部分信息和第二部分信息;或
非周期性地向网络侧设备上报第一部分信息和第二部分信息;或
半持续性地向网络侧设备上报第一部分信息和第二部分信息;
其中,第一部分信息与之后相邻的第二部分信息具有关联关系。
本公开实施例中,终端设备可以周期性地向网络侧设备上报第一部分信息和第二部分信息,其中,第一部分信息与之后相邻的第二部分信息具有关联关系。
本公开实施例中,终端设备可以非周期性地向网络侧设备上报第一部分信息和第二部分信息,其中,第一部分信息与之后相邻的第二部分信息具有关联关系。
本公开实施例中,终端设备可以半持续性地向网络侧设备上报第一部分信息和第二部分信息,其中,第一部分信息与之后相邻的第二部分信息具有关联关系。
可以理解的是,终端设备上报的第一部分信息的内容与它之后且最临近的上报的第二部分内容相对应,第一部分信息与之后相邻的第二部分信息具有关联关系。
本公开实施例中,可以通过预定义或上报标识的关联关系,确定上报的第二部分信息与哪一个上报的第一部分信息相对应。其中,第一部分信息对应第一标识,第二部分信息对应第二标识,可以上报第一标识与第二标识具有关联关系,确定第二部分信息对应的第一部分信息。
在一些实施例中,第一部分信息包括以下至少一项:
RI;
CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第二部分信息包括以下至少一项:
每个层对应的第一模型对下行信道信息进行处理后得到的量化信息;
所有层对应的第一模型对下行信道信息进行处理后得到的所有层的量化信息的长度;
所有层对应的第一模型对下行信道信息进行处理后得到的所有层的码字个数;
特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息;
第一模型的指示信息。
本公开实施例中,第一部分信息可以包括以下至少一项:
RI;
CQI;
第一模型的指示信息;与第一模型匹配使用的第二模型的指示信息。
第二部分信息可以包括以下至少一项:
每个层对应的第一模型对下行信道信息进行处理后得到的量化信息;
所有层对应的第一模型对下行信道信息进行处理后得到的所有层的量化信息的长度;
所有层对应的第一模型对下行信道信息进行处理后得到的所有层的码字个数;
特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息;
第一模型的指示信息。
需要说明的是,在第一部分信息中未包括第一模型的指示信息的情况下,第二部分信息中可以包括第一模型的指示信息。
需要说明的是,在网络侧设备仅为终端设备配置一个第一模型的情况下,第一部分信息和第二部分信息中可以不包括第一模型的指示信息。
在一些实施例中,第一模型和第二模型为根据层对应训练得到的;或者第一模型和第二模型为根据秩对应训练得到的。
本公开实施例中,第一模型和第二模型为根据层对应训练得到的,其中,第一模型和第二模型可以采用层特定的方式进行训练得到,或者还可以采用层共同的方式进行训练得到。
本公开实施例中,第一模型和第二模型为根据层对应训练得到的,其中,第一模型和第二模型可以采用秩特定的方式进行训练得到,或者还可以采用秩共同的方式进行训练得到。
本公开实施例中,根据层对应训练得到第一模型和第二模型,可以采用层特定的方式,或者还可以采用层共同的方式训练得到第一模型和第二模型。
其中,采用层特定的方式训练得到第一模型和第二模型,可以针对每一个层训练一个包含第一模型和第二模型的双边模型。
其中,采用层共同的方式训练得到第一模型和第二模型,可以对所有层只训练一个包含第一模型和第二模型的双边模型。
本公开实施例中,若根据层对应训练得到第一模型和第二模型,第一部分信息包括以下至少一项:
RI;
CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
每个层对应的第一模型对下行信道信息进行处理后得到的量化信息的长度;
每个层对应的第一模型对下行信道信息进行处理后得到的码字个数。
第二部分信息包括每个层对应的第一模型对下行信道信息进行处理后得到的量化信息。
本公开实施例中,根据秩对应训练得到第一模型和第二模型,可以采用秩特定的方式,或者还可以采用秩共同的方式训练得到第一模型和第二模型。
其中,采用秩特定的方式训练得到第一模型和第二模型,可以针对每一个秩训练一个包含第一模型和第二模型的双边模型。
其中,采用秩共同的方式训练得到第一模型和第二模型,可以对所有秩只训练一个包含第一模型和第二模型的双边模型。
本公开实施例中,若根据秩对应训练得到第一模型和第二模型,第一部分信息包括以下至少一项:
RI;
CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息的长度;
特定秩对应的第一模型对下行信道信息进行处理后得到的码字个数。
第二部分信息包括特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
在一些实施例中,输入第一模型的数据类型可以包括两种,一种是空频域的预编码矩阵,另一种是角度与时延域的预编码矩阵。
其中,不管输入第一模型的数据类型哪种,第一部分模型和第二部分模型所包括的信息可以与上面一些实施例中所述的第一部分信息和第二部分信息包括的内容相同。
可以理解的是,本公开实施例中,第一部分信息中包括第一模型的指示信息,相应的每个层或每个秩对应的第一模型对下行信道信息进行处理后得到的量化信息的长度也可以直接确定,终端设备可以无需上报每个层或每个秩对应的第一模型对下行信道信息进行处理后得到的量化信息的长度,从而可以减少终端设备的反馈开销。
在一些实施例中,输入第一模型的数据类型包括空频域的预编码矩阵、或角度与时延域的预编码矩阵,其中,在输入第一模型的数据类型为角度与时延域的预编码矩阵的情况下,第二部分信息中还包括终端设备选择的空域基向量和频域基向量的指示信息。
本公开实施例中,输入第一模型的数据类型可以包括两种,一种是空频域的预编码矩阵,另一种是角度与时延域的预编码矩阵。
其中,在输入第一模型的数据类型为空频域的预编码矩阵的情况下,第一部分模型和第二部分模型所包括的信息可以与上面一些实施例中所述的第一部分信息和第二部分信息包括的内容相同。
其中,在输入第一模型的数据类型为角度与时延域的预编码矩阵的情况下,第一部分信息所包括的内容可以与上面一些实施例中所述的第一部分信息包括的内容相同,第二部分信息中除包括上面一些实施例中所述的第二部分信息包括的内容以外,还可以包括终端设备选择的空域基向量和频域基向量的指示信息。
可以理解的是,终端设备可以基于网络侧设备的配置确定空域基向量和频域基向量的指示信息,在此情况下,终端设备可以不需要上报空域基向量和频域基向量的指示信息。若终端设备选择的空域基向量和频域基向量的指示信息,终端设备需要上报空域基向量和频域基向量的指示信息。
在一些实施例中,CSI中还包括矢量量化的码字指示信息,其中,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息。
本公开实施例中,在第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后才得到量化信息的情况下,CSI中还可以包括矢量量化的码字指示信息。
在一些实施例中,终端设备向网络侧设备上报辅助信息,其中,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息,辅助信息中包括矢量量化的码字指示信息。
本公开实施例中,在第一对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息的情况下,终端设备可以向网络侧设备上报辅助信息,辅助信息中包括矢量量化的码字指示信息。
在本实施方式或实施例中,在不矛盾的情况下,各步骤可以独立、任意组合或交换顺序,可选方式或可选例可以任意组合,且可以与其他实施方式或实施例任意组合。
通过实施本公开实施例,终端设备向网络侧设备上报CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。由此,可以实现终端设备上报包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息的CSI,以使网络侧设备能够获取准确的CSI。
请参见图4,图4是本公开实施例提供的另一种信道状态信息的上报方法的流程图。如图4所示,该方法由终端设备执行,该方法可以包括但不限于如下步骤:
S41:根据确定的最大负载,向网络侧设备上报CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
本公开实施例中,终端设备可以根据确定的最大负载,向网络侧设备上报CSI。
其中,终端设备向网络侧设备上报CSI的相关描述可以参见上述实施例中的相关描述,此处不再赘述。
其中,终端设备可以基于网络侧设备的配置确定最大负载,或者,终端设备还可以根据其他信息确定最大负载,本公开实施例对此不作具体限制。
在一些实施例中,终端设备根据所采用的第一模型和/或接收到的网络侧设备发送的第一配置信息,确定最大负载,其中,第一配置信息用于指示秩约束条件。
本公开实施例中,终端设备可以根据所采用的第一模型,确定最大负载。
本公开实施例中,终端设备可以根据接收到的网络侧设备发送的第一配置信息,确定最大负载。
其中,第一配置信息用于指示秩约束条件。终端设备可以根据网络侧设备发送的秩约束条件,确定最大负载。
可以理解的是,终端设备根据所采用的第一模型和/或接收到的网络侧设备发送的第一配置信息,确定最大负载,无需网络侧设备为终端设备配置最大负载,可以减少信令开销。
本公开实施例中,终端设备根据确定的最大负载,向网络侧设备上报CSI,在CSI小于最大负载的情况下,对剩余的部分填零,向网络侧设备上报CSI。
其中,在CSI等于最大负载的情况下,可以直接向网络侧设备上报CSI。
其中,在CSI大于最大负载的情况下,可以全部丢弃CSI,或者还可以丢弃CSI中的部分信息,向网络侧设备上报CSI的剩余部分信息;其中,可以根据CSI丢弃准则或方法丢弃CSI上报中的部分信息。
在本实施方式或实施例中,在不矛盾的情况下,各步骤可以独立、任意组合或交换顺序,可选方式或可选例可以任意组合,且可以与其他实施方式或实施例任意组合。
需要说明的是,本公开实施例中,S41可以单独被实施,也可以结合本公开实施例中的任何一个其他步骤一起被实施,例如结合本公开实施例中的S31一起被实施,本公开实施例并不对此做出限定。
通过实施本公开实施例,终端设备根据确定的最大负载,向网络侧设备上报CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。由此,可以实现终端设备根据确定的最大负载,上报包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息的CSI,以使网络侧设备能够获取准确的CSI。
请参见图5,图5是本公开实施例提供的一种负载确定方法的流程图。如图5所示,该方法由终端设备执行,该方法可以包括但不限于如下步骤:
S51:根据所采用的第一模型和/或接收到的网络侧设备发送的第一配置信息,确定最大负载,其中,第一配置信息用于指示秩约束条件。
本公开实施例中,终端设备可以根据所采用的第一模型,确定最大负载。
本公开实施例中,终端设备可以根据接收到的网络侧设备发送的第一配置信息,确定最大负载。
其中,第一配置信息用于指示秩约束条件。终端设备可以根据网络侧设备发送的秩约束条件,确定最大负载。
可以理解的是,终端设备根据所采用的第一模型和/或接收到的网络侧设备发送的第一配置信息,确定最大负载,无需网络侧设备为终端设备配置最大负载,可以减少信令开销。
本公开实施例中,终端设备确定所采用的第一模型,可以基于终端设备实现确定所采用的第一模型,或者还可以基于协议约定确定所采用的第一模型,或者还可以基于网络侧设备的配置确定所采用的第一模型。
其中,网络侧设备的配置可以指示一个或多个候选第一模型,终端设备可以确定其中的一个为所采用的第一模型。
在一些实施例中,终端设备接收网络侧设备发送的第二配置信息,其中,第二配置信息用于指示多个候选第一模型;从候选第一模型中确定一个为所采用的第一模型。
本公开实施例中,终端设备可以接收网络侧设备发送的第二配置信息,其中,第二配置信息用于指示多个候选第一模型;由此,终端设备可以从候选第一模型中确定一个为所采用的第一模型。
在本实施方式或实施例中,在不矛盾的情况下,各步骤可以独立、任意组合或交换顺序,可选方式或可选例可以任意组合,且可以与其他实施方式或实施例任意组合。
需要说明的是,本公开实施例中,S51可以单独被实施,也可以结合本公开实施例中的任何一个其他步骤一起被实施,例如结合本公开实施例中的S31和/或S41一起被实施,本公开实施例并不对此做出限定。
通过实施本公开实施例,终端设备根据所采用的第一模型和/或接收到的网络侧设备发送的第一配置信息,确定最大负载,其中,第一配置信息用于指示秩约束条件。由此,可以实现终端设备确定最大负载,减少信令开销。
请参见图6,图6是本公开实施例提供的一种模型指示信息发送方法的流程图。如图6所示,该方法由终端设备执行,该方法可以包括但不限于如下步骤:
S61:向网络侧设备发送模型指示信息。
其中,模型指示信息用于指示以下至少一项:
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第一模型和匹配使用的第二模型的模型对的指示信息;
其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
本公开实施例中,终端设备可以向网络侧设备发送模型指示信息,模型指示信息可以包括第一模型的指示信息。
其中,第一模型的指示信息可以用于指示第一模型,可以用来告诉网络侧设备,终端设备使用的第 一模型的信息。
本公开实施例中,终端设备可以向网络侧设备发送模型指示信息,模型指示信息可以包括与第一模型匹配使用的第二模型的指示信息,其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,与第一模型匹配使用的第二模型可以为网络侧设备的CSI恢复部分模型,第一模型和第二模型可以采用上述示例的秩特定的方式、秩共同的方式、层特定的方式或层共同的方式进行训练得到。
其中,与第一模型匹配使用的第二模型的指示信息,可以用来指示第二模型,用来告诉网络侧设备,其应该与第一模型匹配使用的第二模型的信息,可以告知网络侧设备使用相应的第二模型进行处理。
本公开实施例中,终端设备可以向网络侧设备发送模型指示信息,模型指示信息可以包括第一模型和匹配使用的第二模型的模型对的指示信息,其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,第一模型和匹配使用的第二模型的模型对的指示信息,可以用于指示第一模型和第二模型的模型对的信息,可以用来告诉网络侧设备,终端设备使用的第一模型的信息,以及与第一模型匹配使用的第二模型的信息,可以告知网络侧设备使用相应的第二模型进行处理。
需要说明的是,上述实施例并没有穷举,仅为部分实施例的示意,并且上述实施例可以单独被实施,也可以多个进行组合被实施,上述实施例仅作为示意,不作为对本公开实施例保护范围的具体限制。
在一些实施例中,终端设备处可以配置一个或多个候选第一模型,终端设备可以自行选择一个作为第一模型。
在另一些实施例中,终端设备可以接收网络侧设备的配置信息,配置信息用于指示一个或多个候选第一模型。其中,在配置信息指示一个候选第一模型的情况下,终端设备可以确定该候选第一模型为第一模型;在配置信息指示多个候选第一模型的情况下,终端设备可以选择其中一个确定为第一模型。
需要说明的是,若网络侧设备的配置信息仅指示一个候选第一模型的情况下,由于仅有一个候选第一模型,终端设备必然会选择该候选第一模型为第一模型,网络侧设备可以知晓终端设备选择的第一模型,基于此,终端设备可以不用上报第一模型的指示信息。
在本实施方式或实施例中,在不矛盾的情况下,各步骤可以独立、任意组合或交换顺序,可选方式或可选例可以任意组合,且可以与其他实施方式或实施例任意组合。
需要说明的是,本公开实施例中,S61可以单独被实施,也可以结合本公开实施例中的任何一个其他步骤一起被实施,例如结合本公开实施例中的S31和/或S41和/或S51一起被实施,本公开实施例并不对此做出限定。
通过实施本公开实施例,终端设备向网络侧设备发送模型指示信息。由此,可以实现终端设备向网络侧设备发送模型指示信息。
请参见图7,图7是本公开实施例提供的一种辅助信息上报方法的流程图。如图7所示,该方法由终端设备执行,该方法可以包括但不限于如下步骤:
S71:向网络侧设备上报辅助信息,其中,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息,辅助信息中包括矢量量化的码字指示信息。
本公开实施例中,在第一对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息的情况下,终端设备可以向网络侧设备上报辅助信息,辅助信息中包括矢量量化的码字指示信息。
本公开实施例中,终端设备向网络侧设备上报辅助信息可以单独上报,或者还可以与其他信息同时上报,本公开实施例对此不作具体限制。
本公开实施例中,终端设备向网络侧设备上报辅助信息可以复用现有的信令或消息,或者还可以使用新的信令或消息,本公开实施例对此不作具体限制。
在本实施方式或实施例中,在不矛盾的情况下,各步骤可以独立、任意组合或交换顺序,可选方式或可选例可以任意组合,且可以与其他实施方式或实施例任意组合。
需要说明的是,本公开实施例中,S71可以单独被实施,也可以结合本公开实施例中的任何一个其他步骤一起被实施,例如结合本公开实施例中的S31和/或S41和/或S51和/或S61一起被实施,本公开实施例并不对此做出限定。
通过实施本公开实施例,终端设备向网络侧设备上报辅助信息,其中,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息,辅助信息中包括矢量量化的码字指示信息。由此,可以实现终端设备向网络侧设备上报矢量量化的码字指示信息。
请参见图8,图8是本公开实施例提供的又一种信道状态信息的上报方法的流程图。如图8所示, 该方法由网络侧设备执行,该方法可以包括但不限于如下步骤:
S81:接收终端设备上报的CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
本公开实施例中,网络侧设备可以接收终端设备上报的CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
本公开实施例中,终端设备可以使用第一模型对下行信道信息进行处理得到量化信息。第一模型可以为终端设备侧的CSI生成部分模型。
可以理解的是,第一模型的类型可以有很多种,与其训练时使用的数据、训练方式以及所采用的基础模型等有关。
在一种可能的实现方式中,终端设备使用第一模型对下行信道信息进行处理之后进行矢量量化后可以得到量化信息。
在另一种可能的实现方式中,终端设备使用第一模型对下行信道信息进行处理以及矢量量化之后可以直接得到量化信息。
本公开实施例中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
其中,网络侧设备接收终端设备上报的CSI中,包括每个层对应的第一模型对下行信道信息进行处理后得到的量化信息。
可以理解的是,在存在多个层的情况下,不同层对应的第一模型可以相同或不同,基于此,网络侧设备可以接收终端设备上报的每个层对应的第一模型对下行信道信息进行处理后得到的量化信息。
其中,网络侧设备接收终端设备上报的CSI中,包括特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
可以理解的是,网络侧设备可以指示终端设备上行传输的最大传输秩,在秩≥1的情况下,不同秩对应的第一模型可以相同或不同,终端设备可以选择其中的一个秩为特定秩,基于此,网络侧设备可以接收终端设备上报的特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
在一些实施例中,网络侧设备接收终端设备发送的模型指示信息,其中,模型指示信息用于指示以下至少一项:
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第一模型和匹配使用的第二模型的模型对的指示信息;
其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
本公开实施例中,网络侧设备可以接收终端设备发送的模型指示信息,模型指示信息可以包括第一模型的指示信息。
其中,第一模型的指示信息可以用于指示第一模型,网络侧设备可以确定终端设备使用的第一模型。
本公开实施例中,网络侧设备可以接收终端设备发送的模型指示信息,模型指示信息可以包括与第一模型匹配使用的第二模型的指示信息,其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,与第一模型匹配使用的第二模型可以为网络侧设备的CSI恢复部分模型,第一模型和第二模型可以采用上述示例的秩特定的方式、秩共同的方式、层特定的方式或层共同的方式进行训练得到。
其中,与第一模型匹配使用的第二模型的指示信息,可以用来指示第二模型,网络侧设备可以确定应该与第一模型匹配使用的第二模型,进而可以使用第二模型进行处理。
本公开实施例中,网络侧设备可以接收终端设备发送的模型指示信息,模型指示信息可以包括第一模型和匹配使用的第二模型的模型对的指示信息,其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,第一模型和匹配使用的第二模型的模型对的指示信息,可以用于指示第一模型和第二模型的模型对的信息,网络侧设备可以确定终端设备使用的第一模型的信息,以及与第一模型匹配使用的第二模型,进而可以使用第二模型进行处理。
需要说明的是,上述实施例并没有穷举,仅为部分实施例的示意,并且上述实施例可以单独被实施,也可以多个进行组合被实施,上述实施例仅作为示意,不作为对本公开实施例保护范围的具体限制。
在一些实施例中,终端设备处可以配置一个或多个候选第一模型,终端设备可以自行选择一个作为第一模型。
在另一些实施例中,网络侧设备可以向终端设备发送配置信息,配置信息用于指示一个或多个候选第一模型。其中,在配置信息指示一个候选第一模型的情况下,终端设备可以确定该候选第一模型为第 一模型;在配置信息指示多个候选第一模型的情况下,终端设备可以选择其中一个确定为第一模型。
需要说明的是,若网络侧设备的配置信息仅指示一个候选第一模型的情况下,由于仅有一个候选第一模型,终端设备必然会选择该候选第一模型为第一模型,网络侧设备可以知晓终端设备选择的第一模型,基于此,终端设备可以不用上报第一模型的指示信息。
在一些实施例中,CSI中还包括以下至少一项:
RI;
CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第一模型和匹配使用的第二模型的模型对的指示信息;
其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
本公开实施例中,CSI中还可以包括RI。其中,终端设备可以根据网络侧设备配置的约束确定RI,进而上报给网络侧设备。
本公开实施例中,CSI中还可以包括CQI。
本公开实施例中,CSI中还可以包括第一模型的指示信息。
其中,第一模型的指示信息可以用于指示第一模型,网络侧设备可以确定终端设备使用的第一模型。
本公开实施例中,CSI中还可以包括与第一模型匹配使用的第二模型的指示信息,其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,与第一模型匹配使用的第二模型可以为网络侧设备的CSI恢复部分模型,第一模型和第二模型可以采用上述示例的秩特定的方式、秩共同的方式、层特定的方式或层共同的方式进行训练得到。
其中,CSI中还包括与第一模型匹配使用的第二模型的指示信息,可以用来指示第二模型,网络侧设备可以确定应该与第一模型匹配使用的第二模型,进而可以使用第二模型进行处理。
本公开实施例中,CSI中还可以包括第一模型和匹配使用的第二模型的模型对的指示信息,其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,网络侧设备可以接收终端设备上报的模型对的指示信息,网络侧设备可以确定终端设备使用的第一模型的信息,以及与第一模型匹配使用的第二模型的信息,进而可以使用第二模型进行处理。
需要说明的是,上述实施例并没有穷举,仅为部分实施例的示意,并且上述实施例可以单独被实施,也可以多个进行组合被实施,上述实施例仅作为示意,不作为对本公开实施例保护范围的具体限制。
在一些实施例中,终端设备向网络侧设备上报CSI,可以将CSI的内容作为整体一起上报,或者还可以将CSI的内容进行拆分,分多次分别上报。
在一些实施例中,若终端设备选择将CSI的内容进行拆分,分多次分别上报的情况下,终端设备可以在不同时间,分多次分别上报,以实现向网络侧设备上报CSI。
在一些实施例中,网络侧设备接收终端设备上报的CSI,包括:在不同时刻,接收终端设备上报的第一部分信息和第二部分信息,其中,CSI包括第一部分信息和第二部分信息
本公开实施例中,网络侧设备接收终端设备上报的CSI,可以在不同时刻,接收终端设备上报的第一部分信息和第二部分信息。
其中,CSI包括第一部分信息和第二部分信息。
在一些实施例中,网络侧设备接收终端设备上报的第一部分信息和第二部分信息,包括:接收终端设备使用PUSCH或PUCCH,上报的第一部分信息,以及使用PUSCH或PUCCH上报的第二部分信息。
本公开实施例中,网络侧设备可以接收终端设备使用PUSCH或PUCCH,上报的第一部分信息,以及使用PUSCH或PUCCH,上报的第二部分信息。
在一些实施例中,网络侧设备接收终端设备上报的第一部分信息和第二部分信息,包括:
接收终端设备周期性地上报的第一部分信息和第二部分信息;或
接收终端设备非周期性地上报的第一部分信息和第二部分信息;或
接收终端设备半持续性地上报的第一部分信息和第二部分信息;
其中,第一部分信息与之后相邻的第二部分信息具有关联关系。
本公开实施例中,网络侧设备可以接收终端设备周期性地上报的第一部分信息和第二部分信息,其中,第一部分信息与之后相邻的第二部分信息具有关联关系。
本公开实施例中,网络侧设备可以接收终端设备非周期性地上报的第一部分信息和第二部分信息,其中,第一部分信息与之后相邻的第二部分信息具有关联关系。
本公开实施例中,网络侧设备可以接收终端设备半持续性地上报的第一部分信息和第二部分信息,其中,第一部分信息与之后相邻的第二部分信息具有关联关系。
可以理解的是,终端设备上报的第一部分信息的内容与它之后且最临近的上报的第二部分内容相对应,第一部分信息与之后相邻的第二部分信息具有关联关系。
本公开实施例中,可以通过预定义或上报标识的关联关系,确定上报的第二部分信息与哪一个上报的第一部分信息相对应。其中,第一部分信息对应第一标识,第二部分信息对应第二标识,可以上报第一标识与第二标识具有关联关系,确定第二部分信息对应的第一部分信息。
在一些实施例中,第一部分信息包括以下至少一项:
RI;
CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第二部分信息包括以下至少一项:
每个层对应的第一模型对下行信道信息进行处理后得到的量化信息;
所有层对应的第一模型对下行信道信息进行处理后得到的所有层的量化信息的长度;
所有层对应的第一模型对下行信道信息进行处理后得到的所有层的码字个数;
特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息;
第一模型的指示信息。
本公开实施例中,第一部分信息可以包括以下至少一项:
RI;
CQI;
第一模型的指示信息;与第一模型匹配使用的第二模型的指示信息。
第二部分信息可以包括以下至少一项:
每个层对应的第一模型对下行信道信息进行处理后得到的量化信息;
所有层对应的第一模型对下行信道信息进行处理后得到的所有层的量化信息的长度;
所有层对应的第一模型对下行信道信息进行处理后得到的所有层的码字个数;
特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息;
第一模型的指示信息。
需要说明的是,在第一部分信息中未包括第一模型的指示信息的情况下,第二部分信息中可以包括第一模型的指示信息。
需要说明的是,在网络侧设备仅为终端设备配置一个第一模型的情况下,第一部分信息和第二部分信息中可以不包括第一模型的指示信息。
在一些实施例中,第一模型和第二模型为根据层对应训练得到的;或者第一模型和第二模型为根据秩对应训练得到的。
本公开实施例中,第一模型和第二模型为根据层对应训练得到的,其中,第一模型和第二模型可以采用层特定的方式进行训练得到,或者还可以采用层共同的方式进行训练得到。
本公开实施例中,第一模型和第二模型为根据层对应训练得到的,其中,第一模型和第二模型可以采用秩特定的方式进行训练得到,或者还可以采用秩共同的方式进行训练得到。
本公开实施例中,根据层对应训练得到第一模型和第二模型,可以采用层特定的方式,或者还可以采用层共同的方式训练得到第一模型和第二模型。
其中,采用层特定的方式训练得到第一模型和第二模型,可以针对每一个层训练一个包含第一模型和第二模型的双边模型。
其中,采用层共同的方式训练得到第一模型和第二模型,可以对所有层只训练一个包含第一模型和第二模型的双边模型。
本公开实施例中,若根据层对应训练得到第一模型和第二模型,第一部分信息包括以下至少一项:
RI;
CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
每个层对应的第一模型对下行信道信息进行处理后得到的量化信息的长度;
每个层对应的第一模型对下行信道信息进行处理后得到的码字个数。
第二部分信息包括每个层对应的第一模型对下行信道信息进行处理后得到的量化信息。
本公开实施例中,根据秩对应训练得到第一模型和第二模型,可以采用秩特定的方式,或者还可以采用秩共同的方式训练得到第一模型和第二模型。
其中,采用秩特定的方式训练得到第一模型和第二模型,可以针对每一个秩训练一个包含第一模型和第二模型的双边模型。
其中,采用秩共同的方式训练得到第一模型和第二模型,可以对所有秩只训练一个包含第一模型和第二模型的双边模型。
本公开实施例中,若根据秩对应训练得到第一模型和第二模型,第一部分信息包括以下至少一项:
RI;
CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息的长度;
特定秩对应的第一模型对下行信道信息进行处理后得到的码字个数。
第二部分信息包括特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
在一些实施例中,输入第一模型的数据类型可以包括两种,一种是空频域的预编码矩阵,另一种是角度与时延域的预编码矩阵。
其中,不管输入第一模型的数据类型哪种,第一部分模型和第二部分模型所包括的信息可以与上面一些实施例中所述的第一部分信息和第二部分信息包括的内容相同。
可以理解的是,本公开实施例中,第一部分信息中包括第一模型的指示信息,相应的每个层或每个秩对应的第一模型对下行信道信息进行处理后得到的量化信息的长度也可以直接确定,终端设备可以无需上报每个层或每个秩对应的第一模型对下行信道信息进行处理后得到的量化信息的长度,从而可以减少终端设备的反馈开销。
在一些实施例中,输入第一模型的数据类型包括空频域的预编码矩阵或角度与时延域的预编码矩阵,其中,在输入第一模型的数据类型为角度与时延域的预编码矩阵的情况下,第二部分信息中还包括终端设备选择的空域基向量和频域基向量的指示信息。
本公开实施例中,输入第一模型的数据类型可以包括两种,一种是空频域的预编码矩阵,另一种是角度与时延域的预编码矩阵。
其中,在输入第一模型的数据类型为空频域的预编码矩阵的情况下,第一部分模型和第二部分模型所包括的信息可以与上面一些实施例中所述的第一部分信息和第二部分信息包括的内容相同。
其中,在输入第一模型的数据类型为角度与时延域的预编码矩阵的情况下,第一部分信息所包括的内容可以与上面一些实施例中所述的第一部分信息包括的内容相同,第二部分信息中除包括上面一些实施例中所述的第二部分信息包括的内容以外,还可以包括终端设备选择的空域基向量和频域基向量的指示信息。
可以理解的是,终端设备可以基于网络侧设备的配置确定空域基向量和频域基向量的指示信息,在此情况下,终端设备可以不需要上报空域基向量和频域基向量的指示信息。若终端设备选择的空域基向量和频域基向量的指示信息,终端设备需要上报空域基向量和频域基向量的指示信息。
在一些实施例中,CSI中还包括矢量量化的码字指示信息,其中,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息。
本公开实施例中,在第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后才得到量化信息的情况下,CSI中还可以包括矢量量化的码字指示信息。
在一些实施例中,网络侧设备接收终端设备上报的辅助信息,其中,辅助信息中包括矢量量化的码字指示信息,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息。
本公开实施例中,在第一对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息的情况下,网络侧设备可以接收终端设备上报的辅助信息,辅助信息中包括矢量量化的码字指示信息。
在本实施方式或实施例中,在不矛盾的情况下,各步骤可以独立、任意组合或交换顺序,可选方式或可选例可以任意组合,且可以与其他实施方式或实施例任意组合。
通过实施本公开实施例,网络侧设备接收终端设备上报的CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。由此,可以实现网络侧设备接收终端设备上报的包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息的CSI,以使网络侧设备能够获取准确的CSI。
请参见图9,图9是本公开实施例提供的又一种信道状态信息的上报方法的流程图。如图9所示,该方法由网络侧设备执行,该方法可以包括但不限于如下步骤:
S91:接收终端设备根据确定的最大负载上报的CSI,其中,CSI中包括每个层或特定秩对应的第 一模型对下行信道信息进行处理后得到的量化信息。
本公开实施例中,网络侧设备可以接收终端设备根据确定的最大负载上报的CSI。
其中,网络侧设备接收终端设备上报的CSI的相关描述可以参见上述实施例中的相关描述,此处不再赘述。
其中,终端设备可以基于网络侧设备的配置确定最大负载,或者,终端设备还可以根据其他信息确定最大负载,本公开实施例对此不作具体限制。
在一些实施例中,终端设备根据所采用的第一模型和/或接收到的网络侧设备发送的第一配置信息,确定最大负载,其中,第一配置信息用于指示秩约束条件。
本公开实施例中,终端设备可以根据所采用的第一模型,确定最大负载。
本公开实施例中,终端设备可以根据接收到的网络侧设备发送的第一配置信息,确定最大负载。
其中,第一配置信息用于指示秩约束条件。终端设备可以根据网络侧设备发送的秩约束条件,确定最大负载。
可以理解的是,终端设备根据所采用的第一模型和/或接收到的网络侧设备发送的第一配置信息,确定最大负载,无需网络侧设备为终端设备配置最大负载,可以减少信令开销。
在一些实施例中,网络侧设备向终端设备发送第一配置信息,其中,第一配置信息用于终端设备确定最大负载,第一配置信息用于指示秩约束条件。
本公开实施例中,网络侧设备可以向终端设备发送第一配置信息,其中,第一配置信息用于终端设备确定最大负载,第一配置信息用于指示秩约束条件。由此,终端设备可以根据第一配置信息指示的秩约束条件,确定最大负载。
本公开实施例中,终端设备根据确定的最大负载,向网络侧设备上报CSI,在CSI小于最大负载的情况下,对剩余的部分填零,向网络侧设备上报CSI。
其中,在CSI等于最大负载的情况下,可以直接向网络侧设备上报CSI。
其中,在CSI大于最大负载的情况下,可以全部丢弃CSI,或者还可以丢弃CSI中的部分信息,向网络侧设备上报CSI的剩余部分信息;其中,可以根据CSI丢弃准则或方法丢弃CSI上报中的部分信息。
在本实施方式或实施例中,在不矛盾的情况下,各步骤可以独立、任意组合或交换顺序,可选方式或可选例可以任意组合,且可以与其他实施方式或实施例任意组合。
需要说明的是,本公开实施例中,S91可以单独被实施,也可以结合本公开实施例中的任何一个其他步骤一起被实施,例如结合本公开实施例中的S81一起被实施,本公开实施例并不对此做出限定。
通过实施本公开实施例,网络侧设备接收终端设备根据确定的最大负载上报的CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。由此,可以实现网络侧设备接收终端设备根据确定的最大负载,上报的包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息的CSI,以使网络侧设备能够获取准确的CSI。
请参见图10,图10是本公开实施例提供的另一种模型指示信息发送方法的流程图。如图10所示,该方法由网络侧设备执行,该方法可以包括但不限于如下步骤:
S101:接收终端设备发送的模型指示信息。
其中,模型指示信息用于指示以下至少一项:
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第一模型和匹配使用的第二模型的模型对的指示信息;
其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
本公开实施例中,网络侧设备可以接收终端设备发送的模型指示信息,模型指示信息可以包括第一模型的指示信息。
其中,第一模型的指示信息可以用于指示第一模型,网络侧设备可以确定终端设备使用的第一模型。
本公开实施例中,网络侧设备可以接收终端设备发送的模型指示信息,模型指示信息可以包括与第一模型匹配使用的第二模型的指示信息;其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,与第一模型匹配使用的第二模型可以为网络侧设备的CSI恢复部分模型,第一模型和第二模型可以采用上述示例的秩特定的方式、秩共同的方式、层特定的方式或层共同的方式进行训练得到。
其中,与第一模型匹配使用的第二模型的指示信息,可以用来指示第二模型,网络侧设备可以确定应该与第一模型匹配使用的第二模型,进而可以使用第二模型进行处理。
本公开实施例中,网络侧设备可以接收终端设备发送的模型指示信息,模型指示信息可以包括第一模型和匹配使用的第二模型的模型对的指示信息;其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
其中,第一模型和匹配使用的第二模型的模型对的指示信息,可以用于指示第一模型和第二模型的模型对的信息,网络侧设备可以确定终端设备使用的第一模型的信息,以及与第一模型匹配使用的第二模型,进而使用第二模型进行处理。
需要说明的是,上述实施例并没有穷举,仅为部分实施例的示意,并且上述实施例可以单独被实施,也可以多个进行组合被实施,上述实施例仅作为示意,不作为对本公开实施例保护范围的具体限制。
在一些实施例中,终端设备处可以配置一个或多个候选第一模型,终端设备可以自行选择一个作为第一模型。
在另一些实施例中,终端设备可以接收网络侧设备的配置信息,配置信息用于指示一个或多个候选第一模型。其中,在配置信息指示一个候选第一模型的情况下,终端设备可以确定该候选第一模型为第一模型;在配置信息指示多个候选第一模型的情况下,终端设备可以选择其中一个确定为第一模型。
需要说明的是,若网络侧设备的配置信息仅指示一个候选第一模型的情况下,由于仅有一个候选第一模型,终端设备必然会选择该候选第一模型为第一模型,网络侧设备可以知晓终端设备选择的第一模型,基于此,终端设备可以不用上报第一模型的指示信息。
在本实施方式或实施例中,在不矛盾的情况下,各步骤可以独立、任意组合或交换顺序,可选方式或可选例可以任意组合,且可以与其他实施方式或实施例任意组合。
需要说明的是,本公开实施例中,S101可以单独被实施,也可以结合本公开实施例中的任何一个其他步骤一起被实施,例如结合本公开实施例中的S81和/或S91一起被实施,本公开实施例并不对此做出限定。
通过实施本公开实施例,网络侧设备接收终端设备发送的模型指示信息。由此,可以实现网络侧设备接收终端设备发送的模型指示信息。
请参见图11,图11是本公开实施例提供的另一种辅助信息上报方法的流程图。如图11所示,该方法由终端设备执行,该方法可以包括但不限于如下步骤:
S111:接收终端设备上报的辅助信息,其中,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息,辅助信息中包括矢量量化的码字指示信息。
本公开实施例中,在第一对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息的情况下,网络侧设备可以接收终端设备上报的辅助信息,辅助信息中包括矢量量化的码字指示信息。
本公开实施例中,网络侧设备接收终端设备上报的辅助信息可以单独接收,或者还可以与其他信息同时接收,本公开实施例对此不作具体限制。
本公开实施例中,网络侧设备接收终端设备上报的辅助信息可以复用现有的信令或消息,或者还可以使用新的信令或消息,本公开实施例对此不作具体限制。
在本实施方式或实施例中,在不矛盾的情况下,各步骤可以独立、任意组合或交换顺序,可选方式或可选例可以任意组合,且可以与其他实施方式或实施例任意组合。
需要说明的是,本公开实施例中,S111可以单独被实施,也可以结合本公开实施例中的任何一个其他步骤一起被实施,例如结合本公开实施例中的S81和/或S91和/或S101一起被实施,本公开实施例并不对此做出限定。
通过实施本公开实施例,网络侧设备接收终端设备上报的辅助信息,其中,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息,辅助信息中包括矢量量化的码字指示信息。由此,可以实现网络侧设备接收终端设备上报的矢量量化的码字指示信息。
为方便理解本公开实施例,以第一模型为CSI生成部分模型,第二模型为CSI恢复部分模型为例,进行说明本公开实施例提供的信道状态信息的上报方法。
本公开实施例中,针对双边的AI/ML模型压缩CSI反馈,提出了最大CSI负载大小的确定方法和CSI上报至网络侧设备的内容,用于网络侧设备(gNB)获取准确的CSI反馈信息作为gNB侧的CSI恢复模型的输入信息。
在一些实施例中,终端设备上报的最大CSI负载大小(又称为最大负载,下同)确定方式:
终端设备可以根据终端采用的CSI生成部分AI/ML Model(CSI生成部分模型)和/或网络侧设备配置的秩约束条件确定。
在一些实施例中,CSI生成部分AI/ML Model确定方式:
终端设备采用的CSI生成部分AI/ML Model通过下述的Option1和/或Option2确定。对于Option1和Option2,分别给出了不同的CSI上报方法。
Option1:CSI生成部分AI/ML Model由网络侧设备配置了一个或多个CSI生成部分AI/ML model,终端从中确定一个CSI生成部分AI/ML Model。
Option1-1:CSI上报分为Part 1(第一部分信息)和Part 2(第二部分信息)两部分(输入CSI生成部分AI/ML Model的数据类型为Alt1,即空频域的预编码矩阵)。
Alt1-1:Part 1(第一部分信息)包括:RI、CQI、CSI生成部分AI/ML Model/CSI恢复部分AI/ML Model的指示信息(如果只配置了一个CSI生成部分AI/ML,那么UE(终端设备)不需上报AI/ML Model指示信息)中的一项或多项;Part 2(第二部分信息)包括:每个层(layer)对应的CSI生成部分AI/ML Model输出的量化信息(For layer specific/common model),或者某一秩(rank)对应的CSI生成部分AI/ML Model输出的量化信息(for rank specific/common model)。
可选地,CSI生成部分AI/ML Model的指示信息放在Part 2中上报。
Alt1-2(Layer specific/common model):Part 1包括:RI、CQI、CSI生成部分AI/ML Model/CSI恢复model,每个layer对应的CSI生成部分AI/ML Model输出的量化信息长度或者为CSI生成AI/ML model输出的码字个数(UE把AI/ML model信息指示给NW),UE根据网络侧设备配置的一些候选参数值。Part 2包括:每个layer对应的CSI生成AI/ML model输出的量化信息。
Alt1-3(Rank common/specific):在Part1包含RI、CQI、CSI生成model/CSI恢复model、rank=v的信息长度或根据配置的model已确定信息长度,Part2中包含对rank=v进行压缩后的量化信息。
需要注意的是,对于输入CSI生成部分model的数据类型为Alt2,即角度与时延域的预编码矩阵,Part2可还包括空域基向量和频域基向量的指示信息。
需要注意的是,若矢量量化信息不包含在模型训练中,矢量量化的码字指示信息可通过上述的Part1和Part 2上报,或者它作为辅助的信息与Part1和Part2分开上报。
Option1-2:不拆分CSI,即CSI作为整体一起上报,若上报的CSI小于网络侧设备配置的最大CSI负载,剩余的部分填零。作为整体上报时CSI包括:CQI、每个layer对应的CSI生成AI/ML model输出的量化信息,或者每个rank对于的CSI生成AI/ML Model输出的量化信息。其中RI信息由网络侧设备配置约束确定。
Option1-3:CSI中包含的Part1和Part2的内容分别在不同的上报时刻通过PUCCH和/或PUSCH上报,或者,Part1和Part2分别承载于PUCCH和PUSCH上报。上报的时域行为可以为周期、半持续或非周期。注意,上报的Part2的内容与它之前且最邻近的上报的Part1内容相对应,或者通过预定义或上报ID的关联确定上报的Part2与哪一个上报的Part1相对应。
可选地,RI、CQI和CSI生成部分AI/ML Model输出的量化信息的信息通过两次CSI上报发送到网络侧设备。
Option2:CSI生成AI/ML Model由终端设备选择并上报(考虑多个Model已部署在UE)。
Option2-1:CSI生成部分AI/ML Model指示信息由终端设备独立指示上报。
其中,指示信息可以为是指示AI/ML model的功能ID或Model ID的信息。
Option2-2:CSI生成部分AI/ML Model指示信息与CSI的其它信息联合上报,如把CSI生成AI/ML Model指示信息放在上述的CSI Part 1或Part 2中上报给网络侧设备。
示例性实施例中,假设网络侧设备(gNB)通过信令如RRC、MAC-CE或DCI指示终端设备(UE)采用一个CSI生成部分AI/ML Model和最大传输rank。UE可根据该配置信息确定上行传输的最大负载长度。可选地,gNB通过信令直接指示UE上行传输的最大负载长度和/或最大传输rank。
在一些实施例中,UE根据gNB配置的参数信息和估计的信道信息实现CSI的上报,CSI上报分为Part1(第一部分信息)和Part2(第二部分信息)两部分:
其中,Part 1包括:RI、CQI、CSI生成部分AI/ML Model/CSI恢复部分AI/ML Model的指示信息。其中RI和CQI的指示信息与传统基于码本的CSI上报指示方法相同。通过bits指示UE所选的AI/ML Model,其中X表示在UE侧部署的AI/ML Model个数。
其中,Part 2包括:对于Layer specific/common model,Part2包含了每个layer对应的CSI生成部分AI/ML Model输出的量化信息;对于Rank specific/common model,Part2包含CSI生成部分AI/ML Model输出的量化信息。
由于在Part1中包含了CSI生成部分的AI/ML Model,相应地每层或每个rank对应的压缩后量化信息长度也确定了,不需要UE在反馈指示该信息的长度,从而可以减少UE的反馈开销。
在一些实施例中,CSI中包含的Part1和Part2的内容分别在不同的上报时刻通过PUCCH和/或PUSCH 上报:
Part1包含的RI和CQI信息在T时刻通过PUCCH或PUSCH上报。
Part2包含的CSI生成部分AI/ML Model输出的量化信息在T’时刻通过PUCCH或PUSCH上报,其中T≠T’,CSI生成部分AI/ML Model输出的量化信息可以每个传输层或某个传输秩时对应的量化信息。
示例性实施例中,假设终端设备(UE)侧部署了不同场景、不同配置下对应的X=4个用于基于AI的CSI压缩反馈双边模型。UE根据当前信道情况和网络侧设备配置的子带大小或者CSI-RS端口数确定选择了其中一种双边CSI model。
UE通过一种非周期的CSI上报把该所选模型的指示信息上报给网络侧设备(gNB)。指示信息大小为bits。或者该指示信息与上述实施例1中所述的Part1一块上报给gNB。
因为UE把所选的AI/ML model指示给了gNB,而每种的AI/ML model对应的信道长度是一定的。所以当rank一定的情况,这间接地反应了UE反馈CSI所需的负载大小。如果UE和gNB协商预定义根据model确定CSI反馈负载大小的话,就不需要gNB再单独配置CSI负载的大小了,从而能减少gNB配置信令的开销。
本公开实施例中,根据UE所采用的AI/ML model确定CSI负载大小或CSI上报大小,可以减少配置信令开销或UE反馈开销。
上述本公开提供的实施例中,分别从终端设备、网络侧设备的角度对本公开实施例提供的方法进行了介绍。
请参见图12,为本公开实施例提供的一种通信装置1的结构示意图。图12所示的通信装置1可包括收发模块11和处理模块。收发模块可包括发送模块和/或接收模块,发送模块用于实现发送功能,接收模块用于实现接收功能,收发模块可以实现发送功能和/或接收功能。
通信装置1可以是终端设备,也可以是终端设备中的装置,还可以是能够与终端设备匹配使用的装置。或者,通信装置1可以是网络侧设备,也可以是网络侧设备中的装置,还可以是能够与网络侧设备匹配使用的装置。
通信装置1,被配置在终端设备侧:
该装置,包括:收发模块11。
收发模块11,被配置为向网络侧设备上报信道状态信息CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
在一些实施例中,收发模块11,还被配置为根据确定的最大负载,向网络侧设备上报CSI。
在一些实施例中,该装置,包括:处理模块12。
处理模块12,被配置为根据所采用的第一模型和/或接收到的网络侧设备发送的第一配置信息,确定最大负载,其中,第一配置信息用于指示秩约束条件。
在一些实施例中,收发模块11,还被配置为接收网络侧设备发送的第二配置信息,其中,第二配置信息用于指示多个候选第一模型;处理模块12,还被配置为从候选第一模型中确定一个为所采用的第一模型。
在一些实施例中,CSI中还包括以下至少一项:
秩指示RI;
信道质量指示CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第一模型和匹配使用的第二模型的模型对的指示信息;
其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
在一些实施例中,收发模块11,还被配置为向网络侧设备发送模型指示信息,其中,模型指示信息用于指示以下至少一项:
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第一模型和匹配使用的第二模型的模型对的指示信息;
其中,第二模型用于对量化信息进行处理恢复出与下行信道信息近似的预测下行信道信息。
在一些实施例中,收发模块11,还被配置为在不同时刻,向网络侧设备上报第一部分信息和第二部分信息,其中,CSI包括第一部分信息和第二部分信息。
在一些实施例中,收发模块11,还被配置为使用PUSCH或PUCCH,向网络侧设备上报第一部分 信息,以及使用PUSCH或PUCCH,向网络侧设备上报第二部分信息。
在一些实施例中,收发模块11,还被配置为周期性地向网络侧设备上报第一部分信息和第二部分信息;或
非周期性地向网络侧设备上报第一部分信息和第二部分信息;或
半持续性地向网络侧设备上报第一部分信息和第二部分信息;
其中,第一部分信息与之后相邻的第二部分信息具有关联关系。
在一些实施例中,第一部分信息包括以下至少一项:
RI;
CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第二部分信息包括以下至少一项:
每个层对应的第一模型对下行信道信息进行处理后得到的量化信息;
所有层对应的第一模型对下行信道信息进行处理后得到的所有层的量化信息的长度;
所有层对应的第一模型对下行信道信息进行处理后得到的所有层的码字个数;
特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息;
第一模型的指示信息。
在一些实施例中,第一模型和第二模型为根据层对应训练得到的;或者第一模型和第二模型为根据秩对应训练得到的。
在一些实施例中,输入第一模型的数据类型包括空频域的预编码矩阵、或角度与时延域的预编码矩阵,其中,在输入第一模型的数据类型为角度与时延域的预编码矩阵的情况下,第二部分信息中还包括终端设备选择的空域基向量和频域基向量的指示信息。
在一些实施例中,CSI中还包括矢量量化的码字指示信息,其中,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息。
在一些实施例中,收发模块11,还被配置为向网络侧设备上报辅助信息,其中,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息,辅助信息中包括矢量量化的码字指示信息。
通信装置1,被配置在网络侧设备侧:
该装置,包括:收发模块11。
收发模块11,被配置为接收终端设备上报的CSI,其中,CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
在一些实施例中,收发模块11,还被配置为接收终端设备根据确定的最大负载上报的CSI。
在一些实施例中,收发模块11,还被配置为向终端设备发送第一配置信息,其中,第一配置信息用于终端设备确定最大负载,第一配置信息用于指示秩约束条件。
在一些实施例中,CSI中还包括以下至少一项:
秩指示RI;
信道质量指示CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第一模型和匹配使用的第二模型的模型对的指示信息;
其中,第二模型用于对量化信息进行处理恢复出与所述下行信道信息近似的预测下行信道信息。
在一些实施例中,收发模块11,还被配置为接收终端设备发送的模型指示信息,其中,模型指示信息用于指示以下至少一项:
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第一模型和匹配使用的第二模型的模型对的指示信息;
其中,第二模型用于对量化信息进行处理恢复出与所述下行信道信息近似的预测下行信道信息。
在一些实施例中,收发模块11,还被配置为在不同时刻,接收终端设备上报的第一部分信息和第二部分信息,其中,CSI包括第一部分信息和第二部分信息。
在一些实施例中,收发模块11,还被配置为接收终端设备使用PUSCH或PUCCH,上报的第一部分信息,以及使用PUSCH或PUCCH,上报的第二部分信息。
在一些实施例中,收发模块11,还被配置为接收终端设备周期性地上报的第一部分信息和第二部 分信息;或
接收终端设备非周期性地上报的第一部分信息和第二部分信息;或
接收终端设备半持续性地上报的第一部分信息和第二部分信息;
其中,第一部分信息与之后相邻的第二部分信息具有关联关系。
在一些实施例中,第一部分信息包括以下至少一项:
RI;
CQI;
第一模型的指示信息;
与第一模型匹配使用的第二模型的指示信息;
第二部分信息包括以下至少一项:
每个层对应的第一模型对下行信道信息进行处理后得到的量化信息;
特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息;
第一模型的指示信息。
在一些实施例中,第一模型和第二模型为根据层对应训练得到的;或者第一模型和第二模型为根据秩对应训练得到的。
在一些实施例中,输入第一模型的数据类型包括空频域的预编码矩阵或角度与时延域的预编码矩阵,其中,在输入第一模型的数据类型为角度与时延域的预编码矩阵的情况下,第二部分信息中还包括终端设备选择的空域基向量和频域基向量的指示信息。
在一些实施例中,CSI中还包括矢量量化的码字指示信息,其中,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息。
在一些实施例中,收发模块11,还被配置为接收终端设备上报的辅助信息,其中,辅助信息中包括矢量量化的码字指示信息,第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到量化信息。
关于上述实施例中的通信装置1,其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述,此处将不做详细阐述说明。
本公开上述实施例中提供的通信装置1,与上面一些实施例中提供的信道状态信息的上报方法取得相同或相似的有益效果,此处不再赘述。
请参见图13,图13是本公开实施例提供的另一种通信装置1000的结构示意图。通信装置1000可以是终端设备,也可以是网络侧设备,也可以是支持终端设备实现上述方法的芯片、芯片系统、或处理器等,还可以是支持网络侧设备实现上述方法的芯片、芯片系统、或处理器等。该通信装置1000可用于实现上述方法实施例中描述的方法,具体可以参见上述方法实施例中的说明。
通信装置1000可以包括一个或多个处理器1001。处理器1001可以是通用处理器或者专用处理器等。例如可以是基带处理器或中央处理器。基带处理器可以用于对通信协议以及通信数据进行处理,中央处理器可以用于对通信装置(如,网络侧设备、基带芯片,终端设备、终端设备芯片,DU或CU等)进行控制,执行计算机程序,处理计算机程序的数据。
可选的,通信装置1000中还可以包括一个或多个存储器1002,其上可以存有计算机程序1004,存储器1002执行所述计算机程序1004,以使得通信装置1000执行上述方法实施例中描述的方法。可选的,所述存储器1002中还可以存储有数据。通信装置1000和存储器1002可以单独设置,也可以集成在一起。
可选的,通信装置1000还可以包括收发器1005、天线1006。收发器1005可以称为收发单元、收发机、或收发电路等,用于实现收发功能。收发器1005可以包括接收器和发送器,接收器可以称为接收机或接收电路等,用于实现接收功能;发送器可以称为发送机或发送电路等,用于实现发送功能。
可选的,通信装置1000中还可以包括一个或多个接口电路1007。接口电路1007用于接收代码指令并传输至处理器1001。处理器1001运行所述代码指令以使通信装置1000执行上述方法实施例中描述的方法。
通信装置1000为终端设备:收发器1005用于执行图3中的S31;图4中的S41;图5中的S51;图6中的S61;图7中的S71;处理器1001用于执行图5中的S51。
通信装置1000为网络侧设备:收发器1005用于执行图8中的S81;图9中的S91;图10中的S101;图11中的S111。
在一种实现方式中,处理器1001中可以包括用于实现接收和发送功能的收发器。例如该收发器可以是收发电路,或者是接口,或者是接口电路。用于实现接收和发送功能的收发电路、接口或接口电路可以是分开的,也可以集成在一起。上述收发电路、接口或接口电路可以用于代码/数据的读写,或者, 上述收发电路、接口或接口电路可以用于信号的传输或传递。
在一种实现方式中,处理器1001可以存有计算机程序1003,计算机程序1003在处理器1001上运行,可使得通信装置1000执行上述方法实施例中描述的方法。计算机程序1003可能固化在处理器1001中,该种情况下,处理器1001可能由硬件实现。
在一种实现方式中,通信装置1000可以包括电路,所述电路可以实现前述方法实施例中发送或接收或者通信的功能。本公开中描述的处理器和收发器可实现在集成电路(integrated circuit,IC)、模拟IC、射频集成电路RFIC、混合信号IC、专用集成电路(application specific integrated circuit,ASIC)、印刷电路板(printed circuit board,PCB)、电子设备等上。该处理器和收发器也可以用各种IC工艺技术来制造,例如互补金属氧化物半导体(complementary metal oxide semiconductor,CMOS)、N型金属氧化物半导体(nMetal-oxide-semiconductor,NMOS)、P型金属氧化物半导体(positive channel metal oxide semiconductor,PMOS)、双极结型晶体管(bipolar junction transistor,BJT)、双极CMOS(BiCMOS)、硅锗(SiGe)、砷化镓(GaAs)等。
以上实施例描述中的通信装置可以是终端设备或网络侧设备,但本公开中描述的通信装置的范围并不限于此,而且通信装置的结构可以不受图13的限制。通信装置可以是独立的设备或者可以是较大设备的一部分。例如所述通信装置可以是:
(1)独立的集成电路IC,或芯片,或,芯片系统或子系统;
(2)具有一个或多个IC的集合,可选的,该IC集合也可以包括用于存储数据,计算机程序的存储部件;
(3)ASIC,例如调制解调器(Modem);
(4)可嵌入在其他设备内的模块;
(5)接收机、终端设备、智能终端设备、蜂窝电话、无线设备、手持机、移动单元、车载设备、网络侧设备、云设备、人工智能设备等等;
(6)其他等等。
对于通信装置可以是芯片或芯片系统的情况,请参见图14,为本公开实施例中提供的一种芯片的结构图。
芯片1100包括处理器1101和接口1103。其中,处理器1101的数量可以是一个或多个,接口1103的数量可以是多个。
对于芯片用于实现本公开实施例中终端设备的功能的情况:
接口1103,用于接收代码指令并传输至所述处理器。
处理器1101,用于运行代码指令以执行如上面一些实施例所述的信道状态信息的上报方法。
对于芯片用于实现本公开实施例中网络侧设备的功能的情况:
接口1103,用于接收代码指令并传输至所述处理器。
处理器1101,用于运行代码指令以执行如上面一些实施例所述的信道状态信息的上报方法。
可选的,芯片1100还包括存储器1102,存储器1102用于存储必要的计算机程序和数据。
本领域技术人员还可以了解到本公开实施例列出的各种说明性逻辑块(illustrative logical block)和步骤(step)可以通过电子硬件、电脑软件,或两者的结合进行实现。这样的功能是通过硬件还是软件来实现取决于特定的应用和整个系统的设计要求。本领域技术人员可以对于每种特定的应用,可以使用各种方法实现所述的功能,但这种实现不应被理解为超出本公开实施例保护的范围。
本公开实施例还提供一种信道状态信息的上报系统,该系统包括前述图12实施例中作为终端设备的通信装置和作为网络侧设备的通信装置,或者,该系统包括前述图13实施例中作为终端设备的通信装置和作为网络侧设备的通信装置。
本公开还提供一种可读存储介质,其上存储有指令,该指令被计算机执行时实现上述任一方法实施例的功能。
本公开还提供一种计算机程序产品,该计算机程序产品被计算机执行时实现上述任一方法实施例的功能。
在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机程序。在计算机上加载和执行所述计算机程序时,全部或部分地产生按照本公开实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机程序可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,所述计算机程序可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line,DSL))或无线(例如红外、无线、微波等)方式向另一个网站站 点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如,软盘、硬盘、磁带)、光介质(例如,高密度数字视频光盘(digital video disc,DVD))、或者半导体介质(例如,固态硬盘(solid state disk,SSD))等。
本领域普通技术人员可以理解:本公开中涉及的第一、第二等各种数字编号仅为描述方便进行的区分,并不用来限制本公开实施例的范围,也表示先后顺序。
本公开中的至少一个还可以描述为一个或多个,多个可以是两个、三个、四个或者更多个,本公开不做限制。在本公开实施例中,对于一种技术特征,通过“第一”、“第二”、“第三”、“A”、“B”、“C”和“D”等区分该种技术特征中的技术特征,该“第一”、“第二”、“第三”、“A”、“B”、“C”和“D”描述的技术特征间无先后顺序或者大小顺序。
取决于语境,如在此所使用的词语“如果”及“若”可以被解释成为“在……时”或“当……时”或“响应于确定”。
本公开中各表所示的对应关系可以被配置,也可以是预定义的。各表中的信息的取值仅仅是举例,可以配置为其他值,本公开并不限定。在配置信息与各参数的对应关系时,并不一定要求必须配置各表中示意出的所有对应关系。例如,本公开中的表格中,某些行示出的对应关系也可以不配置。又例如,可以基于上述表格做适当的变形调整,例如,拆分,合并等等。上述各表中标题示出参数的名称也可以采用通信装置可理解的其他名称,其参数的取值或表示方式也可以通信装置可理解的其他取值或表示方式。上述各表在实现时,也可以采用其他的数据结构,例如可以采用数组、队列、容器、栈、线性表、指针、链表、树、图、结构体、类、堆、散列表或哈希表等。
本公开中的预定义可以理解为定义、预先定义、存储、预存储、预协商、预配置、固化、或预烧制。
本领域普通技术人员可以意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本公开的范围。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
以上所述,仅为本公开的具体实施方式,但本公开的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本公开揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本公开的保护范围之内。因此,本公开的保护范围应以所述权利要求的保护范围为准。

Claims (32)

  1. 一种信道状态信息的上报方法,其特征在于,所述方法由终端设备执行,包括:
    向网络侧设备上报信道状态信息CSI,其中,所述CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
  2. 如权利要求1所述的方法,其特征在于,所述向网络侧设备上报CSI,包括:
    根据确定的最大负载,向网络侧设备上报CSI。
  3. 如权利要求2所述的方法,其特征在于,所述方法还包括:
    根据所采用的所述第一模型和/或接收到的所述网络侧设备发送的第一配置信息,确定所述最大负载,其中,所述第一配置信息用于指示秩约束条件。
  4. 如权利要求3所述的方法,其特征在于,所述方法还包括:
    接收所述网络侧设备发送的第二配置信息,其中,所述第二配置信息用于指示多个候选第一模型;
    从所述候选第一模型中确定一个为所采用的所述第一模型。
  5. 如权利要求1至4中任一项所述的方法,其特征在于,所述CSI中还包括以下至少一项:
    秩指示RI;
    信道质量指示CQI;
    所述第一模型的指示信息;
    与所述第一模型匹配使用的第二模型的指示信息;
    所述第一模型和匹配使用的第二模型的模型对的指示信息;
    其中,所述第二模型用于对所述量化信息进行处理恢复出与所述下行信道信息近似的预测下行信道信息。
  6. 如权利要求1至4中任一项所述的方法,其特征在于,所述方法还包括:
    向所述网络侧设备发送模型指示信息,其中,所述模型指示信息用于指示以下至少一项:
    所述第一模型的指示信息;
    与所述第一模型匹配使用的第二模型的指示信息;
    所述第一模型和匹配使用的第二模型的模型对的指示信息;
    其中,所述第二模型用于对所述量化信息进行处理恢复出与所述下行信道信息近似的预测下行信道信息。
  7. 如权利要求1至5中任一项所述的方法,其特征在于,所述向网络侧设备上报CSI,包括:
    在不同时刻,向所述网络侧设备上报第一部分信息和第二部分信息,其中,所述CSI包括所述第一部分信息和所述第二部分信息。
  8. 如权利要求7所述的方法,其特征在于,所述向所述网络侧设备上报第一部分信息和第二部分信息,包括:
    使用PUSCH或PUCCH,向所述网络侧设备上报所述第一部分信息,以及
    使用PUSCH或PUCCH,向所述网络侧设备上报所述第二部分信息。
  9. 如权利要求7或8所述的方法,其特征在于,所述向所述网络侧设备上报第一部分信息和第二部分信息,包括:
    周期性地向所述网络侧设备上报所述第一部分信息和所述第二部分信息;或
    非周期性地向所述网络侧设备上报所述第一部分信息和所述第二部分信息;或
    半持续性地向所述网络侧设备上报所述第一部分信息和所述第二部分信息;
    其中,所述第一部分信息与之后相邻的所述第二部分信息具有关联关系。
  10. 如权利要求7至9中任一项所述的方法,其特征在于,所述第一部分信息包括以下至少一项:
    RI;
    CQI;
    所述第一模型的指示信息;
    与所述第一模型匹配使用的第二模型的指示信息;
    所述第二部分信息包括以下至少一项:
    每个层对应的所述第一模型对下行信道信息进行处理后得到的量化信息;
    所有层对应的所述第一模型对下行信道信息进行处理后得到的所有层的量化信息的长度;
    所有层对应的所述第一模型对下行信道信息进行处理后得到的所有层的码字个数;
    特定秩对应的所述第一模型对下行信道信息进行处理后得到的量化信息;
    所述第一模型的指示信息。
  11. 如权利要求10所述的方法,其特征在于,所述第一模型和所述第二模型为根据层对应训练得到的;或者所述第一模型和所述第二模型为根据秩对应训练得到的。
  12. 如权利要求10或11所述的方法,其特征在于,输入所述第一模型的数据类型包括空频域的预编码矩阵、或角度与时延域的预编码矩阵,其中,在输入所述第一模型的数据类型为角度与时延域的预编码矩阵的情况下,所述第二部分信息中还包括所述终端设备选择的空域基向量和频域基向量的指示信息。
  13. 如权利要求1至12中任一项所述的方法,其特征在于,所述CSI中还包括所述矢量量化的码字指示信息,其中,所述第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到所述量化信息。
  14. 如权利要求1至12中任一项所述的方法,其特征在于,所述方法还包括:
    向所述网络侧设备上报辅助信息,其中,所述第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到所述量化信息,所述辅助信息中包括矢量量化的码字指示信息。
  15. 一种信道状态信息的上报方法,其特征在于,所述方法由网络侧设备执行,包括:
    接收终端设备上报的CSI,其中,所述CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
  16. 如权利要求15所述的方法,其特征在于,所述接收终端设备上报的CSI,包括:
    接收所述终端设备根据确定的最大负载上报的CSI。
  17. 如权利要求16所述的方法,其特征在于,所述方法还包括:
    向所述终端设备发送第一配置信息,其中,所述第一配置信息用于所述终端设备确定所述最大负载,所述第一配置信息用于指示秩约束条件。
  18. 如权利要求15至17中任一项所述的方法,其特征在于,所述CSI中还包括以下至少一项:
    秩指示RI;
    信道质量指示CQI;
    所述第一模型的指示信息;
    与所述第一模型匹配使用的第二模型的指示信息;
    所述第一模型和匹配使用的第二模型的模型对的指示信息;
    其中,所述第二模型用于对所述量化信息进行处理恢复出与所述下行信道信息近似的预测下行信道信息。
  19. 如权利要求15至17中任一项所述的方法,其特征在于,所述方法还包括:
    接收所述终端设备发送的模型指示信息,其中,所述模型指示信息用于指示以下至少一项:
    所述第一模型的指示信息;
    与所述第一模型匹配使用的第二模型的指示信息;
    所述第一模型和匹配使用的第二模型的模型对的指示信息;
    其中,所述第二模型用于对所述量化信息进行处理恢复出与所述下行信道信息近似的预测下行信道信息。
  20. 如权利要求15至18中任一项所述的方法,其特征在于,所述接收终端设备上报的CSI,包括:
    在不同时刻,接收所述终端设备上报的第一部分信息和第二部分信息,其中,所述CSI包括所述第一部分信息和所述第二部分信息。
  21. 如权利要求20所述的方法,其特征在于,所述接收所述终端设备上报的第一部分信息和第二部分信息,包括:
    接收所述终端设备使用PUSCH或PUCCH,上报的所述第一部分信息,以及
    使用PUSCH或PUCCH,上报的所述第二部分信息。
  22. 如权利要求20或21所述的方法,其特征在于,所述接收所述终端设备上报的第一部分信息和第二部分信息,包括:
    接收所述终端设备周期性地上报的所述第一部分信息和所述第二部分信息;或
    接收所述终端设备非周期性地上报的所述第一部分信息和所述第二部分信息;或
    接收所述终端设备半持续性地上报的所述第一部分信息和所述第二部分信息;
    其中,所述第一部分信息与之后相邻的所述第二部分信息具有关联关系。
  23. 如权利要求20至22中任一项所述的方法,其特征在于,所述第一部分信息包括以下至少一项:
    RI;
    CQI;
    所述第一模型的指示信息;
    与所述第一模型匹配使用的第二模型的指示信息;
    所述第二部分信息包括以下至少一项:
    每个层对应的所述第一模型对下行信道信息进行处理后得到的量化信息;
    特定秩对应的所述第一模型对下行信道信息进行处理后得到的量化信息;
    所述第一模型的指示信息。
  24. 如权利要求23所述的方法,其特征在于,所述第一模型和所述第二模型为根据层对应训练得到的;或者所述第一模型和所述第二模型为根据秩对应训练得到的。
  25. 如权利要求23或24所述的方法,其特征在于,输入所述第一模型的数据类型包括空频域的预编码矩阵或角度与时延域的预编码矩阵,其中,在输入所述第一模型的数据类型为角度与时延域的预编码矩阵的情况下,所述第二部分信息中还包括所述终端设备选择的空域基向量和频域基向量的指示信息。
  26. 如权利要求15至25中任一项所述的方法,其特征在于,所述CSI中还包括所述矢量量化的码字指示信息,其中,所述第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到所述量化信息。
  27. 如权利要求15至25中任一项所述的方法,其特征在于,所述方法还包括:
    接收所述终端设备上报的辅助信息,其中,所述辅助信息中包括矢量量化的码字指示信息,所述第一模型对下行信道信息进行处理后,进一步经过矢量量化处理后得到所述量化信息。
  28. 一种通信装置,其特征在于,所述装置包括:
    收发模块,被配置为向网络侧设备上报信道状态信息CSI,其中,所述CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
  29. 一种通信装置,其特征在于,所述装置包括:
    收发模块,被配置为接收终端设备上报的CSI,其中,所述CSI中包括每个层或特定秩对应的第一模型对下行信道信息进行处理后得到的量化信息。
  30. 一种通信装置,其特征在于,所述装置包括处理器和存储器,所述存储器中存储有计算机程序,所述处理器执行所述存储器中存储的计算机程序,以使所述装置执行如权利要求1至14中任一项所述的方法,或所述处理器执行所述存储器中存储的计算机程序,以使所述装置执行如权利要求15至27中任一项所述的方法。
  31. 一种通信装置,其特征在于,包括:处理器和接口电路;
    所述接口电路,用于接收代码指令并传输至所述处理器;
    所述处理器,用于运行所述代码指令以执行如权利要求1至14中任一项所述的方法,或用于运行所述代码指令以执行如权利要求15至27中任一项所述的方法。
  32. 一种计算机可读存储介质,用于存储有指令,当所述指令被执行时,使如权利要求1至14中任一项所述的方法被实现,或当所述指令被执行时,使如权利要求15至27中任一项所述的方法被实现。
PCT/CN2023/086721 2023-04-06 2023-04-06 信道状态信息的上报方法和装置 Pending WO2024207367A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202380008963.3A CN119096583A (zh) 2023-04-06 2023-04-06 信道状态信息的上报方法及装置
PCT/CN2023/086721 WO2024207367A1 (zh) 2023-04-06 2023-04-06 信道状态信息的上报方法和装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2023/086721 WO2024207367A1 (zh) 2023-04-06 2023-04-06 信道状态信息的上报方法和装置

Publications (1)

Publication Number Publication Date
WO2024207367A1 true WO2024207367A1 (zh) 2024-10-10

Family

ID=92970783

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/086721 Pending WO2024207367A1 (zh) 2023-04-06 2023-04-06 信道状态信息的上报方法和装置

Country Status (2)

Country Link
CN (1) CN119096583A (zh)
WO (1) WO2024207367A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022040046A1 (en) * 2020-08-18 2022-02-24 Qualcomm Incorporated Reporting configurations for neural network-based processing at a ue
CN114531355A (zh) * 2020-11-23 2022-05-24 维沃移动通信有限公司 通信方法、装置及通信设备
CN115280833A (zh) * 2022-06-16 2022-11-01 北京小米移动软件有限公司 信道状态信息的处理方法、装置及通信设备
CN115603838A (zh) * 2021-07-09 2023-01-13 维沃移动通信有限公司(Cn) 信道状态信息csi上报处理方法、接收方法及相关设备
CN116939649A (zh) * 2022-04-01 2023-10-24 维沃移动通信有限公司 信道特征信息传输方法、装置、终端及网络侧设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022040046A1 (en) * 2020-08-18 2022-02-24 Qualcomm Incorporated Reporting configurations for neural network-based processing at a ue
CN114531355A (zh) * 2020-11-23 2022-05-24 维沃移动通信有限公司 通信方法、装置及通信设备
CN115603838A (zh) * 2021-07-09 2023-01-13 维沃移动通信有限公司(Cn) 信道状态信息csi上报处理方法、接收方法及相关设备
CN116939649A (zh) * 2022-04-01 2023-10-24 维沃移动通信有限公司 信道特征信息传输方法、装置、终端及网络侧设备
CN115280833A (zh) * 2022-06-16 2022-11-01 北京小米移动软件有限公司 信道状态信息的处理方法、装置及通信设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
DEUTSCHE TELEKOM: "Use cases for AI/ML in RAN and potential benefits", 3GPP DRAFT; R3-206198, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. RAN WG3, no. E-meeting; 20201102 - 20201112, 22 October 2020 (2020-10-22), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , XP051941655 *

Also Published As

Publication number Publication date
CN119096583A (zh) 2024-12-06

Similar Documents

Publication Publication Date Title
US20240022303A1 (en) Channel state information reporting method and related apparatus
WO2025000209A1 (zh) 模型性能的监测方法和装置
WO2024207381A1 (zh) 信道状态信息参考信号csi-rs资源的配置方法及其装置
WO2023184372A1 (zh) 上行信道的发送和接收的方法及装置
EP4412127A1 (en) Resource configuration method, apparatus and storage medium
WO2023283782A1 (zh) 一种信道状态反馈的方法及其装置
WO2023184450A1 (zh) 一种基于非码本的pusch接收/发送信息的方法及其装置
CN116195326A (zh) 一种探测参考信号srs的发送方法及其装置
WO2023070586A1 (zh) 物理下行共享信道pdsch配置方法及装置
WO2024207367A1 (zh) 信道状态信息的上报方法和装置
WO2023245683A1 (zh) 基向量类型的指示方法和装置
CN118120163A (zh) 一种信道质量指示cqi上报方法、装置、设备及存储介质
WO2024168762A1 (zh) 一种指示方法、确定方法及其装置
WO2023184451A1 (zh) 一种基于非码本的pusch发送、接收信息的方法及其装置
WO2023168575A1 (zh) 一种天线切换能力上报方法及其装置
EP4557815A1 (en) Basis vector selecting, indicating and reporting method and apparatus
EP4503796A1 (en) Information sending/receiving method and apparatus based on non-codebook-based pusch
WO2024207365A1 (zh) 一种信道状态信息csi的上报方法及其装置
EP4604434A1 (en) Physical downlink shared channel (pdsch) transmission method and apparatus
EP4465699A1 (en) Measurement report reporting method and device
WO2023184449A1 (zh) 一种发送tri的方法及其装置、接收tri的方法及其装置
WO2024168915A1 (zh) 幅度约束方法和装置
WO2024077619A1 (zh) 一种信息确定方法/装置/设备及存储介质
WO2024092833A1 (zh) 一种确定信道状态信息csi的方法及其装置
WO2024207530A1 (zh) 信道状态信息csi处理方法及装置

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 202380008963.3

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23931435

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE