CSI reporting method, apparatus and system

Abstract

A CSI reporting method, apparatus and system, relating to the field of communications, for use in implementing CSI reporting. The method comprises: a network apparatus sends, to a terminal apparatus, first information for indicating a use of CSI; and the terminal apparatus acquires the first information, acquires, on the basis of the indication of the first information, the CSI meeting the use of the CSI indicated by the first information, and sends the CSI to the network apparatus, wherein the use of the CSI at least includes whether the CSI is used for an AI use case. The solution of the present application can be widely applied to the technical field of communications and the fields of artificial intelligence, vehicle-to-everything, smart home networking, and the like.

Description

A CSI reporting method, device and system

[0001] The present application claims priority to the Chinese patent application No. 202410903685.4, filed on July 5, 2024, and entitled "A CSI reporting method, device and system", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, in particular to a CSI reporting method, device and system. BACKGROUND

[0003] In a communication system, in the application of beam management (BM) and / or channel state information (CSI), a terminal can measure and report CSI to a network device, so that the network device optimizes downlink transmission and / or resource allocation based on the reported CSI.

[0004] How to report CSI becomes a problem to be solved SUMMARY

[0005] The present application provides a CSI reporting method, device and system to achieve CSI reporting.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a CSI reporting method, which can be executed by a terminal device, and the terminal device can be a terminal device or a functional module or a chip in the terminal device. Taking the execution of the terminal device as an example, the method comprises: the terminal device acquires first information for indicating the purpose of CSI, acquires CSI meeting the purpose of CSI indicated by the first information according to the indication of the first information, and reports the CSI meeting the purpose of CSI indicated by the first information to a network device. Wherein, the purpose of CSI at least includes whether the CSI is used for AI use case.

[0008] Based on the method of the first aspect, the terminal device can accurately determine whether the reported CSI is used for AI use case according to the indication of the first information, and report the CSI meeting the purpose of CSI indicated by the first information to the network device, which realizes the reporting of CSI under AI use case or non-AI use case to the network device. At the same time, the terminal device avoids acquiring multiple signaling to acquire the required CSI of the network device, and introduces signaling overhead.

[0009] In a possible design, the use of the CSI includes at least one of a use case to which the CSI is applicable, an AI use case type to which the CSI is applicable, an AI use case stage to which the CSI is applicable, or content required to be reported under the use case to which the CSI is applicable; the use case to which the CSI is applicable includes an AI use case and / or a non-AI use case; the AI use case type to which the CSI is applicable includes an AI-BM use case and / or an AI-CSI compression use case; the AI use case stage to which the CSI is applicable includes a data collection stage and / or an inference stage; and the content required to be reported under the use case to which the CSI is applicable includes whether L1-RSRP or L1-SINR measurement results under the AI use case are all reported or not, or at least one of the CSI required to be reported under the AI use case.

[0010] Based on the possible design, various information that the use of the CSI can include is given, so that the technical solution of the present application can be flexibly applied to various communication scenarios.

[0011] In a possible design, the first information includes a first field, and the first field is used to indicate whether the CSI is used for an AI use case. Based on the possible design, whether the CSI is used for an AI use case can be indicated through the first field in the first information, so that the terminal device can obtain, from the first field in the first information, whether the CSI is used for an AI use case.

[0012] In a possible design, in a case where the first field indicates that the CSI is not used for an AI use case, the first information does not include a second field; and the second field is used to indicate codebook information used by the AI use case.

[0013] Based on the possible design, in a case where the first field indicates that the CSI is not used for an AI use case, the codebook information used by the AI use case is not included in the first information, so as to ensure that the terminal device can report the CSI according to codebook information corresponding to a non-AI use case.

[0014] In a possible design, in a case where the first field indicates that the CSI is used for an AI use case, the first information further includes a second field and / or a third field; the second field is used to indicate codebook information used by the AI use case; and the third field is used to indicate whether L1-RSRP or L1-SINR measurement results under the AI use case are all reported or not.

[0015] Based on the possible design, the codebook information used by the AI use case and / or whether L1-RSRP or L1-SINR measurement results under the AI use case are all reported or not can be flexibly indicated in different AI use case scenarios through configuration of the first field, the second field, and the third field in the first information, without the need for the terminal device to receive multiple signals to respectively indicate the codebook information used by the AI use case and whether L1-RSRP or L1-SINR measurement results under the AI use case are all reported or not in different AI use case scenarios, thereby saving signaling overhead.

[0016] In a possible design, in the case that the first field indicates that the CSI is for an AI use case and the first information includes the second field, the CSI satisfying the use case at least includes the PMI.

[0017] Based on the possible design, the terminal device receives the first field indicating that the CSI is for an AI use case and the second field, and obtains the PMI by using the codebook information indicated by the second field for the AI use case.

[0018] In a possible design, in the case that the first field indicates that the CSI is for an AI use case, the first information does not include the second field, and the third field indicates that all L1-RSRP or L1-SINR measurement results under the AI use case are reported, the CSI satisfying the use case at least includes all L1-RSRP or L1-SINR measurement results under the AI use case.

[0019] Based on the possible design, the terminal device receives the first field indicating that the CSI is for an AI use case and the third field indicating that all L1-RSRP or L1-SINR measurement results under the AI use case are reported, and obtains all L1-RSRP or L1-SINR measurement results under the AI use case, to support reporting all L1-RSRP or L1-SINR measurement results under the AI use case at one time, thereby avoiding that the terminal device does not support reporting all L1-RSRP or L1-SINR measurement results under the AI use case at one time, and introducing multiple reporting signaling consumption.

[0020] In a possible design, in the case that the first field indicates that the CSI is for an AI use case, the first information does not include the second field, and the third field indicates that part of L1-RSRP or L1-SINR measurement results under the AI use case are reported, the first information further includes a fourth field, and the fourth field is used to indicate CSI required to be reported under the AI use case, and the fourth field includes one of cri-RI-PMI-CQI and cri-RSRP.

[0021] Based on the possible design, in the case that the first information includes the first field and the third field used to indicate that part of L1-RSRP or L1-SINR measurement results under the AI use case are reported, the fourth field used to indicate CSI required to be reported under the AI use case is configured, to flexibly indicate the CSI required to be reported, and the terminal device does not need to receive multiple signals to indicate the CSI required to be reported under different AI use case scenarios, thereby saving signaling overhead.

[0022] In a possible design, the fourth field includes cri-RI-PMI-CQI, the CSI satisfying the use case includes the cri, the RI, and the PMI; the fourth field includes cri-RSRP, and the output of the AI model under the AI use case does not include a predicted value of the L1-RSRP, the CSI satisfying the use case includes the cri; the fourth field includes cri-RSRP, and the output of the AI model under the AI use case includes the predicted value of the L1-RSRP, the CSI satisfying the use case includes the cri and the RSRP.

[0023] Based on the possible design, the terminal device can obtain different CSI according to different information included in the fourth field when receiving the fourth field. Meanwhile, different CSI can be obtained according to the output of the AI model under different AI use cases when the information included in the fourth field is the same. In this way, the overhead of the terminal device receiving multiple signals to obtain different CSI is saved.

[0024] In a possible design, the first field is carried in a lower-level information element of the CSI-ReportConfig; or the first field is carried in a higher-level information element of the CSI-ReportConfig; or the first field is carried in the CSI-ReportConfig information element.

[0025] Based on the possible design, the information element carrying the first field can be configured to indicate whether the CSI is used for the AI use case in different granularities, and the flexibility of the first information indicating whether the CSI is used for the AI use case is improved.

[0026] In a possible design, the first field is an ai-Enable field, the second field is a CodebookConfig-AI field, the third field is an nroReportedRS field, and the fourth field is a reportQuantity field.

[0027] Based on the possible design, specific field names of the first field, the second field, the third field, and the fourth field are given, so that the present solution can be applied to a standard communication protocol.

[0028] In a possible design, the first information includes a fifth field, and the fifth field is used to indicate the CSI satisfying the use case when the CSI is used for the AI use case. Based on the possible design, the terminal device can directly report the CSI satisfying the use case indicated by the first information under the AI use case through the indication of the fifth field without combining other information elements or fields, and the complexity of the terminal device obtaining the CSI satisfying the use case indicated by the first information is reduced.

[0029] In a possible design, the fifth field includes one of cri-RI-PMI, cri-RI-PMI-CQI, cri-RSRP-DataCollection, cri-RSRP-Inference, rsrp, and cri.

[0030] Based on the possible design, various information included in the fifth field is given, so that the terminal device reports different CSI under different AI use cases, and the applicability of the scheme is improved.

[0031] In a possible design, the fifth field includes cri-RI-PMI, and the CSI required for use includes cri, RI, and PMI.

[0032] Based on the possible design, the terminal device acquires cri, RI, and PMI when the fifth field includes cri-RI-PMI, and further reports cri, RI, and PMI to the network device, so that the network device accurately acquires the required CSI.

[0033] In a possible design, the fifth field includes cri-RI-PMI-CQI, and the first information further includes a second field, and the CSI required for use includes cri, RI, PMI, and CQI. The second field indicates codebook information used by the AI use case.

[0034] Based on the possible design, the terminal device acquires cri, RI, PMI, and CQI when the fifth field includes cri-RI-PMI-CQI, and further reports cri, RI, PMI, and CQI to the network device, so that the network device accurately acquires the required CSI. At the same time, through the indication of the second field, the terminal device acquires the PMI by using the codebook information used by the AI use case.

[0035] In a possible design, the fifth field includes cri-RSRP-DataCollection, and the CSI required for use includes all L1-RSRP measurement results under the AI use case and cri.

[0036] Based on the possible design, the terminal device acquires all L1-RSRP measurement results under the AI use case and cri when the fifth field includes cri-RSRP-DataCollection, and further reports all L1-RSRP measurement results under the AI use case and cri to the network device, so that the network device accurately acquires the required CSI.

[0037] In a possible design, the fifth field includes rsrp, and the CSI meeting the use case includes all L1-RSRP measurement results under the AI use case. Based on this possible design, the terminal device acquires all L1-RSRP measurement results under the AI use case in the case where the fifth field includes rsrp, and further reports all L1-RSRP measurement results under the AI use case to the network device, so that the network device accurately acquires the required CSI.

[0038] In a possible design, the fifth field includes cri-RSRP-Inference, the first information further includes a third field, and the third field indicates partial reporting of L1-RSRP or L1-SINR measurement results under the AI use case, and the CSI meeting the use case includes cri and RSRP.

[0039] Based on this possible design, the terminal device acquires partial L1-RSRP measurement results and cri under the AI use case in the case where the fifth field includes cri-RSRP-Inference, and further reports the partial L1-RSRP measurement results and the cri under the AI use case to the network device, so that the network device accurately acquires the required CSI.

[0040] In a possible design, the fifth field includes cri, and the CSI meeting the use case includes the cri. Based on this possible design, the terminal device acquires the cri in the case where the fifth field includes cri, and further reports the cri to the network device, so that the network device accurately acquires the required CSI.

[0041] In a possible design, the fifth field is a reportQuantity-AI field. Based on this possible design, a specific field name of the fifth field is given, so that the present solution can be applied to a standard communication protocol.

[0042] In a second aspect, an embodiment of the present application provides a CSI reporting method, which can be executed by a network device, and the network device can be a network equipment or a functional module or a chip in the network equipment. Taking the network device as an example, the method includes: the network device sends first information used for indicating a use of CSI, and in response to the first information, receives CSI meeting the use of the CSI indicated by the first information from a terminal device. The use of the CSI at least includes whether the CSI is used for an AI use case.

[0043] In the method of the second aspect, the network device can accurately indicate the terminal device to report the CSI under the AI use case or the non-AI use case by sending the first information to the terminal device, so as to accurately obtain the CSI required by the network device under the AI use case or the non-AI use case. Meanwhile, the network device is avoided from configuring multiple signaling to obtain the CSI required by the network device, and signaling overhead is introduced.

[0044] In a possible design, the use of the CSI includes at least one of a use case to which the CSI is applicable, an artificial intelligence (AI) use case type to which the CSI is applicable, an AI use case stage to which the CSI is applicable, and content required to be reported under the use case to which the CSI is applicable; the use case to which the CSI is applicable includes an AI use case and / or a non-AI use case; the AI use case type to which the CSI is applicable includes an AI-BM use case and / or an AI-CSI compression use case; the AI use case stage to which the CSI is applicable includes a data collection stage and / or an inference stage; and the content required to be reported under the use case to which the CSI is applicable includes whether L1-RSRP or L1-SINR measurement results under the AI use case are all reported, and at least one of the CSI required to be reported under the AI use case.

[0045] Based on the possible design, the use of the CSI can include various information, so that the technical solution of the present application can be flexibly applied to various communication scenarios.

[0046] In a possible design, the first information includes a first field, and the first field is used to indicate whether the CSI is used for the AI use case.

[0047] Based on the possible design, whether the CSI is used for the AI use case can be indicated by the first field in the first information, so that the network device can send the first field in the first information to indicate whether the CSI is used for the AI use case.

[0048] In a possible design, in a case where the first field indicates that the CSI is not used for the AI use case, the first information does not include a second field; and the second field is used to indicate codebook information used by the AI use case.

[0049] Based on the possible design, in a case where the first field indicates that the CSI is not used for the AI use case, the network device does not send the codebook information used by the AI use case in the first information, so as to ensure that the terminal device can report the CSI according to the codebook information corresponding to the non-AI use case.

[0050] In a possible design, in a case where the first field indicates that the CSI is used for the AI use case, the first information further includes a second field and / or a third field; the second field is used to indicate the codebook information used by the AI use case; and the third field is used to indicate whether L1-RSRP or L1-SINR measurement results under the AI use case are all reported.

[0051] Based on the possible design, the network device can flexibly indicate, by sending the first field, the second field, and the third field in the first information, codebook information used by the AI use case and whether the L1-RSRP or L1-SINR measurement result under the AI use case is all reported in different AI use case scenarios, without the network device sending multiple signals to respectively indicate the codebook information used by the AI use case and whether the L1-RSRP or L1-SINR measurement result under the AI use case is all reported for different AI use case scenarios, thereby saving signaling overhead.

[0052] In a possible design, in a case where the first field indicates that the CSI is used for the AI use case and the first information includes the second field, the CSI that meets the use purpose at least includes the PMI.

[0053] Based on the possible design, the network device, in a case where the first field and the second field indicating that the CSI is used for the AI use case are sent, can obtain the PMI obtained by the terminal device using the codebook information indicated by the second field.

[0054] In a possible design, in a case where the first field indicates that the CSI is used for the AI use case, the first information does not include the second field, and the third field indicates that all L1-RSRP or L1-SINR measurement results under the AI use case are reported, the CSI that meets the use purpose at least includes all L1-RSRP or L1-SINR measurement results of the AI use case.

[0055] Based on the possible design, the network device, in a case where the first field indicating that the CSI is used for the AI use case and the third field indicating that all L1-RSRP or L1-SINR measurement results under the AI use case are reported are sent, can support receiving all L1-RSRP or L1-SINR measurement results under the AI use case at one time, thereby avoiding multiple reporting signaling consumption introduced by not supporting receiving all L1-RSRP or L1-SINR measurement results under the AI use case at one time.

[0056] In a possible design, in a case where the first field indicates that the CSI is used for the AI use case, the first information does not include the second field, and the third field indicates that part of the L1-RSRP or L1-SINR measurement result under the AI use case is reported, the first information further includes a fourth field, and the fourth field is used to indicate CSI required by the AI use case to report, and the fourth field includes one of cri-RI-PMI-CQI and cri-RSRP.

[0057] Based on the possible design, in a case that the network device sends the first information including the first field and the third field for indicating the L1-RSRP or L1-SINR measurement result part reporting under the AI use case, the network device can also indicate the CSI required to be reported by the terminal device by configuring the first information to include the fourth field for indicating the CSI required to be reported by the AI use case, so as to flexibly indicate the CSI required to be reported by the terminal device, without the network device needing to send multiple signals to indicate the CSI required to be reported by the AI use case in different AI use case scenarios, thereby saving signaling overhead.

[0058] In a possible design, the fourth field includes cri-RI-PMI-CQI, the CSI required to meet the use case includes cri, RI, and PMI; the fourth field includes cri-RSRP, and the output of the AI model under the AI use case does not include the predicted value of L1-RSRP, the CSI required to meet the use case includes cri; the fourth field includes cri-RSRP, and the output of the AI model under the AI use case includes the predicted value of L1-RSRP, the CSI required to meet the use case includes cri and RSRP.

[0059] Based on the possible design, the network device can obtain different CSI according to different information included in the fourth field in a case that the network device sends the fourth field. Meanwhile, different CSI can be obtained for the output of the AI model under different AI use cases in a case that the information included in the fourth field is the same. In this way, the network device is saved from sending multiple signals to obtain different CSI, thereby saving overhead.

[0060] In a possible design, the first field is carried in a lower-level information element of the CSI-ReportConfig; or the first field is carried in a higher-level information element of the CSI-ReportConfig; or the first field is carried in the CSI-ReportConfig information element.

[0061] Based on the possible design, the information element carrying the first field can be configured to indicate whether the CSI is used for the AI use case in different granularities, thereby improving the flexibility of the first information indicating whether the CSI is used for the AI use case.

[0062] In a possible design, the first field is an ai-Enable field, the second field is a CodebookConfig-AI field, the third field is an nroReportedRS field, and the fourth field is a reportQuantity field.

[0063] Based on the possible design, specific field names of the first field, the second field, the third field, and the fourth field are given, so that the present solution can be applied to a standard communication protocol.

[0064] In a possible design, the first information includes a fifth field, and the fifth field is used to indicate the CSI that meets the CSI usage when the CSI is used for the AI use case. Based on this possible design, the network device can directly report the CSI that meets the CSI usage indicated by the first information through the indication of the fifth field, without sending other information elements or fields, thereby reducing the complexity of the network device in sending the CSI that meets the CSI usage indicated by the first information.

[0065] In a possible design, the fifth field includes one of cri-RI-PMI, cri-RI-PMI-CQI, cri-RSRP-DataCollection, cri-RSRP-Inference, rsrp, and cri. Based on this possible design, the fifth field includes various information, so that the network device can send the fifth field including different information in different AI use cases, thereby improving the applicability of the scheme.

[0066] In a possible design, the fifth field includes cri-RI-PMI, and the CSI that meets the usage includes cri, RI, and PMI. Based on this possible design, when the network device sends the fifth field including cri-RI-PMI, the network device can obtain the cri, RI, and PMI sent by the terminal device, so as to accurately obtain the required CSI.

[0067] In a possible design, when the fifth field includes cri-RI-PMI-CQI, the first information further includes a second field, and the CSI that meets the usage includes cri, RI, PMI, and CQI. The second field indicates codebook information used by the AI use case.

[0068] Based on this possible design, when the network device sends the fifth field including cri-RI-PMI-CQI, the network device can obtain the cri, RI, PMI, and CQI sent by the terminal device, so as to accurately obtain the required CSI. Meanwhile, through the indication of the second field, the network device can obtain the PMI obtained by the terminal device through the codebook information used by the AI use case.

[0069] In a possible design, the fifth field includes cri-RSRP-DataCollection, and the CSI that meets the usage includes all L1-RSRP measurement results in the AI use case and cri.

[0070] Based on this possible design, when the network device sends the fifth field including cri-RSRP-DataCollection, the network device can obtain all L1-RSRP measurement results in the AI use case and the cri sent by the terminal device, so as to accurately obtain the required CSI.

[0071] In a possible design, the fifth field includes rsrp, and the CSI meeting the use case includes all L1-RSRP measurement results in the AI use case. Based on this possible design, the network device acquires all L1-RSRP measurement results in the AI use case sent by the terminal device in the case where the fifth field includes rsrp, so as to enable the network device to accurately acquire the required CSI.

[0072] In a possible design, the fifth field includes cri-RSRP-Inference, the first information further includes a third field, and the third field indicates partial reporting of L1-RSRP or L1-SINR measurement results in the AI use case, and the CSI meeting the use case includes cri and RSRP.

[0073] Based on this possible design, the network device acquires partial L1-RSRP measurement results in the AI use case and cri sent by the terminal device in the case where the fifth field includes cri-RSRP-Inference, so as to enable the network device to accurately acquire the required CSI.

[0074] In a possible design, the fifth field includes cri, and the CSI meeting the use case includes the cri. Based on this possible design, the network device acquires the cri sent by the terminal device in the case where the fifth field includes cri, so as to enable the network device to accurately acquire the required CSI.

[0075] In a possible design, the fifth field is a reportQuantity-AI field. Based on this possible design, a specific field name of the fifth field is given, so that the present solution can be applied to a standard communication protocol.

[0076] In a third aspect, the present application provides a communication device, which can be a terminal device or a chip or system on chip in the terminal device, and can also be a functional module in the terminal device for implementing the method in the first aspect or any possible design of the first aspect. The communication device can implement the functions performed by the first device in the first aspect or any possible design of the first aspect, and the functions can be implemented by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the functions. For example, the communication device can include a transceiver and a processing unit. Wherein,

[0077] The transceiver is configured to acquire first information, the first information being used to indicate a use of CSI, and the use of CSI at least including whether the CSI is used for an AI use case.

[0078] The processing unit is configured to acquire, according to the indication of the first information, CSI meeting the use of CSI indicated by the first information.

[0079] The transceiver unit is further configured to report the CSI that meets the use of the CSI indicated by the first information.

[0080] Specifically, the execution actions of each unit of the communication apparatus can refer to those described in the first aspect or any possible design of the first aspect, and will not be described here.

[0081] In a fourth aspect, the present application provides a communication apparatus, which can be a network device or a chip or system on chip in a network device, and can also be a functional module in a network device for implementing the method in the second aspect or any possible design of the second aspect. The communication apparatus can implement the functions performed by the network apparatus in the second aspect or any possible design of the second aspect, and the functions can be implemented by hardware or software. The hardware or software includes one or more modules corresponding to the functions. For example, the communication apparatus can include a transceiver unit. Wherein,

[0082] The transceiver unit is configured to send first information, and the first information is used to indicate the use of CSI, and the use of CSI at least includes whether the CSI is used for an AI use case.

[0083] The transceiver unit is further configured to receive, in response to the first information, the CSI that meets the use of the CSI indicated by the first information.

[0084] Specifically, the execution actions of each unit of the communication apparatus can refer to those described in the second aspect or any possible design of the second aspect, and will not be described here.

[0085] In a fifth aspect, the present application provides a communication apparatus, which can be the terminal apparatus or the network apparatus. In one possible design, the communication apparatus includes a processor. Wherein, the processor is configured to support the communication apparatus to perform the CSI reporting method in the first aspect or any possible design of the first aspect, or the processor is configured to support the communication apparatus to perform the CSI reporting method in the second aspect or any possible design of the second aspect. In another possible design, the communication apparatus can further include a memory, and the memory is configured to store instructions and / or data. When the communication apparatus is running, the processor executes the computer-executable instructions stored in the memory, so that the communication apparatus performs the CSI reporting method described in the first aspect or any possible design of the first aspect, or performs the CSI reporting method described in the second aspect or any possible design of the second aspect.

[0086] In a sixth aspect, the present application provides a communication system, which includes the communication apparatus provided in the third aspect and the communication apparatus provided in the fourth aspect.

[0087] In a seventh aspect, the present application provides a computer readable storage medium storing computer instructions, when the computer instructions are executed on a computer, causing the computer to perform the CSI reporting method in the first aspect or any possible design of the first aspect; or causing the computer to perform the CSI reporting method in the second aspect or any possible design of the second aspect.

[0088] In an eighth aspect, the present application provides a computer program product comprising computer instructions, when the computer instructions are executed on a computer, causing the computer to perform the CSI reporting method in the first aspect or any possible design of the first aspect; or causing the computer to perform the CSI reporting method in the second aspect or any possible design of the second aspect. BRIEF DESCRIPTION OF DRAWINGS

[0089] FIG. 1 is a flow diagram of an AI-BM model in a data collection phase in an AI-BM use case;

[0090] FIG. 2 is a flow diagram of an AI-BM model in an inference phase in an AI-BM use case;

[0091] FIG. 3 is a schematic diagram of a communication system architecture provided by an embodiment of the present application;

[0092] FIG. 4 is a flow diagram of a CSI reporting method provided by an embodiment of the present application;

[0093] FIG. 5 is a flow diagram of a CSI reporting method provided by an embodiment of the present application;

[0094] FIG. 6 is a flow diagram of a CSI reporting method provided by an embodiment of the present application;

[0095] FIG. 7 is a flow diagram of a CSI reporting method provided by an embodiment of the present application;

[0096] FIG. 8 is a flow diagram of a CSI reporting method provided by an embodiment of the present application;

[0097] FIG. 9 is a schematic diagram of a communication device provided by an embodiment of the present application;

[0098] FIG. 10 is a schematic diagram of a communication device provided by an embodiment of the present application;

[0099] FIG. 11 is a schematic diagram of a communication device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0100] Before the embodiments of the present application are introduced, some technical terms related to the embodiments of the present application are explained and described. It should be noted that the following explanation and description are to make the embodiments of the present application easier to be understood, and should not be regarded as a limitation on the protection scope required by the embodiments of the present application.

[0101] In the research of wireless communication, with the introduction of the fifth generation (5th generation, 5G) mobile communication system and its evolution version, the rapid development of various future communication networks, the physical layer related technology will undoubtedly become more and more complex. With the wide recognition of the great advantages of AI technology based on machine learning (machine learning, ML), deep learning (deep learning, DL) and reinforcement learning (reinforcement learning, RL) in solving problems with high complexity and difficulty in modeling and solving, there is an increasingly obvious consensus in the academic and industrial circles on using AI to solve the complex problems of the physical layer of future wireless communication. AI is also increasingly applied to the research and development process of various air interface technologies.

[0102] In the research of 3rd generation partnership project (3rd generation partnership project, 3GPP) air interface AI technology, three typical use cases are involved, which are AI-based beam management (beam management, BM) use case, AI-based channel state information (channel State information, CSI) use case and AI-based positioning (positioning, POS) use case. The AI-based beam management use case can be referred to as AI-BM use case, the AI-based channel state information use case can be referred to as AI-CSI use case, and the AI-based positioning use case can be referred to as AI-POS use case. Among them, the AI-BM use case and the AI-CSI use case both involve the reporting of CSI, so that the base station can optimize the downlink transmission and resource allocation according to the CSI.

[0103] The AI-BM use case is for a millimeter wave frequency band, uses existing mechanisms to perform beam scanning and beam measurement on a subset of beams (referred to as SetB), uses the measurement results as input of an AI-BM model, and outputs an optimal beam in a full set of beams (referred to as SetA) predicted by the AI-BM model, thereby reducing the overhead of beam scanning. In the AI-BM use case, the base station indicates CSI measurement resource configuration information and CSI reporting configuration information to the terminal through RRC signaling. The terminal measures and collects the resources indicated by the CSI measurement resource configuration information, and further reports the CSI conforming to the CSI reporting configuration information to the base station. The CSI conforming to the CSI reporting configuration information can include the reference signal receiving power (RSRP) measurement value of the beams in SetA, the RSRP prediction value of the beams in SetA, the RSRP measurement value of the beams in SetB, the RSRP prediction value of the beams in SetB, and the like.

[0104] The AI-BM model can be deployed in a terminal device or a network device. The stages of the AI-BM model can include a data collection stage, a training stage, and an inference stage. The data collection stage is used to measure and collect the RSRP of the beams in SetA and the RSRP of the beams in SetB. The training stage is used to train the AI-BM model according to the data measured and collected in the data collection stage, to obtain a trained AI-BM model. The inference stage is used to infer an inference result according to the trained AI-BM model. The inference result can include the RSRP prediction value of the beams in SetA, and the like.

[0105] In an example, taking the AI-BM model in the data collection stage in the AI-BM use case as an example, FIG. 1 shows a flowchart of the AI-BM model in the data collection stage in the AI-BM use case, as shown in FIG. 1, the process includes:

[0106] S101: The base station sends radio resource control (RRC) signaling to the terminal, and the terminal receives the RRC signaling.

[0107] The RRC signaling is used to indicate CSI measurement resource configuration information and CSI reporting configuration information. The CSI measurement resource configuration information is used to indicate the measured CSI resources. The CSI reporting configuration information is used to indicate the resources for reporting the CSI measurement results and / or the contents of the reported CSI measurement results.

[0108] The CSI measurement resource configuration information is used to indicate a measured CSI resource, which can be understood as a measured reference signal (RS) or a time-frequency resource carrying the reference signal, which can be used to measure the CSI. The reference signal can be referred to as a channel state information reference signal (CSI-RS). For example, the CSI measurement resource configuration information can include a CSI-RS corresponding to a beam in SetA.

[0109] The CSI reporting configuration information is used to indicate a resource for reporting the CSI and / or the content of the reported CSI. The CSI reporting configuration information can be carried in a CSI-ReportConfig information element. The CSI-ReportConfig information element can include a reportQuantity field and an nrofReportedRS field. The resource for reporting the CSI is used to indicate a resource corresponding to the reported CSI, which can be represented by a channel state information reference signal resource indicator (CRI).

[0110] The reportQuantity field is used to indicate parameters included in the reported CSI.

[0111] The reportQuantity field includes cri-RSRP, which is used to indicate one or more of the following parameters included in the CSI reported by the terminal: cri and RSRP. The cri is used to indicate a CSI-RS resource. The RSRP is used to indicate the signal reception strength of the CSI-RS.

[0112] The following is an example of the reportQuantity field:

[0113] In the above configuration, the reportQuantity field can include any one of none, cri-RI-PMI-CQI, cri-RI-i1, cri-RI-i1-CQI, cri-RI-CQI, cri-RSRP, ssb-Index-RSRP, cri-RI-LI-PMI-CQI. If any one of the above included by the reportQuantity field does not have a further data structure type (such as SEQUENCE, INTEGER), the configuration corresponding to the item of information is NULL; if any one of the above included by the reportQuantity field has a further data structure type, the data structure type detailed configuration information corresponding to the item of information can be represented in the data structure type. For example, the data structure type corresponding to cri-RI-i1-CQI is SEQUENCE, and the SEQUENCE can further include pdsch-BundleSizeForCSI to indicate the subband size assumed when calculating CQI. When ENUMERATED includes n2, the number of PRBs contained in each subband is 2; when ENUMERATED includes n4, the number of PRBs contained in each subband is 4. The information included by the reportQuantity field is introduced as follows:

[0114] When the reportQuantity field includes none, the terminal does not report CSI.

[0115] When the reportQuantity field includes cri-RI-PMI-CQI, the parameters included in the CSI reported by the terminal include: cri, rank indicator (RI), precoding matrix indicator (PMI), and channel quality indicator (CQI).

[0116] When the reportQuantity field includes cri-RI-i1, the parameters included in the CSI reported by the terminal include: cri, RI, and i1.

[0117] When the reportQuantity field includes cri-RI-i1-CQI, the parameters included in the CSI reported by the terminal include: cri, RI, i1, and CQI.

[0118] When the reportQuantity field includes cri-RSRP, the parameters included in the CSI reported by the terminal include: cri and RSRP.

[0119] When the reportQuantity field includes ssb-Index-RSRP, the parameters included in the CSI reported by the terminal include: synchronization signal block index (ssb-Index) and RSRP.

[0120] When the reportQuantity field includes cri-RI-LI-PMI-CQI, the parameters included in the CSI reported by the terminal include: cri, RI, LI, PMI and CQI.

[0121] In this application, RI is used to represent the number of spatial division multiplexing in multiple-input multiple-output (MIMO) transmission. PMI is used to indicate the precoding matrix. CQI is used to indicate the channel quality. i1 is the index of wideband. LI can be a layer indicator (Layer Indicator) or other layer-related indicators.

[0122] It should be understood that this application does not limit the corresponding English representation of Chinese nouns. For example, the English representation of reference signal received power can be RSRP or rsrp. The English representation of channel state information reference signal resource indication can be CRI or cri.

[0123] Optionally, the reportQuantity field can also include any of cri-SINR and ssb-Index-SINR. When the reportQuantity field includes cri-SINR, the parameters included in the CSI reported by the terminal include: cri and signal to interference plus noise ratio (SINR). When the reportQuantity field includes ssb-Index-SINR, the parameters included in the CSI reported by the terminal include: ssb-Index and SINR.

[0124] In the case where the reportQuantity field includes any of cri-RSRP, ssb-Index-RSRP, cri-SINR and ssb-Index-SINR, the terminal needs to report CSI in combination with the information of the nrofReportedRS field. In the case where the reportQuantity field includes other information except cri-RSRP, ssb-Index-RSRP, cri-SINR and ssb-Index-SINR, the terminal does not need to report CSI in combination with the information of the nrofReportedRS field.

[0125] The nrofReportedRS field is used to indicate the number of beams corresponding to the reported CSI. The nrofReportedRS field supports indicating that the maximum number of beams corresponding to the reported CSI is 4.

[0126] The nrofReportedRS field includes n4 to indicate that the number of beams corresponding to the reported CSI is 4.

[0127] The following is a specific example of the nrofReportedRS field:

[0128] nrofReportedRS ………………… ENUMERATED{n1, n2, n3, n4}

[0129] The value of the nrofReportedRS field in the above configuration can include any of n1, n2, n3, and n4.

[0130] When the nrofReportedRS field includes / assigns n1, the terminal reports the CSI corresponding to 1 beam; when the nrofReportedRS field includes / assigns n2, the terminal reports the CSI corresponding to 2 beams; when the nrofReportedRS field includes / assigns n3, the terminal reports the CSI corresponding to 3 beams; and when the nrofReportedRS field includes / assigns n4, the terminal reports the CSI corresponding to 4 beams.

[0131] S102: The base station iterates through the beams in SetA and transmits the CSI-RS corresponding to the beams in SetA; and the terminal receives the CSI-RS corresponding to the beams in SetA.

[0132] S103: The terminal measures the CSI-RS corresponding to the beams in SetA to obtain the RSRP measurement values of the beams in SetA.

[0133] S104: In the case where the AI-BM model is deployed on the terminal, the terminal uses the RSRP measurement values of the beams in SetA as training data to train the AI-BM model.

[0134] S104 is an optional execution step, which is executed in the case where the AI-BM model is deployed on the terminal, and is not executed in the case where the AI-BM model is deployed on the base station.

[0135] S105: In the case where the AI-BM model is deployed on the base station, the terminal transmits the RSRP measurement values of different beams in SetA to the base station multiple times, and the base station receives and stores the RSRP measurement values of the beams in SetA.

[0136] Specifically, the terminal sends the RSRP measurement values of different beams in SetA to the base station multiple times until the terminal sends the RSRP measurement values of all beams in SetA to the base station. Wherein, the terminal sends the RSRP measurement values of 4 beams in SetA to the base station each time.

[0137] S106: The base station trains the AI-BM model with the RSRP measurement values of all beams in SetA as training data.

[0138] Wherein, SetA includes SetB, that is, SetB is a subset of SetA.

[0139] S105 and S106 are optional execution steps, which are executed when the AI-BM model is deployed on the base station; and are not executed when the AI-BM model is deployed on the terminal.

[0140] In another example, taking the case that the AI-BM model is in the inference stage under the AI-BM use case, and the output of the AI-BM model does not include the predicted value of L1-RSRP as an example, Fig. 2 shows a flowchart of the AI-BM model in the inference stage under the AI-BM use case, as shown in Fig. 2, the process includes:

[0141] S201: The base station sends RRC signaling to the terminal, and the terminal receives the RRC signaling.

[0142] Wherein, the RRC signaling includes a CSI-ReportConfig information element, and the CSI-ReportConfig information element includes a reportQuantity field and a nrofReportedRS field. The reportQuantity field includes cri-RSRP, and the nrofReportedRS field includes n4.

[0143] S202: The base station traverses the beams in SetB and sends the CSI-RS corresponding to the beams in SetB; and the terminal receives the CSI-RS corresponding to the beams in SetB.

[0144] S203: The terminal measures the CSI-RS corresponding to the beams in SetB to obtain the RSRP measurement values of the beams in SetB.

[0145] In the case that the AI-BM model is deployed on the terminal, the terminal executes the following S204-S206 steps after executing the S203 step:

[0146] S204: The terminal inputs the RSRP measurement values of the beams in SetB into the AI-BM model to obtain the inference result of the AI-BM model.

[0147] Wherein, the inference result includes the RSRP predicted values of all beams in SetA.

[0148] S205: The terminal sends the cri corresponding to the four optimal beam pairs in SetA and the RSRP prediction value of the four optimal beams in SetA to the base station based on the inference result of the AI-BM model. The base station receives the cri corresponding to the four optimal beam pairs in SetA and the RSRP prediction value of the four optimal beams in SetA.

[0149] Specifically, the terminal sorts the RSRP prediction values of all beams in SetA from large to small, selects the beams corresponding to the first four RSRP prediction values in the sequence as the four optimal beams in SetA, and further sends the cri corresponding to the four optimal beams in SetA and the RSRP prediction value of the four optimal beams in SetA to the base station.

[0150] S206: The base station selects the optimal beam in SetA from the four optimal beams in SetA.

[0151] Specifically, the base station selects the beam with the largest RSRP among the four optimal beams in SetA as the optimal beam in SetA.

[0152] In the case where the AI-BM model is deployed at the base station, the terminal performs the following steps S207-S209 after performing step S203:

[0153] S207: The terminal sends the RSRP measurement value of the four beams in SetB to the base station, and the base station receives the RSRP measurement value of the four beams in SetB.

[0154] S208: The base station inputs the RSRP measurement value of the four beams in SetB into the AI-BM model to obtain the inference result of the AI-BM model.

[0155] The inference result includes the RSRP prediction value of all beams in SetA.

[0156] S209: The base station determines the optimal beam in SetA based on the inference result of the AI-BM model.

[0157] Specifically, the base station selects the beam corresponding to the largest RSRP in the inference result as the optimal beam in SetA.

[0158] An AI-CSI compression use case, using CSI-RS for channel estimation, taking the estimated channel or channel eigenvector as the input of the AI-CSI model, and outputting PMI, thereby reducing the overhead of PMI feedback or improving precoding performance. In the AI-CSI use case, the base station indicates the CSI measurement resource configuration information and the CSI reporting configuration information to the terminal through RRC signaling. The terminal measures and collects the resources indicated by the CSI measurement resource configuration information, and further reports the CSI conforming to the CSI reporting configuration information to the base station. The CSI conforming to the CSI reporting configuration information can include cri, RI, PMI, and the like in the AI-CSI compression use case.

[0159] The AI-CSI compression model can be deployed in a terminal device and a network device. The stages of the AI-CSI compression model can include a data collection stage, a training stage, and an inference stage. The data collection stage is used to measure and collect cri, RI, PMI, and the like. The training stage is used to train the AI-CSI compression model according to the data measured and collected in the data collection stage, to obtain a trained AI-CSI compression model. The inference stage is used to infer an inference result according to the trained AI-CSI compression model. The inference result can include PMI and the like.

[0160] In an example, the AI-CSI model in the AI-CSI use case is in the data collection stage. The base station sends RRC signaling to the terminal, and the RRC signaling includes a CSI-ReportConfig information element and a CSI-RS. The reportQuantity field in the CSI-ReportConfig information element includes cri-RI-PMI-CQI, and the CodebookConfig field includes CodebookConfig-r16. The terminal receives the CSI-RS, performs channel estimation, estimates the channel coefficient H, performs eigenvalue decomposition on H to obtain the channel eigenvector V, and further quantizes the eigenvector V according to the R16 codebook configured by CodebookConfig-r16 to obtain PMI. Since the reportQuantity field includes cri-RI-PMI-CQI, the terminal also needs to measure the channel quality to report cri, RI, PMI, and CQI to the base station. The base station receives the cri, RI, PMI, and CQI reported by the terminal, recovers and stores the channel eigenvector V based on the PMI and the codebook of CodebookConfig-r16.

[0161] The CodebookConfig field is used to indicate the reported codebook information.

[0162] The following is a specific example of the CodebookConfig field:

[0163] In the above configuration, the CodebookConfig field can include any one of CodebookConfig-r16, CodebookConfig-r17, CodebookConfig-v1730, CodebookConfig-r18. The information included in the CodebookConfig field is introduced as follows:

[0164] The CodebookConfig field includes CodebookConfig-r16, which represents an R16 codebook configured by the terminal according to CodebookConfig-r16 to obtain PMI. The CodebookConfig field includes CodebookConfig-r17, which represents an R17 codebook configured by the terminal according to CodebookConfig-r17 to obtain PMI. The CodebookConfig field includes CodebookConfig-v1730, which represents a v1730 codebook configured according to CodebookConfig-v1730 to obtain PMI. The CodebookConfig field includes CodebookConfig-r18, which represents an R18 codebook configured by the terminal according to CodebookConfig-r18 to obtain PMI.

[0165] In another example, in the AI-CSI use case, the AI-CSI model is in the inference stage, the base station sends the CSI-ReportConfig information element and the CSI-RS to the terminal, the reportQuantity field in the CSI-ReportConfig information element includes cri-RI-PMI-CQI, and the CodebookConfig field includes CodebookConfig-r16. The terminal receives the CSI-RS, performs channel estimation, estimates the channel coefficient H, and decomposes H to obtain the channel eigenvector V. The terminal takes the channel eigenvector V as the input of the AI-CSI compression model deployed in the terminal, and obtains the AI-PMI output by the AI-CSI compression model. Since the reportQuantity field includes cri-RI-PMI-CQI, the terminal also needs to measure the channel quality to report cri, RI, AI-PMI and CQI to the base station. The base station receives the cri, RI, AI-PMI, CQI reported by the terminal, takes the AI-PMI as the input of the AI-CSI decompression model deployed in the base station, obtains the channel eigenvector V' output by the AI-CSI decompression model, and further takes the channel eigenvector V' as the precoding matrix to precode the subsequent downlink data.

[0166] In the present application, AI-PMI refers to PMI obtained by using an AI model for inference.

[0167] In the present application, AI-BM model refers to an AI model under the AI-BM use case, and AI-CSI model refers to an AI model under the AI-CSI use case.

[0168] From the above analysis, it can be seen that the CSI reporting configuration information currently configured by the base station does not indicate the CSI content that the terminal needs to report under the AI use case or the non-AI use case, that is, there is no field for indicating whether the reported CSI is used for the AI use case. For example, when the AI-CSI model under the AI-CSI use case is in the inference stage, the terminal uses the AI-PMI obtained by using the AI-CSI compression model deployed by itself for inference, rather than using the codebook configured by the base station to obtain the PMI, but the CodebookConfig field does not support indicating the AI-PMI obtained by using the AI model for inference. In addition, the CSI reporting configuration information configured by the base station under the AI use case cannot accurately indicate the CSI content that the terminal needs to report under the current AI use case and / or the stage of the AI model under the current AI use case, and there is a problem of redundant reporting of CSI content, which wastes the reporting resources of the terminal. For example, when the AI-BM model under the AI-BM use case is in the inference stage and the AI-BM model belongs to a classification model, the terminal can meet the requirement of the base station to determine the optimal beam in SetA from the better beams in SetA by reporting cri to the base station, where cri indicates the better beam in SetA obtained by the AI-BM model for inference, but the information included in the reportQuantity field currently indicates that the terminal at least reports cri and RSRP.

[0169] Therefore, to solve the above problems, the present application provides a CSI reporting method, which can include: a network device sending first information for indicating the use of CSI to a terminal device, the terminal device obtaining the first information, obtaining CSI satisfying the use of the CSI indicated by the first information according to the first information, and sending the CSI to the network device. Wherein, the use of the CSI at least includes whether the CSI is used for the AI use case. In this way, the terminal device can accurately determine whether the reported CSI is used for the AI use case according to the indication of the first information, and report the CSI satisfying the use of the CSI indicated by the first information to the network device, thereby realizing the reporting of the CSI under the AI use case or the non-AI use case to the network device. At the same time, the terminal device avoids obtaining multiple signaling to obtain the CSI required by the network device, and introduces signaling overhead.

[0170] The CSI reporting method provided by the embodiments of the present application will be described below in conjunction with the drawings of the specification.

[0171] The technical method of the embodiments of the present application can be applied to various communication systems in an AI scenario, which can be a third generation partnership project (3GPP) communication system, for example, a long term evolution (LTE) system, and can also be a fifth generation (5G) mobile communication system, a new radio (NR) system, a new radio vehicle to everything (NR V2X) system, and can also be applied to a system in which LTE and 5G are hybrid networked, or a wireless fidelity (WiFi) system, a device-to-device (D2D) communication system, a machine to machine (M2M) communication system, an integrated access and backhaul (IBA) communication system, an Internet of Things (IoT), and other future communication systems, and can also be a non-3GPP communication system, without limitation.

[0172] The technical solution of the embodiments of the present application can be applied to various communication scenarios, for example, can be applied to one or more of the following communication scenarios: enhanced mobile broadband (eMBB), ultra-reliable low latency communication (URLLC), machine type communication (MTC), massive machine type communication (mMTC), D2D, V2X, and IoT communication scenarios.

[0173] FIG. 3 is a structural diagram of a communication system provided by the embodiments of the present application, as shown in FIG. 3, the communication system can include a network device, a terminal device, and an AI node. The devices / nodes in FIG. 3 are introduced as follows.

[0174] The network device can be any device deployed in an access network capable of wireless communication with the terminal device, can also be a chip or chip system that can be provided in the above device, can also be a logic node or logic module or a software-implemented function, and is mainly responsible for functions such as wireless physical control, resource scheduling, wireless resource management, quality of service management, data compression and encryption, wireless access control, and mobility management. Specifically, the network device can be a device supporting wired access or a device supporting wireless access.

[0175] For example, the network device can be composed of one or more access network (AN) / radio access network (RAN) nodes. The AN / RAN node can be various forms of base stations, such as: satellite base station, continued evolution of NodeB (gNB), transmission reception point (TRP), evolved NodeB (eNB), radio network controller (RNC), NodeB (NB), base station controller (BSC), base transceiver station (BTS), home base station (such as home evolved NodeB or home NodeB, HNB), macro base station, micro base station, pico base station, small station, relay station, balloon station, unmanned aerial vehicle station, wireless backhaul node, baseband unit (BBU), or wireless fidelity (Wi-Fi) access point (AP), or star flash management node (grant node, G node), etc. It can be understood that the network device can be a device placed on the ground, or a non-ground device (such as a satellite, an unmanned aerial vehicle, a high-altitude communication device, etc.). In addition, in a communication system using different wireless access technologies, the name of the network device with base station function may be different, which is not limited in the present application.

[0176] In another example, the network device can include a BBU and a remote radio unit (RRU). The BBU and the RRU can be placed in different places, for example: the RRU is pulled away and placed in a high traffic area, and the BBU is placed in a central machine room. The BBU and the RRU can also be placed in the same machine room. The BBU and the RRU can also be different components under one rack.

[0177] In another example, the network device can also be a device including a centralized unit (CU) node, or including a distributed unit (DU) node, or including a CU node and a DU node. For example, the network device can be divided into a CU and a DU from a logical function perspective, functions of part protocol layers are centrally controlled in the CU, and the rest or all protocol layers are distributed in the DU and controlled by the CU. The CU and the DU can be separately arranged, or can be included in the same network element, such as a BBU. Further, the centralized unit CU can also be divided into a control plane (CU-CP) and a user plane (CU-UP).

[0178] In another example, the network device can also be a device including a radio unit (RU), or including a CU, a DU and a RU. The RU can be included in a radio frequency device or a radio frequency unit, such as a RRU, an active antenna unit (AAU) or a remote radio head (RRH).

[0179] It can be understood that the CU (or CU-CP and CU-UP), DU or RU can also have different names in different systems, but those skilled in the art can understand their meanings. For example, in an open radio access network (O-RAN) system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, the CU-CP, the CU-UP, the DU and the RU are taken as examples for description in the present application. Any one of the CU (or the CU-CP, the CU-UP), the DU and the RU in the present application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0180] The terminal device can be a device with wireless transceiving function or a chip or chip system that can be arranged in the device, can allow a user to access a network, and is a device used to provide voice and / or data connectivity to a user. The terminal device can also be referred to as a first terminal device, a user equipment (UE), a subscriber unit, a terminal or a mobile station (MS) or a mobile terminal (MT), etc.

[0181] Exemplarily, the terminal device can be a mobile phone, a tablet computer, or a computer with wireless transceiver function. The terminal device can also be a user station, a mobile station, a remote station, a remote terminal device, a mobile terminal device, a user terminal device, a wireless communication device, a user agent, a user device, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless communication function, a computing device, a processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in Internet of Things, a household appliance, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in unmanned driving, a wireless terminal in telemedicine, a wireless terminal in smart grid, a wireless terminal in smart city, a wireless terminal in smart home, a vehicle with vehicle-to-vehicle (V2V) communication capability, a smart connected vehicle, a drone with unmanned aerial vehicle to unmanned aerial vehicle (UAV to UAV, U2U) communication capability, a terminal device in future network, a terminal device in future evolved public land mobile network (PLMN), a wireless fidelity (Wi-Fi) station (STA), or a terminal node in Iridium satellite communication system, etc. It can be understood that the terminal device and the mobile user can be completely independent. All information related to the user can be stored in a subscriber identity module (SIM) card, which can be used on the terminal device. The terminal device can send and / or receive signals through the air interface to complete interaction with the network side device.

[0182] The AI node is configured to support the use of AI technology in an AI scenario.

[0183] Optionally, the AI node can be deployed in one or more of the following positions in the communication system shown in FIG. 3: a network device, a terminal device, etc., or the AI node can also be deployed separately, for example, in a host or a cloud server of an over the top (OTT) system or a position other than any of the above-mentioned devices.

[0184] It can be understood that the number of AI nodes is not limited in the present application. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, such as different AI nodes being responsible for different functions.

[0185] It can also be understood that the AI nodes can be independent devices, can be integrated into the same device to implement different functions, or can be network elements in a hardware device, or can be software functions running on special hardware, or virtualized functions instantiated on a platform (for example, a cloud platform), and the specific form of the AI nodes is not limited in the present application.

[0186] The AI node can be an AI network element or an AI module.

[0187] It can be understood that the above-mentioned FIG. 3 is only a schematic diagram and does not constitute a limitation on the applicable scenarios of the technical solutions provided by the present application. Those skilled in the art should understand that in the specific implementation process, the communication system shown in FIG. 3 can also include fewer devices than those shown in FIG. 3, or the communication system shown in FIG. 3 can also include other devices, and the number of devices in the communication system shown in FIG. 3 can also be determined according to specific needs and is not limited.

[0188] Optionally, each device in FIG. 3, such as a terminal device and a network device, can also be referred to as a communication device, which can be a general-purpose device or a special-purpose device, and the embodiments of the present application do not make specific limitations.

[0189] Optionally, the functions of each device in FIG. 3 of the present application can be implemented by one device, or can be implemented by multiple devices together, or can be implemented by one or more functional modules in a device, and the embodiments of the present application do not make specific limitations. It can be understood that the above-mentioned functions can be network elements in a hardware device, can be software functions running on special hardware, or can be a combination of hardware and software, or virtualized functions instantiated on a platform (for example, a cloud platform).

[0190] The communication method provided by the embodiments of the present application will be described below in combination with the communication system shown in FIG. 3. The actions, terms, etc. involved in the following embodiments can be mutually referenced, and the message names or parameter names in the messages exchanged between devices in each embodiment are only an example, and other names can also be used in specific implementation. For example, “corresponding” in the following embodiments can be replaced by “associated” and the like, and “sending” in the following embodiments can be replaced by “transmitting” and the like.

[0191] FIG. 4 is a flow diagram of a CSI reporting method according to an embodiment of the present application. As shown in FIG. 4, the CSI reporting method can include the following steps.

[0192] S401: The network device sends first information to the terminal device, and the terminal device acquires the first information.

[0193] The first information is used to indicate the use of CSI.

[0194] The use of CSI indicated by the first information can at least include whether the CSI is used for an AI use case. For example, the use of CSI can include at least one of a CSI applicable use case, a CSI applicable AI use case type, a CSI applicable AI use case stage, or a CSI applicable content to be reported under a use case. The CSI applicable use case includes an AI use case and / or a non-AI use case. The CSI applicable AI use case type includes an AI-BM use case and / or an AI-CSI compression use case. The CSI applicable AI use case stage includes a data collection stage and / or an inference stage. The CSI applicable content to be reported under a use case can include whether all L1-RSRP or L1-SINR measurement results under an AI use case are reported, or any of the CSI to be reported under an AI use case. It should be understood that the CSI applicable AI use case type, the CSI applicable AI use case stage, and the CSI applicable content to be reported under an AI use case are included in the use of CSI in the case of CSI used for an AI use case.

[0195] In this application, the first information can carry a field corresponding to the use of CSI, and the use of CSI is indicated by the carried field. For example, the first information can include at least one of a first field, a second field, a third field, a fourth field, and a fifth field.

[0196] In this application, the first field is used to indicate whether the CSI is used for an AI use case.

[0197] In this application, the element carrying the first field is not limited. For example, the first field can be carried in a CSI-ReportConfig element, or the first field is carried in a lower-level element of the CSI-ReportConfig, or the first field is carried in a higher-level element of the CSI-ReportConfig. The CSI-ReportConfig element is part of the RRC layer signaling, which can usually contain multiple parameters and sub-configurations. The lower-level element of the CSI-ReportConfig refers to an element used to indicate the multiple parameters or sub-configurations contained in the CSI-ReportConfig element, such as the NZP-CSI-RS-ResourceSet element. The higher-level element of the CSI-ReportConfig refers to a higher-level configuration element containing the CSI-ReportConfig element, such as the CSI-MeasConfig element.

[0198] In the case that the first field is carried in the sub-element of CSI-ReportConfig, more fine-grained and flexible indication of whether the CSI is used for AI use cases can be achieved.

[0199] For example, the sub-element of CSI-ReportConfig is NZP-CSI-RS-ResourceSet element, and the first field can be carried in the NZP-CSI-RS-ResourceSet element, achieving the indication of whether the CSI is used for AI use cases with ResourceSet as the granularity. At this time, in the case that the first field indicates that the CSI is used for AI use cases, the AI use cases corresponding to all Resources in the same ResourceSet can be the same or different. The NZP-CSI-RS-ResourceSet element is used to indicate the resources for the terminal to perform downlink channel quality measurement.

[0200] For another example, the sub-element of CSI-ReportConfig is NZP-CSI-RS-Resource element, and the first field can be carried in the NZP-CSI-RS-Resource element, achieving the indication of whether the CSI is used for AI use cases with Resource as the granularity. At this time, in the case that the first field indicates that the CSI is used for AI use cases, the AI use cases corresponding to different Resources can be the same or different.

[0201] In the case that the first field is carried in the super-element of CSI-ReportConfig, more coarse-grained indication of whether the CSI is used for AI use cases can be achieved, saving the signaling overhead. For example, the super-element of CSI-ReportConfig is CSI-MeasConfig element, and the first field can be carried in the CSI-MeasConfig element, achieving the indication of whether the CSI is used for AI use cases with CSI measurement as the granularity. If the first field indicates that the CSI is used for AI use cases, all the CSI measured by the terminal is the CSI under AI use cases. If the first field indicates that the CSI is not used for AI use cases, all the CSI measured by the terminal is not the CSI under AI use cases. The CSI-MeasConfig element is used to indicate all the configuration information required for the terminal to perform CSI measurement.

[0202] In the present application, whether the CSI is used for the AI use case can be indicated by the value of the first field, and the bit length of the first field is not limited. For example, the bit length of the first field is 1 bit, and whether the CSI is used for the AI use case can be indicated by 1 bit value of the first field: if the value of the first field is 1, the first field indicates that the CSI is used for the AI use case. If the value of the first field is 0, the first field indicates that the CSI is not used for the AI use case. For another example, the bit length of the first field is 2 bits, and there is 1 bit in the 2 bits for indicating whether the CSI is used for the AI use case, so that whether the CSI is used for the AI use case can be indicated by the value of the bit. For example, the first bit in the 2 bits of the first field is used for indicating whether the CSI is used for the AI use case, and the second bit is used for indicating the AI use case stage to which the CSI is applicable. If the value of the first bit in the first field is 1, the first field indicates that the CSI is used for the AI use case, and if the value of the first bit in the first field is 0, the first field indicates that the CSI is not used for the AI use case. In the case where the value of the first bit in the first field is 1, if the value of the second bit is 0, the first field indicates that the AI use case stage to which the CSI is applicable is the data collection stage; and if the value of the second bit is 1, the first field indicates that the AI use case stage to which the CSI is applicable is the inference stage.

[0203] Optionally, the first field can be named as an AI enable (ai-Enable) field or other names, which are not limited. The ai-Enable field indicates that the CSI is used for the AI use case, which means that the AI use case is enabled, and vice versa. The ai-Enable field indicates that the CSI is not used for the AI use case, which means that the AI use case is not enabled, and the non-AI use case is enabled.

[0204] In the present application, the second field is used to indicate the codebook information used by the AI use case.

[0205] In the present application, in the case where the AI use case type to which the CSI is applicable includes the AI-CSI compression use case, the second field can be included in the first information, and at this time, the use of the CSI indicated by the first information specifically includes the codebook information used in the AI-CSI compression use case. In the case where the AI use case type to which the CSI is applicable includes the AI-BM use case, the second field can not be included in the first information.

[0206] Optionally, the second field is a CodebookConfig-AI field, or the second field is an enhanced CodebookConfig field. The enhanced CodebookConfig field refers to the CodebookConfig field including a second parameter.

[0207] The following is a specific example of the CodebookConfig-AI field or the enhanced CodebookConfig field:

[0208] The CodebookConfig-AI field or the enhanced CodebookConfig field in the above configuration can include one of CodebookConfig-r16, CodebookConfig-r17, CodebookConfig-v1730, CodebookConfig-r18, and a first parameter. The CodebookConfig-AI field or the enhanced CodebookConfig field includes the first parameter, which indicates a codebook corresponding to an AI use case used by the terminal. Optionally, the first parameter is CodebookConfig-AI.

[0209] The CodebookConfig-AI field or the enhanced CodebookConfig field includes one of CodebookConfig-r16, CodebookConfig-r17, CodebookConfig-v1730, and CodebookConfig-r18, which indicates a codebook corresponding to a non-AI use case used by the terminal. Specifically, the CodebookConfig-AI field or the enhanced CodebookConfig field includes CodebookConfig-r16, which indicates that the terminal obtains the PMI according to the R16 codebook configured by CodebookConfig-r16. The CodebookConfig-AI field or the enhanced CodebookConfig field includes CodebookConfig-r17, which indicates that the terminal obtains the PMI according to the R17 codebook configured by CodebookConfig-r17. The CodebookConfig-AI field or the enhanced CodebookConfig field includes CodebookConfig-v1730, which indicates that the terminal obtains the PMI according to the v1730 codebook configured by CodebookConfig-v1730. The CodebookConfig-AI field or the enhanced CodebookConfig field includes CodebookConfig-r18, which indicates that the terminal obtains the PMI according to the R18 codebook configured by CodebookConfig-r18.

[0210] In the present application, the third field is used to indicate whether the L1-RSRP or L1-SINR measurement result under the AI use case is reported in full. The network device can perform beam management through the measurement result of L1-RSRP or L1-SINR to improve the overall performance of the system. L1-RSRP refers to the average power of the synchronization signal received by the terminal from a single resource element (resource element, RE). L1-SINR can be used for beam management to achieve fast switching between beams. L1-SINR refers to the ratio of the power of the signal received by the terminal to the sum of the interference and noise power. L1-SINR can be used to select beams with low interference and reduce inter-user interference.

[0211] In the present application, in the case that the AI use case type to which the CSI is applicable includes the AI-BM use case, the first information can include a third field, and at this time, the use of the CSI indicated by the first information specifically includes whether the L1-RSRP or L1-SINR measurement result under the AI-BM use case is reported in full.

[0212] Optionally, the third field is an enhanced nroReportedRS field, and the enhanced nroReportedRS field refers to the nroReportedRS field including a second parameter.

[0213] The following is a specific example of the enhanced nrofReportedRS field:

[0214] nrofReportedRS…………………ENUMERATED{n1, n2, n3, n4, second parameter}

[0215] The enhanced nrofReportedRS field in the above configuration can include one of n1, n2, n3, n4, and the second parameter.

[0216] The information of the enhanced nrofReportedRS field includes the second parameter, which indicates that the L1-RSRP or L1-SINR measurement result under the AI use case is reported in full. Optionally, the second parameter is ALL.

[0217] The enhanced nrofReportedRS field can include one of n1, n2, n3, n4, representing partial reporting of L1-RSRP or L1-SINR measurement results under the AI use case. Specifically, when the enhanced nrofReportedRS field includes n1, the number of reported L1-RSRP or L1-SINR measurement results under the AI use case is 1. When the enhanced nrofReportedRS field includes n2, the number of reported L1-RSRP or L1-SINR measurement results under the AI use case is 2. When the enhanced nrofReportedRS field includes n3, the number of reported L1-RSRP or L1-SINR measurement results under the AI use case is 3. When the enhanced nrofReportedRS field includes n4, the number of reported L1-RSRP or L1-SINR measurement results under the AI use case is 4.

[0218] In the present application, the fourth field is used to indicate the content that needs to be reported under the CSI applicable use case. The fourth field can include one of CRI-RI-PMI-CQI, CRI-RSRP.

[0219] Optionally, the fourth field is a reportQuantity field.

[0220] In the present application, the fifth field is used to indicate the CSI that meets the CSI use indicated by the first information when the CSI is used for the AI use case. The fifth field can include at least one of cri-RI-PMI, cri-RI-PMI-CQI, cri-RSRP-DataCollection, cri-RSRP-Inference, rsrp, cri.

[0221] In the present application, the information of the fifth field can be maintained or updated. For example, AI-First Use Case and AI-Second Use Case are both AI use cases that require CSI reporting, and the CSI required by AI-First Use Case and AI-Second Use Case for reporting is cri-RSRP. Then cri-RSRP-First Use Case and cri-RSRP-Second Use Case can be added to the information of the fifth field. The information of the fifth field includes cri-RSRP-First Use Case, representing reporting of cri and RSRP measured under AI-First Use Case. The information of the fifth field includes cri-RSRP-Second Use Case, representing reporting of cri and RSRP measured under AI-Second Use Case, so as to accurately indicate the CSI required by the network device for reporting by the terminal device.

[0222] Optionally, the fifth field is a reportQuantity-AI field.

[0223] The following is a specific example of the reportQuantity-AI field:

[0224] In an example, the first information includes at least one of a first field, a second field, a third field, and a fourth field. It is assumed below that the first information is carried in a CSI-ReportConfig information element, the first field is an ai-Enable field, the second field is an enhanced CodebookConfig field, the first parameter in the enhanced CodebookConfig field is CodebookConfig-AI, the third field is an enhanced nroReportedRS field, the second parameter in the enhanced nroReportedRS field is ALL, and the fourth field is a reportQuantity field. The following describes specific fields included in the first information sent by the network device to the terminal device:

[0225] (1) CSI is not used for AI use cases, the network device sends the first information including the ai-Enable field to the terminal device, and the ai-Enable field indicates that CSI is not used for AI use cases. Optionally, the first information can further include the reportQuantity field and / or an enhanced CodebookConfig field including any one of CodebookConfig-r16, CodebookConfig-r17, CodebookConfig-v1730, and CodebookConfig-r18. The enhanced CodebookConfig field is included in the first information, and the enhanced CodebookConfig field does not include CodebookConfig-AI.

[0226] (2) CSI is used for AI use cases, and the AI use case type to which CSI is applicable is an AI-CSI compression use case, and the AI use case phase to which CSI is applicable is a data collection phase. The network device sends the first information including the ai-Enable field and the reportQuantity field to the terminal device. The ai-Enable field indicates that CSI is used for AI use cases, and the reportQuantity field includes cri-RI-PMI-CQI. Optionally, the first information can further include an enhanced CodebookConfig field or a CodebookConfig field, and the enhanced CodebookConfig field does not include CodebookConfig-AI. The first information further includes an enhanced nroReportedRS field, and the enhanced nroReportedRS field does not include ALL.

[0227] (3) CSI is used for AI use cases, and the AI use case type to which the CSI is applicable is an AI-BM use case, and the AI use case stage to which the CSI is applicable is an inference stage, the network device sends first information including an ai-Enable field, an enhanced nroReportedRS field, and a reportQuantity field to the terminal device, and the first information does not include an enhanced CodebookConfig field. Wherein the enhanced nroReportedRS field includes any of n1, n2, n3, n4, and the reportQuantity field includes cri-RSRP. At this time, the output of the AI model deployed in the terminal device or the network device can or can not include the predicted value of L1-RSRP.

[0228] (4) CSI is used for AI use cases, and the AI use case type to which the CSI is applicable is an AI-BM use case, and the AI use case stage to which the CSI is applicable is a data collection stage, the network device sends first information including an ai-Enable field and an enhanced nroReportedRS field to the terminal device, and the first information does not include an enhanced CodebookConfig field. Wherein the ai-Enable field indicates that the CSI is used for AI use cases, and the enhanced nroReportedRS field includes ALL. Optionally, the first information can include a reportQuantity field, and the reportQuantity field includes cri-RSRP.

[0229] (5) CSI is used for AI use cases, and the AI use case type to which the CSI is applicable is an AI-CSI compression use case, and the AI use case stage to which the CSI is applicable is an inference stage, the network device sends first information including an ai-Enable field, an enhanced CodebookConfig field, and a reportQuantity field to the terminal device. Wherein the ai-Enable field indicates that the CSI is used for AI use cases, the enhanced CodebookConfig field includes CodebookConfig-AI, and the reportQuantity field includes cri-RI-PMI-CQI. The first information can not include an enhanced nroReportedRS field.

[0230] In summary, the specific fields included in the first information sent by the network device to the terminal device are shown in the following Table 1:

[0231] Table 1

[0232] In Table 1, the ai-Enable field is enabled, indicating that the ai-Enable field in the first information includes CSI for AI use cases, and the ai-Enable field is not enabled, indicating that the ai-Enable field in the first information includes CSI not for AI use cases.

[0233] In Table 1, the enhanced CodebookConfig field includes CodebookConfig-AI configuration, indicating that the enhanced CodebookConfig field in the first information includes CodebookConfig-AI configuration, and the enhanced CodebookConfig field includes CodebookConfig-AI. The enhanced CodebookConfig field includes CodebookConfig-AI configuration, indicating that the enhanced CodebookConfig field in the first information includes the enhanced CodebookConfig field or does not include the enhanced CodebookConfig field, and in the case of including the enhanced CodebookConfig field in the first information, the enhanced CodebookConfig field does not include CodebookConfig-AI.

[0234] In Table 1, the enhanced nroReportedRS field includes ALL configuration, indicating that the enhanced nroReportedRS field in the first information includes ALL configuration, and the enhanced nroReportedRS field includes ALL. The enhanced nroReportedRS field includes ALL configuration, indicating that the enhanced nroReportedRS field in the first information includes the enhanced nroReportedRS field or does not include the enhanced nroReportedRS field, and in the case of including the enhanced nroReportedRS field in the first information, the enhanced nroReportedRS field does not include ALL.

[0235] In Table 1, the reportQuantity field is configured, indicating that the reportQuantity field is included in the first information.

[0236] In another example, the first information includes at least one of the fifth field, the second field, and the third field, and the following assumes that the first information is carried in the CSI-ReportConfig information element, the second field is the enhanced CodebookConfig field, the first parameter is CodebookConfig-AI, the third field is the enhanced nroReportedRS field, the second parameter is ALL, and the fifth field is the reportQuantity-AI field. The description of the specific field included in the first information sent by the network device to the terminal device is as follows:

[0237] (1) The AI use case type to which the CSI is applicable is an AI-CSI compression use case, the AI use case stage to which the CSI is applicable is a data collection stage, and the network device sends first information including a reportQuantity-AI field to the terminal device through a CSI-ReportConfig information element, wherein the reportQuantity-AI field includes cri-RI-PMI. Optionally, the first information can also include a CodebookConfig field or an enhanced CodebookConfig field, and the enhanced CodebookConfig field does not include CodebookConfig-AI.

[0238] (2) The AI use case type to which the CSI is applicable is an AI-CSI compression use case, the AI use case stage to which the CSI is applicable is an inference stage, and the network device sends first information including a reportQuantity-AI field and an enhanced CodebookConfig field to the terminal device through a CSI-ReportConfig information element, wherein the reportQuantity-AI field includes cri-RI-PMI-CQI, and the enhanced CodebookConfig field includes CodebookConfig-AI.

[0239] (3) The AI use case type to which the CSI is applicable is an AI-BM use case, the AI use case stage to which the CSI is applicable is a data collection stage, and the network device sends first information including a reportQuantity-AI field and an enhanced nroReportedRS field to the terminal device through a CSI-ReportConfig information element, wherein the reportQuantity-AI field includes cri-RSRP-DataCollection, and the enhanced nroReportedRS field includes ALL.

[0240] (4) The AI use case type to which the CSI is applicable is an AI-BM use case, the AI use case stage to which the CSI is applicable is an inference stage, and the network device sends first information including a reportQuantity-AI field and an enhanced nroReportedRS field to the terminal device through a CSI-ReportConfig information element, wherein the reportQuantity-AI field includes cri-RSRP-Inference, and the enhanced nroReportedRS field includes one of n1, n2, n3, and n4.

[0241] (5) The AI use case type to which the CSI is applicable is an AI-BM use case, and the AI use case stage to which the CSI is applicable is a data collection stage. The network device sends, to the terminal device, first information including a reportQuantity-AI field through a CSI-ReportConfig information element, where the reportQuantity-AI field includes rsrp. Optionally, the first information includes an enhanced nroReportedRS field. The enhanced nroReportedRS field includes information of ALL. At this time, the network device sends corresponding CSI-RSs according to a preset protocol constraint on the order of beams, and the terminal device reports rsrp according to the order of beams in the preset protocol constraint.

[0242] In this application, the preset protocol constraint is used to constrain the order of beams.

[0243] (6) The AI use case type to which the CSI is applicable is an AI-BM use case, and the AI use case stage to which the CSI is applicable is an inference stage. The network device sends, to the terminal device, first information including a reportQuantity-AI field through a CSI-ReportConfig information element, where the reportQuantity-AI field includes cri. At this time, the output of the AI model deployed in the terminal device or the network device can or can not include a predicted value of L1-RSRP.

[0244] It should be understood that, in this application, if the output of the AI model deployed in the terminal device or the network device does not include the predicted value of L1-RSRP, it can be characterized that the AI model deployed in the terminal device or the network device is a classification model. The classification model is a main model type in AI models, and the classification model refers to an AI model for predicting a category type output. If the output of the AI model deployed in the terminal device or the network device includes the predicted value of L1-RSRP, it can be characterized that the AI model deployed in the terminal device or the network device is a regression model. The regression model is a main model type in AI models, and the regression model refers to an AI model for predicting a numerical type output.

[0245] S402: The terminal device acquires CSI that meets the purpose of the CSI indicated by the first information according to the indication of the first information.

[0246] In an example, the first information includes at least one of a first field, a second field, a third field, and a fourth field, and the terminal device acquires CSI that meets the purpose of the CSI indicated by the first information, including:

[0247] (1) The first information includes a first field, a third field, and a fourth field, and the first field indicates that the CSI is used for the AI use case, the third field indicates an L1-RSRP or L1-SINR measurement result reporting part under the AI use case, and the fourth field includes a cri-RI-PMI-CQI. The terminal device acquires the cri, RI, and PMI. The terminal device acquires the cri, RI, and PMI according to the prior art, which is not described here.

[0248] It should be understood that the manner in which the third field indicates the L1-RSRP or L1-SINR measurement result reporting part under the AI use case is not limited in this application. For example, by sending signaling including a nrofReportedRS field to the terminal, indicating that the number of L1-RSRP or L1-SINR measurement results corresponding to the AI use case is any one of 1, 2, 3, or 4, to indirectly indicate the L1-RSRP or L1-SINR measurement result reporting part under the AI use case. Alternatively, a new signaling is added to indicate the number of L1-RSRP or L1-SINR measurement results to be reported under the AI use case, and the number of L1-RSRP or L1-SINR measurement results to be reported under the AI use case is less than or equal to the total number of L1-RSRP or L1-SINR measurement results under the AI use case.

[0249] (2) The first information includes a first field, a third field, and a fourth field, and the first field indicates that the CSI is used for the AI use case, the third field indicates an L1-RSRP or L1-SINR measurement result reporting part under the AI use case, and the fourth field includes a cri-RSRP. If the output of the AI model under the AI use case does not include the predicted value of L1-RSRP, the terminal device acquires the cri. If the output of the AI model under the AI use case includes the predicted value of L1-RSRP, the terminal device acquires the cri and RSRP. The terminal device acquires the cri and RSRP according to the prior art, which is not described here.

[0250] (3) The first information includes a first field and a third field, and the first information does not include a second field, the first field indicates that the CSI is used for the AI use case, and the third field indicates that all L1-RSRP or L1-SINR measurement results under the AI use case are reported. The terminal device acquires at least all L1-RSRP or L1-SINR measurement results of the AI use case.

[0251] (4) The first information includes a first field and a second field, and the first field indicates that the CSI is used for the AI use case. The terminal device acquires the cri, RI, PMI, and CQI. The PMI is the PMI acquired by the terminal device using the AI model. The terminal device acquires the cri, RI, and CQI according to the prior art, which is not described here.

[0252] (5) The first information comprises a first field, the first field indicates that the CSI is not used for the AI use case, and the terminal device can obtain the corresponding CSI according to the CSI reporting content configured by the network device.

[0253] In another example, the first information comprises at least one of the fifth field, the second field, and the third field, and the terminal device obtains the CSI that meets the use of the CSI indicated by the first information, including:

[0254] (1) The first information comprises the fifth field, and the fifth field comprises information of cri-RI-PMI. The terminal device obtains the cri, the RI, and the PMI. The terminal device obtains the cri, the RI, and the PMI according to the prior art, and the PMI is the PMI obtained by the terminal device based on the codebook technology.

[0255] (2) The first information comprises the fifth field and the second field, and the fifth field comprises information of cri-RI-PMI-CQI. The terminal device obtains the cri, the RI, the PMI, and the CQI. The terminal device obtains the cri, the RI, the PMI, and the CQI according to the prior art, and the PMI is the PMI obtained by the terminal device using the AI model.

[0256] (3) The first information comprises the fifth field, and the fifth field comprises information of cri-RSRP-DataCollection. The terminal device obtains all L1-RSRP measurement results of the AI use case and the cri. The terminal device obtains the L1-RSRP measurement results and the cri according to the prior art, which will not be described here.

[0257] (4) The first information comprises the fifth field and the third field, the fifth field comprises information of cri-RSRP-Inference, and the third field indicates the L1-RSRP or L1-SINR measurement result reporting part under the AI use case. The terminal device obtains part of the L1-RSRP or L1-SINR measurement results under the AI use case and the cri indicated by the third field. The terminal device obtains the L1-RSRP measurement results and the cri according to the prior art, which will not be described here.

[0258] (5) The first information comprises the fifth field, and the fifth field comprises information of rsrp. The terminal device obtains all L1-RSRP measurement results under the AI use case. The terminal device obtains the L1-RSRP measurement results according to the prior art, which will not be described here.

[0259] (6) The first information comprises the fifth field, and the fifth field comprises information of cri. The terminal device obtains the cri. The terminal device obtains the cri according to the prior art, which will not be described here.

[0260] S403: The terminal device reports the CSI satisfying the use of the CSI indicated by the first information to the network device, and the network device receives the CSI satisfying the use of the CSI indicated by the first information from the terminal device.

[0261] Specifically, the terminal device reports the CSI satisfying the use of the CSI indicated by the first information obtained in S402 to the network device.

[0262] Based on the CSI reporting method shown in FIG. 4, the terminal device can accurately determine whether the reported CSI is used for the AI use case according to the indication of the first information, and report the CSI satisfying the use of the CSI indicated by the first information to the network device, thereby achieving reporting the CSI under the AI use case or the non-AI use case to the network device. At the same time, in the case where the first information indicates that the CSI is used for the AI use case, the AI use case type and the AI use case stage to which the CSI is applicable can also be refined according to the first field, the second field, the third field, the fourth field and the fifth field in the first information, so that the network device does not need to send corresponding CSI reporting indication signaling for different AI use case types and different AI use case stages, thereby saving the signaling overhead.

[0263] Hereinafter, taking the communication system shown in FIG. 3 as an example, the AI use case is an AI-CSI compression use case, the stage of the AI use case is a data collection stage, the terminal device is a terminal, the network device is a base station, the AI-CSI compression model is deployed in the terminal, the AI-CSI decompression model is deployed in the base station, and the first information includes at least the first field and the fourth field. The first information is carried in the CSI-ReportConfig information element, the first field is the ai-Enable field, the bit length of the ai-Enable field is 1 bit, the value of the ai-Enable field is 1, indicating that the CSI is used for the AI use case; the value of the ai-Enable field is 0, indicating that the CSI is not used for the AI use case. The fourth field is the reportQuantity field.

[0264] The CSI reporting method shown in FIG. 4 will be introduced below in combination with FIG. 5.

[0265] S501: The base station sends RRC signaling carrying the CSI-ReportConfig information element to the terminal, and the terminal receives the RRC signaling carrying the CSI-ReportConfig information element.

[0266] The RRC signaling is used to control and manage wireless resources.

[0267] The CSI-ReportConfig information element is used to indicate CSI reporting configuration information.

[0268] The CSI-ReportConfig information element can include an ai-Enable field and a reportQuantity field. The value of the ai-Enable field is 1. The information included in the reportQuantity field includes cri-RI-PMI-CQI. Optionally, the CSI-ReportConfig information element can further include a CodebookConfig field, and the information included in the CodebookConfig field is CodebookConfig-r16. The ai-Enable field is described in S401, and the reportQuantity field and the CodebookConfig field are described above, and thus will not be described here.

[0269] S502: The base station sends a CSI-RS, and the terminal receives the CSI-RS.

[0270] S503: The terminal obtains a channel feature vector based on the CSI-RS.

[0271] S504: The terminal obtains cri, RI, and PMI according to the indication of the CSI-ReportConfig information element.

[0272] Specifically, the terminal quantizes the channel feature vector according to the R16 codebook configured by the CodebookConfig-r16 to obtain the PMI. The terminal obtains the cri and RI according to the prior art, and thus will not be described here.

[0273] S505: The terminal reports the cri, RI, and PMI to the base station, and the base station receives the cri, RI, and PMI.

[0274] S506: The base station obtains a recovered channel feature vector according to the PMI and the R16 codebook configured by the CodebookConfig-r16.

[0275] The base station obtains the recovered channel feature vector according to the PMI and the codebook disclosed by r16 according to the prior art, and thus will not be described here.

[0276] After obtaining the recovered channel feature vector, the base station stores the recovered channel feature vector as a data set to train an AI-CSI compression model and / or an AI-CSI decompression model.

[0277] Based on the CSI reporting method shown in FIG. 5, in the scenario of the data collection phase in the AI-CSI compression use case phase, the terminal can not report the CQI to the base station according to the indication of the first information including the first field and the cri-RI-PMI-CQI, thereby avoiding the problem of redundant reporting of the CQI.

[0278] The following is an example of a communication system shown in FIG. 3, the AI use case is an AI-CSI compression use case, the stage of the AI use case is an inference stage, the terminal device is a terminal, the network device is a base station, and the first information includes a first field and a second field. Among them, the AI-CSI compression model is deployed in the terminal, the AI-CSI decompression model is deployed in the base station, the first information is carried in the CSI-ReportConfig information element, the first field is the ai-Enable field, the bit length of the ai-Enable field is 1 bit, and the value of the ai-Enable field is 1, indicating that the CSI is used for the AI use case; the value of the ai-Enable field is 0, and the CSI is not used for the AI use case. The second field is the enhanced CodebookConfig field.

[0279] The CSI reporting method shown in FIG. 4 is introduced below in conjunction with FIG. 6.

[0280] S601: The base station sends RRC signaling carrying the CSI-ReportConfig information element to the terminal, and the terminal receives the RRC signaling carrying the CSI-ReportConfig information element.

[0281] The RRC signaling is used to control and manage wireless resources.

[0282] The CSI-ReportConfig information element is used to indicate CSI reporting configuration information.

[0283] The CSI-ReportConfig information element can include an ai-Enable field and an enhanced CodebookConfig field. The value of the ai-Enable field is 1. The information of the enhanced CodebookConfig field includes CodebookConfig-AI. The enhanced CodebookConfig field is described in S401 and is not repeated here.

[0284] S602: The base station sends CSI-RS, and the terminal receives the CSI-RS.

[0285] S603: The terminal obtains a channel eigenvector based on the CSI-RS.

[0286] Specifically, the terminal performs channel estimation based on the CSI-RS to obtain channel coefficients, and performs eigenvalue decomposition on the channel coefficients to obtain a channel eigenvector. The channel coefficients are used to describe the attenuation or gain of the channel to the signal. The channel eigenvector is used to describe the characteristics of the channel.

[0287] S604: The terminal obtains cri, RI, PMI, and CQI according to the AI-CSI compression model and the indication of the CSI-ReportConfig information element.

[0288] Specifically, the terminal inputs the channel feature vector into the AI-CSI compression model to obtain the PMI. The terminal obtains the cri, RI, and CQI according to the prior art, which is not described herein. The AI-CSI compression model is a model for compressing and encoding channel state information by using AI technology.

[0289] S605: The terminal reports the cri, RI, PMI, and CQI to the base station, and the base station receives the cri, RI, PMI, and CQI.

[0290] S606: The base station inputs the PMI into the AI-CSI decompression model to obtain the recovered channel feature vector.

[0291] The AI-CSI decompression model is used to recover the channel feature vector from the PMI.

[0292] S607: The base station uses the recovered channel feature vector as a precoding matrix to precode the downlink data.

[0293] The precoding matrix refers to a matrix used for linear transformation of a signal. The downlink data refers to data transmitted by the base station to the terminal. Precoding is a technique for pre-processing a signal.

[0294] Based on the CSI reporting method shown in FIG. 6, in the scenario of the inference stage as the AI-CSI compression use case stage, the terminal can accurately use the AI-CSI compression model deployed by itself to obtain the PMI according to the indication of the first information including the first field and the second field, and report the PMI to the base station, thereby realizing the gain of obtaining the PMI by using AI technology.

[0295] Taking the communication system shown in FIG. 3 as an example, the AI use case is the AI-BM use case, the stage of the AI use case is the data collection stage, the terminal device is the terminal, the network device is the base station, and the first information includes the first field and the third field. The AI-BM model is deployed in the base station, the first information is carried in the CSI-ReportConfig information element, the first field is the ai-Enable field, the bit length of the ai-Enable field is 1 bit, the value of the ai-Enable field is 1, indicating that the CSI is used for the AI use case; the value of the ai-Enable field is 0, indicating that the CSI is not used for the AI use case. The third field is the enhanced nrofReportedRS field.

[0296] The CSI reporting method shown in FIG. 4 is described below in combination with FIG. 7.

[0297] S701: The base station sends RRC signaling carrying a CSI-ReportConfig information element to the terminal, and the terminal receives the RRC signaling carrying the CSI-ReportConfig information element.

[0298] The RRC signaling is used for control and management of wireless resources.

[0299] The CSI-ReportConfig information element can include an ai-Enable field and an enhanced nrofReportedRS field. The value of the ai-Enable field is 1. The information of the enhanced nrofReportedRS field includes ALL. Optionally, the CSI-ReportConfig information element can further include a reportQuantity field, and the information included in the reportQuantity field is cri-RSRP. The ai-Enable field and the enhanced nrofReportedRS field are described in S401, and the reportQuantity field is described above, and thus will not be described here.

[0300] S702: The base station sends CSI-RS corresponding to the beams in SetA, and the terminal receives the CSI-RS corresponding to the beams in SetA.

[0301] S703: The terminal measures the CSI-RS corresponding to the beams in SetA to obtain the RSRP measurement values of the beams in SetA.

[0302] S704: The terminal sends the RSRP measurement values of all the beams in SetA to the base station, and the base station receives and stores the RSRP measurement values of all the beams in SetA.

[0303] S705: The base station uses the RSRP measurement values of all the beams in SetA as training data to train the AI-BM model.

[0304] SetA includes SetB, i.e., SetB is a subset of SetA.

[0305] Based on the CSI reporting method shown in FIG. 7, in the scenario of the AI-BM use case stage as the data collection stage, the terminal can report the measurement results of all the beams to the base station at a time according to the indication of the first information including the first field and the third field, so that the base station can fully use the measurement results of all the beams to train a high-gain AI-BM model, and the signaling consumption introduced by the terminal sending the measurement results of different beams in SetA and SetB multiple times is avoided.

[0306] The following is an example of a communication system shown in FIG. 3, the AI use case is an AI-BM use case, the stage of the AI use case is an inference stage, the terminal device is a terminal, the network device is a base station, and the first information includes a first field and a third field. Among them, the AI-BM model is deployed in the terminal, and the inference result of the AI-BM model includes a probability value that all beams in SetA are optimal beams. The first information is carried in a CSI-ReportConfig information element, the first field is an ai-Enable field, the bit length of the ai-Enable field is 1 bit, the value of the ai-Enable field is 1, indicating that the CSI is used for the AI use case; the value of the ai-Enable field is 0, and the CSI is not used for the AI use case. The third field is an enhanced nrofReportedRS field. The CSI reporting method shown in FIG. 4 is introduced below in conjunction with FIG. 8.

[0307] S801: The base station sends RRC signaling carrying a CSI-ReportConfig information element to the terminal, and the terminal receives the RRC signaling carrying the CSI-ReportConfig information element.

[0308] The RRC signaling is used to control and manage wireless resources.

[0309] The CSI-ReportConfig information element can include an ai-Enable field and an enhanced nrofReportedRS field. The value of the ai-Enable field is 1. The information of the enhanced nrofReportedRS field includes n4. Optionally, the CSI-ReportConfig information element can also include a reportQuantity field, and the information included in the reportQuantity field is cri-RSRP. The ai-Enable field and the enhanced nrofReportedRS field are described in S401, and the reportQuantity field is described above, which will not be repeated here.

[0310] S802: The base station traverses the beams in SetB and sends the CSI-RS corresponding to the beams in SetB; the terminal receives the CSI-RS corresponding to the beams in SetB.

[0311] S803: The terminal measures the CSI-RS corresponding to the beams in SetB to obtain the RSRP measurement value of the beams in SetB.

[0312] S804: The terminal inputs the RSRP measurement value of the beams in SetB into the AI-BM model to obtain the predicted probability value that all beams in SetA are optimal beams.

[0313] S805: The terminal sends the cri corresponding to the four better beam pairs in SetA to the base station based on the inference result of the AI-BM model. The base station receives the cri corresponding to the four better beam pairs in SetA.

[0314] Specifically, the terminal sorts the prediction probability values of all beams in SetA from large to small, selects the beams corresponding to the first four prediction probability values in the sequence as the four better beams in SetA, and further sends the cri corresponding to the four better beams in SetA to the base station.

[0315] S806: The base station selects the best beam in SetA from the four better beams in SetA.

[0316] Specifically, the base station selects any beam in the four better beams in SetA as the best beam in SetA.

[0317] Based on the CSI reporting method shown in FIG. 8, in the inference stage of the AI-BM use case, since the output of the AI-BM model configured by the terminal does not include the prediction value of L1-RSRP, that is, the inference result of the AI-BM model includes the probability value that all beams in SetA are the best beams, at this time, the terminal can report the cri corresponding to the better beams in SetA to the base station according to the indication of the first information including the first field, so as to realize the base station to determine the best beam in SetA from the better beams in SetA, and avoid the terminal to measure the RSRP of all beams in SetA redundantly, thereby saving the energy consumption of the terminal.

[0318] The above mainly describes the scheme provided by the embodiments of the present application from the perspective of interaction between devices. It can be understood that each device, such as a terminal device and a network device, contains a hardware structure and / or software module corresponding to each function to realize the above functions. Those skilled in the art should easily realize that the algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0319] The embodiments of the present application can group the functional modules of the terminal device, network device and the like according to the above method examples. For example, each functional module can be grouped according to each function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. It should be noted that the grouping of modules in the embodiments of the present application is illustrative, and is only a logical grouping. Actual implementation can have another grouping manner.

[0320] FIG. 9 shows a structural diagram of a communication device 900, which can be used to perform the functions of the terminal device involved in the above embodiments. As a possible implementation manner, the communication device 900 shown in FIG. 9 includes a transceiver unit 901, a processing unit 902;

[0321] The transceiver unit 901 is configured to obtain first information, the first information being used to indicate a use of CSI, and the use of CSI at least including whether the CSI is used for an AI use case. For example, the transceiver unit 901 can support the communication device 900 to perform S501, or can support the communication device 900 to perform S601, or can support the communication device 900 to perform S701, or can support the communication device 900 to perform S801.

[0322] The processing unit 902 is configured to obtain, according to the indication of the first information, CSI satisfying the use of CSI indicated by the first information. For example, the processing unit 902 can support the communication device 900 to perform S503-S504, or can support the communication device 900 to perform S603-S604, or can support the communication device 900 to perform S703, or can support the communication device 900 to perform S803-S804.

[0323] The transceiver unit 901 is further configured to report the CSI satisfying the use of CSI indicated by the first information. For example, the transceiver unit 901 can support the communication device 900 to perform S505, or can support the communication device 900 to perform S605, or can support the communication device 900 to perform S704, or can support the communication device 900 to perform S805.

[0324] The above descriptions of the first information, the use of CSI, and the CSI satisfying the use of CSI indicated by the first information can refer to the descriptions in the above method embodiments.

[0325] Specifically, all related contents of the steps involved by the terminal device in the method embodiments shown in FIG. 5, FIG. 6, FIG. 7 and FIG. 8 can be referred to the function description of the corresponding function modules, and will not be repeated here. The communication device 900 is configured to perform the functions of the terminal device in the CSI reporting method shown in FIG. 5, FIG. 6, FIG. 7 and FIG. 8, so as to achieve the same effect as the above CSI reporting.

[0326] FIG. 10 shows a structure diagram of a communication device 1000, which can be used to perform the functions of the network device involved in the above embodiments. As a possible implementation manner, the communication device 1000 shown in FIG. 10 includes a transceiver 1001;

[0327] The transceiver 1001 is configured to send first information, wherein the first information is used to indicate the use of CSI, and the use of CSI at least includes whether the CSI is used for AI use cases. For example, the transceiver 1001 can support the communication device 1000 to perform S501, or can support the communication device 1000 to perform S601, or can support the communication device 1000 to perform S701, or can support the communication device 1000 to perform S801.

[0328] The transceiver 1001 is further configured to receive CSI satisfying the use of CSI indicated by the first information in response to the first information. For example, the transceiver 1001 can support the communication device 1000 to perform S505, or can support the communication device 1000 to perform S605, or can support the communication device 1000 to perform S704, or can support the communication device 1000 to perform S805.

[0329] Wherein, the related descriptions of the first information, the use of CSI, and the CSI satisfying the use of CSI indicated by the first information can be referred to the above method embodiments.

[0330] Specifically, all related contents of the steps involved by the network device in the method embodiments shown in FIG. 5, FIG. 6, FIG. 7 and FIG. 8 can be referred to the function description of the corresponding function modules, and will not be repeated here. The communication device 1000 is configured to perform the functions of the network device in the CSI reporting method shown in FIG. 5, FIG. 6, FIG. 7 and FIG. 8, so as to achieve the same effect as the above CSI reporting method.

[0331] The processing unit can be a processing module, a processor or a controller. It can implement or execute the various exemplary logical blocks, modules, and circuits described in connection with the disclosure. The processor can also be a combination of implementing computing functions, such as a combination of one or more microprocessors, a combination of DSP and microprocessor, and the like. The transceiver can be a communication module, a transceiver circuit or a communication interface, and the like. Any of the above-mentioned communication devices can also include a storage unit for storing the program code and data of any of the communication devices. The storage unit can be a storage module or a memory. When the processing module is a processor, the communication module is a communication interface, and the storage module is a memory, the communication device 900 and the communication device 1000 involved in the embodiments of the present application can be a communication device 1100 shown in FIG. 11. For example, the terminal and the base station mentioned above can adopt the constituent structure shown in FIG. 11 or include the components shown in FIG. 11. FIG. 11 is a constituent diagram of a communication device 1100 provided by an embodiment of the present application. As shown in FIG. 11, the communication device 1100 can include a processor 1101, and optionally, a communication line 1102 and a communication interface 1103.

[0332] Further, the communication device 1100 can also include a memory 1104. The processor 1101, the memory 1104 and the communication interface 1103 can be connected through the communication line 1102.

[0333] The processor 1101 can be a central processing unit (CPU), a general processor network processor (NP), a digital signal processing (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD) or any combination thereof. The processor 1101 can also be other communication devices with processing functions, such as circuits, devices or software modules, and the like.

[0334] The communication line 1102 is used to transmit information between the components included in the communication device 1100.

[0335] The communication interface 1103 is configured to communicate with other devices or other communication networks. The other communication networks can be an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), or the like. The communication interface 1103 can be a radio frequency module, a transceiver, or any communication device capable of communication. In this embodiment of this application, the communication interface 1103 is taken as a radio frequency module for example, and the radio frequency module can include an antenna, a radio frequency circuit, and the like. The radio frequency circuit can include a radio frequency integrated chip, a power amplifier, and the like.

[0336] The memory 1104 is configured to store instructions. The instructions can be a computer program.

[0337] The memory 1104 can be a read-only memory (ROM) or another type of static storage device that can store static information and / or instructions, or can be a random access memory (RAM) or another type of dynamic storage device that can store information and / or instructions, or can be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or another optical disk storage, a magneto-optical disk, a magnetic disk storage medium, or another magnetic storage device, or the like.

[0338] It should be noted that the memory 1104 can exist independently of the processor 1101, or can be integrated with the processor 1101. The memory 1104 can be configured to store instructions or program codes or some data, and the like. The memory 1104 can be located in the communication device 1100, or can be located outside the communication device 1100, without limitation. The processor 1101 is configured to execute the instructions stored in the memory 1104, to implement the random access process preamble sending method provided in the embodiments of this application.

[0339] In an example, the processor 1101 can include one or more CPUs, such as CPU0 and CPU1 in FIG. 11.

[0340] As an optional implementation, the communication device 1100 includes a plurality of processors, for example, in addition to the processor 1101 in FIG. 11, the processor 1107 can also be included.

[0341] As an optional implementation, the communication apparatus 1100 further includes an output device 1105 and an input device 1106. The input device 1106 is a keyboard, a mouse, a microphone, a joystick or the like, and the output device 1105 is a display screen, a speaker or the like.

[0342] It should be noted that the communication apparatus 1100 can be a desktop computer, a laptop computer, a network server, a mobile phone, a tablet computer, a wireless terminal, an embedded device, a chip system or a device having a similar structure as shown in FIG. 11. In addition, the constituent structure shown in FIG. 11 does not constitute a limitation on the communication apparatus, and the communication apparatus can include more or fewer components than those shown in FIG. 11, or combine certain components, or have a different arrangement of components.

[0343] In the embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.

[0344] The embodiments of the present application further provide a computer readable storage medium. All or part of the processes of the above method embodiments can be instructed by a computer program to relevant hardware, and the program can be stored in the above computer readable storage medium. When the program is executed, the processes of the above method embodiments can be included. The computer readable storage medium can be the terminal device of any of the preceding embodiments, such as an internal storage unit including a data transmission end and / or a data receiving end, for example, a hard disk or a memory of the terminal device. The above computer readable storage medium can also be an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card and the like equipped on the terminal device. Further, the above computer readable storage medium can include both the internal storage unit and the external storage device of the terminal device. The above computer readable storage medium is used to store the above computer program and other programs and data required by the terminal device. The above computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0345] It should be understood that, in the technical solutions of the present application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information and the like processing comply with relevant legal provisions and do not violate public order and good customs. For example, the processing of user personal information in the technical solutions of the present application is performed under the authorization of the user, and the same description is not repeated here.

[0346] It should be noted that the terms "first", "second", and the like in the description, claims and drawings of the application are intended to distinguish between similar objects, but are not intended to describe a particular sequential order. Moreover, the terms "comprises", "comprising", and the like are intended to encompass non-exclusive inclusions. For example, processes, methods, articles, or apparatuses that comprise a list of steps or elements are not limited to the listed steps or elements, but can optionally include additional steps or elements not listed. The terms "comprises", "comprising", and the like can be used interchangeably with "includes", "including", and the like.

[0347] It should be understood that in the present application, "at least one" refers to one or more, "multiple" refers to two or more, "at least two" refers to two or three and more, and "and / or" is used to describe the association between the associated objects, indicating that there can be three relationships, for example, "A and / or B" can represent three cases: only A, only B, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can mean a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0348] It should be understood that in the embodiments of the present application, "B corresponding to A" means that B is associated with A. For example, B can be determined according to A. It should also be understood that determining B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information. In addition, "connection" appearing in the embodiments of the present application means direct connection or indirect connection and various connection modes to achieve communication between devices, which is not limited in the embodiments of the present application.

[0349] The "transmit" (transmit / transmission) appearing in the embodiments of the present application means bidirectional transmission, including sending and / or receiving actions, unless otherwise specified. Specifically, "transmit" in the embodiments of the present application includes data sending, data receiving, or data sending and data receiving. Or, the data transmission here includes uplink and / or downlink data transmission. The data can include channels and / or signals, uplink data transmission means uplink channel and / or uplink signal transmission, and downlink data transmission means downlink channel and / or downlink signal transmission. The "network" and "system" appearing in the embodiments of the present application represent the same concept, and the communication system is a communication network.

[0350] Through the description of the above embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the grouping of the above functional modules is exemplified, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is grouped into different functional modules to complete all or part of the functions described above.

[0351] In several embodiments provided in the present application, it should be understood that the disclosed communication device and method can be implemented in other ways. For example, the above-described communication device embodiments are only illustrative, for example, the grouping of the modules or units is only a logical function grouping, and actual implementation can have another grouping manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0352] The units described as separate components can or can not be physically separated, and the components displayed as units can be one physical unit or multiple physical units, that is, can be located in one place or can be distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0353] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0354] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium, including a plurality of instructions for causing an apparatus, such as a single-chip microcomputer, a chip, or a processor, to execute all or part of the steps of the method described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, and various storage program codes.

[0355] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any changes or replacements that are easily thought of by those skilled in the art within the technical scope of the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A CSI reporting method, characterized in that, obtaining first information, the first information being used to indicate the use of channel state information (CSI); the use of the CSI at least including whether the CSI is used for an AI use case; obtaining the CSI satisfying the use according to the indication of the first information; reporting the CSI satisfying the use.

2. A CSI reporting method, characterized in that, sending first information; the first information being used to indicate the use of channel state information (CSI); the use of the CSI at least including whether the CSI is used for an AI use case; receiving the CSI satisfying the use in response to the first information.

3. The method according to claim 1 or 2, characterized in that, The use of the CSI includes at least one of the following: a use case to which the CSI is applicable, an artificial intelligence (AI) use case type to which the CSI is applicable, an AI use case stage to which the CSI is applicable, or content to be reported under the use case to which the CSI is applicable. The use case to which the CSI is applicable includes an AI use case and / or a non-AI use case. The AI use case type to which the CSI is applicable includes an AI-beam management (BM) use case and / or an AI-CSI compression use case. The AI use case stage to which the CSI is applicable includes a data collection stage and / or an inference stage. The content to be reported under the use case to which the CSI is applicable includes at least one of the following: whether L1-RSRP or L1-SINR measurement results under an AI use case are all reported, or CSI to be reported under the AI use case.

4. The method according to claim 1 or 2, characterized in that, The first information includes a first field, and the first field is used to indicate whether the CSI is used for an AI use case.

5. The method of claim 4, characterized in that, in the case where the first field indicates that the CSI is not used for an AI use case, the first information does not include a second field; and the second field indicates codebook information used by the AI use case.

6. The method of claim 4, characterized in that, in the case where the first field indicates that the CSI is used for an AI use case, the first information further includes a second field and / or a third field; the second field indicates codebook information used under the AI use case; the third field indicates whether L1-RSRP or L1-SINR measurement results under the AI use case are all reported.

7. The method of claim 6, characterized in that, in the case where the first field indicates that the CSI is used for an AI use case, and the first information includes the second field, the CSI satisfying the use at least includes a PMI.

8. The method of claim 6, characterized in that, in the case where the first field indicates that the CSI is used for an AI use case, the first information does not include the second field, and the third field indicates that L1-RSRP or L1-SINR measurement results under the AI use case are all reported, the CSI satisfying the use at least includes all L1-RSRP or L1-SINR measurement results under the AI use case.

9. The method of claim 6, characterized in that, In a case that the first field indicates that the CSI is used for the AI use case, the first information does not include the second field, and the third field indicates partial reporting of L1-RSRP or L1-SINR measurement results under the AI use case, the first information further includes a fourth field, the fourth field is used to indicate CSI required to be reported under the AI use case, and the fourth field includes one of cri-RI-PMI-CQI and cri-RSRP.

10. The method of claim 9, wherein, the fourth field includes cri-RI-PMI-CQI, and the CSI satisfying the use case includes channel state information reference signal resource indication cri, rank indication RI, and precoding matrix indication PMI; the fourth field includes cri-RSRP, and the output of the AI model under the AI use case does not include a predicted value of L1-RSRP, and the CSI satisfying the use case includes cri; the fourth field includes cri-RSRP, and the output of the AI model under the AI use case includes a predicted value of L1-RSRP, and the CSI satisfying the use case includes cri and reference signal received power RSRP.

11. The method of any one of claims 2-10, wherein, the first field is carried in a subfield of CSI-ReportConfig; or the first field is carried in a superfield of CSI-ReportConfig; or the first field is carried in a CSI-ReportConfig field.

12. The method of any one of claims 2-11, wherein, the first field is an ai-Enable field, the second field is a CodebookConfig-AI field, the third field is an nroReportedRS field, and the fourth field is a reportQuantity field.

13. The method of claim 1 or 2, wherein, the first information includes a fifth field, and the fifth field is used to indicate the CSI satisfying the use case when the CSI is used for the AI use case.

14. The method of claim 13, wherein, the fifth field includes at least one of cri-RI-PMI, cri-RI-PMI-CQI, cri-RSRP-DataCollection, cri-RSRP-Inference, rsrp, and cri.

15. The method of claim 14, wherein, the fifth field includes the cri-RI-PMI, and the CSI satisfying the use case includes cri, RI, and PMI.

16. The method of claim 14, wherein, in a case that the fifth field includes the cri-RI-PMI-CQI, the first information further includes a second field, and the CSI satisfying the use case includes cri, RI, PMI, and channel quality indication CQI; and the second field indicates codebook information used by the AI use case.

17. The method of claim 14, wherein, The fifth field includes the cri-RSRP-DataCollection, and the CSI satisfying the use includes all L1-RSRP measurement results under the AI use case, cri.

18. The method of claim 14, wherein, The fifth field includes the rsrp, and the CSI satisfying the use includes all L1-RSRP or L1-SINR measurement results under the AI use case.

19. The method of claim 14, wherein, The fifth field includes the cri-RSRP-Inference, the first information further includes a third field, and the third field indicates partial reporting of L1-RSRP or L1-SINR measurement results under the AI use case, and the CSI satisfying the use includes cri and RSRP.

20. The method of claim 14, wherein, The fifth field includes the cri, and the CSI satisfying the use includes cri.

21. The method according to any one of claims 13-20, characterized in that, The fifth field is a reportQuantity-AI field.

22. A communications device, characterized by The communication device is configured to support performing the method of any one of claims 1 and 3-21.

23. A communications device, characterized by The communication device is configured to support performing the method of any one of claims 2 and 3-21.

24. A communications device, characterized by The communication device includes a processor configured to support the communication device to perform the communication method of any one of claims 1 and 3-21, or to perform the method of any one of claims 2 and 3-21.

25. A communication system, characterized by The communication system includes the communication device of claim 22, the communication device of claim 23.

26. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions that, when executed on a computer, cause the computer to perform the method of any one of claims 1 and 3-21, or cause the computer to perform the method of any one of claims 2 and 3-21.

27. A computer program product, characterised in that, The computer program product includes computer instructions that, when executed on a computer, cause the computer to perform the method of any one of claims 1 and 3-21, or cause the computer to perform the method of any one of claims 2 and 3-21.

Images