Reporting method and device, communication equipment, communication system and storage medium

Abstract

The invention provides a reporting method and device, equipment and a storage medium. The method comprises the steps that a terminal reports at least one of first channel state information (CSI) and second CSI to network equipment; wherein the first CSI is determined based on an artificial intelligence (AI) model deployed on the terminal side, the second CSI is determined based on codebook parameters configured by the network equipment, and the first CSI and / or the second CSI are / is used for performing performance monitoring on the AI model. The invention provides a CSI (Channel State Information) reporting method, which can improve the accuracy of monitoring the performance of an AI (Artificial Intelligence) model.

Description

Reporting method and device, communication equipment, communication system, and storage medium Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a reporting method and apparatus, communication equipment, a communication system, and a storage medium. Background Art

[0002] In a communication system, a terminal device typically needs to report downlink channel state information (CSI) to a network device so that the network device can determine the downlink channel quality based on the CSI. Alternatively, the 3rd Generation Partnership Project (3GPP) system introduces compressed CSI reporting and recovery based on a bilateral artificial intelligence (AI) model.

[0003] Summary of the Invention

[0004] The present disclosure provides a reporting method and apparatus, communication equipment, a communication system, and a storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a reporting method is proposed, including:

[0006] The terminal reports at least one of the first channel state information CSI and the second CSI to the network device; wherein the first CSI is determined based on the artificial intelligence AI model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to monitor the performance of the AI ​​model.

[0007] According to a second aspect of an embodiment of the present disclosure, a reporting method is proposed, including:

[0008] The network device receives at least one of the first CSI and the second CSI reported by the terminal; wherein the first CSI is determined based on the AI ​​model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to perform performance monitoring on the AI ​​model.

[0009] According to a third aspect of an embodiment of the present disclosure, a reporting method is provided for a communication system, the communication system including a terminal and a network device, the method including at least one of the following:

[0010] The terminal reports at least one of first channel state information (CSI) and second CSI to the network device; wherein the first CSI is determined based on the AI ​​model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to monitor the performance of the AI ​​model;

[0011] The network device receives at least one of the first CSI and the second CSI reported by the terminal;

[0012] The network device performs performance monitoring on the AI ​​model based on at least one of the first CSI and the second CSI.

[0013] According to a fourth aspect of an embodiment of the present disclosure, a terminal is provided, including:

[0014] A sending module, configured for a terminal to report at least one of first channel state information (CSI) and second CSI to a network device; wherein the first CSI is determined based on an AI model deployed on the terminal side, and the second CSI is determined based on codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to perform performance monitoring on the AI ​​model.

[0015] According to a fifth aspect of an embodiment of the present disclosure, a network device is provided, including:

[0016] A receiving module, configured to receive, by a network device, at least one of a first CSI and a second CSI reported by a terminal; wherein the first CSI is determined based on an AI model deployed on the terminal side, the second CSI is determined based on codebook parameters configured by the network device, and the first CSI and / or the second CSI is used to perform performance monitoring on the AI ​​model.

[0017] According to a sixth aspect of an embodiment of the present disclosure, a communication device is provided, including:

[0018] one or more processors;

[0019] The processor is used to call instructions to enable the communication device to execute the reporting method described in the first aspect or the second aspect.

[0020] According to the seventh aspect of an embodiment of the present disclosure, a communication system is proposed, characterized in that it includes a terminal and a network device, wherein the terminal is configured to implement the reporting method described in the first aspect, and the network device is configured to implement the reporting method described in the first aspect or the second aspect.

[0021] According to an eighth aspect of an embodiment of the present disclosure, a storage medium is proposed, which stores instructions, and is characterized in that when the instructions are executed on a communication device, the communication device executes the reporting method described in the first aspect or the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0023] FIG1A is a schematic diagram of the architecture of some communication systems provided by embodiments of the present disclosure;

[0024] FIG1B is a structural block diagram of a method for “CSI compression reporting and recovery based on a bilateral AI model” provided by one embodiment of the present disclosure;

[0025] 2A-2C are interactive diagrams of a reporting method provided by an embodiment of the present disclosure;

[0026] 3A-3D are flowcharts of a reporting method provided in yet another embodiment of the present disclosure;

[0027] 4A-4D are flowcharts of a reporting method provided in yet another embodiment of the present disclosure;

[0028] FIG5A is a flowchart of a reporting method provided in yet another embodiment of the present disclosure;

[0029] FIG5B is an association relationship between CSI report 1, CSI report 2, CSI report 3 and CSI-RS resource ID 1 provided by one embodiment of the present disclosure;

[0030] FIG6A is a schematic structural diagram of a terminal provided by an embodiment of the present disclosure;

[0031] FIG6B is a schematic diagram of the structure of a network device provided by an embodiment of the present disclosure;

[0032] FIG7A is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure;

[0033] FIG7B is a schematic structural diagram of a chip provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0034] The embodiments of the present disclosure provide a reporting method and apparatus, a communication device, a communication system, and a storage medium.

[0035] In a first aspect, an embodiment of the present disclosure provides a reporting method, the method comprising:

[0036] The terminal reports at least one of the first channel state information CSI and the second CSI to the network device; wherein the first CSI is determined based on the artificial intelligence AI model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to perform performance monitoring on the AI ​​model.

[0037] In the above embodiment, the terminal reports the CSI generated by the AI ​​model (i.e., the aforementioned first CSI) and / or the CSI generated based on the codebook parameters (i.e., the aforementioned second CSI) to the network device. The network device can then monitor the performance of the AI ​​model (e.g., the AI ​​model deployed on the terminal side and / or the AI ​​model deployed on the network device side) based on the “CSI generated by the AI ​​model”. Alternatively, the network device can refer to the “CSI generated based on the codebook parameters (i.e., the aforementioned second CSI)” and combine it with the “CSI generated by the AI ​​model (i.e., the aforementioned first CSI)” to more accurately monitor the performance of the AI ​​model. It can be seen that the present disclosure provides a CSI reporting method that can improve the accuracy of monitoring the performance of the AI ​​model.

[0038] In conjunction with some embodiments of the first aspect, in some embodiments, before the terminal reports at least one of the first CSI and the second CSI to the network device, the method further includes at least one of the following:

[0039] Performing downlink channel estimation to obtain channel estimation information;

[0040] Determining input information of an AI model deployed on the terminal side based on the channel estimation information, and inputting the input information into the AI ​​model deployed on the terminal side to obtain the first CSI;

[0041] The second CSI is determined based on the channel estimation information and a codebook parameter configured by the network device.

[0042] In the above embodiment, the terminal can first obtain channel estimation information and determine the first CSI and / or the second CSI based on the channel estimation information, so that the terminal can subsequently report at least one of the first CSI and the second CSI to the network device, so that the network device can monitor the performance of the AI ​​model (such as: the AI ​​model deployed on the terminal side, and / or the AI ​​model deployed on the network device side) based on the "CSI generated by the AI ​​model (i.e., the aforementioned first CSI)". Alternatively, the network device can refer to the "CSI generated based on the codebook parameters (i.e., the aforementioned second CSI)" and combine it with the CSI generated by the AI ​​model (i.e., the aforementioned first CSI) to more accurately monitor the performance of the AI ​​model, thereby ensuring the successful execution and accuracy of the AI ​​model monitoring.

[0043] In conjunction with some embodiments of the first aspect, in some embodiments, the input information of the AI ​​model includes at least one of the following:

[0044] channel estimation information;

[0045] Angle domain information obtained by preprocessing the channel estimation information;

[0046] Angle and delay domain information obtained by preprocessing the channel estimation information;

[0047] The eigenvector corresponding to the channel estimation information.

[0048] In combination with some embodiments of the first aspect, in some embodiments, the first CSI and the second CSI are included in a first CSI report.

[0049] In the above embodiment, a method is provided for a terminal to report the first CSI and / or the second CSI, so that the terminal can successfully report the first CSI and / or the second CSI, thereby enabling the network device to subsequently successfully monitor the AI ​​model based on the first CSI and / or the second CSI.

[0050] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0051] If the input information of the AI ​​model deployed on the terminal side is angle domain information or angle and delay domain information, determine at least one first spatial domain basis vector and / or at least one first frequency domain basis vector used when calculating the first CSI, and determine at least one second spatial domain basis vector and / or at least two second frequency domain basis vectors used when calculating the second CSI;

[0052] Determine indication information based on at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector, where the indication information is used to indicate at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector;

[0053] The indication information is included in the first CSI report.

[0054] In the above embodiment, when the input information of the AI ​​model deployed on the terminal side is angle domain information or angle and delay domain information, the terminal will indicate at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector to the network device, so that the network device can subsequently determine at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector, and based on at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector, restore information similar to the original channel estimation information, and perform performance monitoring of the AI ​​model based on the restored information.

[0055] In conjunction with some embodiments of the first aspect, in some embodiments, determining the indication information based on at least one of the first spatial basis vector, the first frequency domain basis vector, the second spatial basis vector, and the second frequency domain basis vector includes at least one of the following:

[0056] If the first spatial domain basis vector is the same as the second spatial domain basis vector, and / or the first frequency domain basis vector is the same as the second frequency domain basis vector, determining a first indication, where the first indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector; or, the first indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector;

[0057] If the at least one second spatial domain basis vector is a proper subset of the at least one first spatial domain basis vector, and / or the at least one second frequency domain basis vector is a proper subset of the at least one first frequency domain basis vector, determining a second indication and a third indication, wherein the second indication is used to indicate the at least one first spatial domain basis vector and / or the at least one first frequency domain basis vector, and the third indication is used to indicate the at least one second spatial domain basis vector in the at least one first spatial domain basis vector, and / or, to indicate the at least one second frequency domain basis vector in the at least one first frequency domain basis vector;

[0058] If the at least one second spatial domain basis vector is not a proper subset of the at least one first spatial domain basis vector, and the first spatial domain basis vector is different from the second spatial domain basis vector, and / or if the at least one second frequency domain basis vector is not a proper subset of the at least one first frequency domain basis vector, and the first frequency domain basis vector is different from the second frequency domain basis vector, determine a fourth indication and a fifth indication, the fourth indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector, and the fifth indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector.

[0059] In the above embodiment, when the first CSI and the second CSI are reported simultaneously using the first CSI report, if at least one first spatial basis vector and / or at least one first frequency domain basis vector used when calculating the first CSI is the same as at least one second spatial basis vector and / or at least two second frequency domain basis vectors used when calculating the second CSI, then the first CSI report can include only one first indication to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector, or to indicate at least one second spatial basis vector and / or at least one second frequency domain basis vector, without including two indication information to separately indicate the first spatial basis vector and / or the first frequency domain basis vector and the second spatial basis vector and / or the second frequency domain basis vector, thereby reducing the reporting overhead of the first CSI report (or the bit length value of the first CSI report). Furthermore, when at least one second spatial domain basis vector is a proper subset of at least one first spatial domain basis vector, and / or at least one second frequency domain basis vector is a proper subset of at least one first frequency domain basis vector, a second indication and a third indication may be included in the first CSI report, wherein the second indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector, and the third indication is used to indicate at least one second spatial domain basis vector in at least one first spatial domain basis vector, and / or to indicate at least one second frequency domain basis vector in at least one first frequency domain basis vector. Optionally, since the third indication indicates at least one second spatial basis vector in at least one first spatial basis vector, and / or indicates at least one second frequency domain basis vector in at least one first frequency domain basis vector, rather than indicating at least one second spatial basis vector in all candidate spatial basis vectors, and / or indicating at least one second frequency domain basis vector in all candidate frequency domain basis vectors, the reporting overhead required for the basis vector indication can be reduced. Moreover, since the above-mentioned first spatial basis vector and / or second spatial basis vector are already higher-performance basis vectors, even if the second spatial basis vector is not selected from all candidate spatial basis vectors, and / or the second frequency domain basis vector is not selected from all candidate frequency domain basis vectors, but the second spatial basis vector is selected from at least one first spatial basis vector, and / or the second frequency domain basis vector is selected from at least one first frequency domain basis vector, it can be ensured that the performance will not degrade.

[0060] In combination with some embodiments of the first aspect, in some embodiments, the first CSI is included in a second CSI report, and the second CSI is included in a third CSI report; the second CSI report and the third CSI report are associated with the same CSI-RS resource.

[0061] In the above embodiment, a method is provided for a terminal to report the first CSI and / or the second CSI, so that the terminal can successfully report the first CSI and / or the second CSI, thereby enabling the network device to subsequently successfully monitor the AI ​​model based on the first CSI and / or the second CSI.

[0062] In combination with some embodiments of the first aspect, in some embodiments, the first CSI also includes at least one of the combination coefficient information corresponding to the first spatial basis vector and the combination coefficient information of the first frequency domain basis vector; the second CSI also includes at least one of the combination coefficient information corresponding to the second spatial basis vector and the combination coefficient information of the second frequency domain basis vector.

[0063] In the above embodiment, by including at least one of the combination coefficient information corresponding to the first spatial basis vector and the combination coefficient information of the first frequency domain basis vector in the first CSI; and including at least one of the combination coefficient information corresponding to the second spatial basis vector and the combination coefficient information of the second frequency domain basis vector in the second CSI, so that the network device can subsequently recover information similar to the original channel estimation information based on the above combination coefficient information, the network device can subsequently monitor the performance of the AI ​​model based on the information similar to the original channel estimation information, thereby ensuring the successful monitoring of the AI ​​model.

[0064] In combination with some embodiments of the first aspect, in some embodiments, the absolute value of the reporting overhead difference between the second CSI report and the third CSI report is less than a first threshold.

[0065] In the above embodiment, the reporting overhead is saved and the communication resources are reduced by making the absolute value of the difference in reporting overhead between the second CSI report and the third CSI report smaller than the first threshold.

[0066] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0067] Reporting to the network device at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information; wherein, at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information is included in the first CSI report, or included in the second CSI report, or included in the third CSI report, or included in a fourth CSI report different from the first CSI report, the second CSI report, and the third CSI report;

[0068] The first CSI report and the fourth CSI report are associated with the same CSI-RS resource, or the second CSI report, the third CSI report, and the fourth CSI report are associated with the same CSI-RS resource.

[0069] In the above embodiment, the terminal reports to the network device the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and at least one of the angle and delay domain information obtained by preprocessing the channel estimation information, so that the network device can determine the original channel estimation information based on the input information of the AI ​​model, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and at least one of the angle and delay domain information obtained by preprocessing the channel estimation information, and realize performance monitoring of the AI ​​model by comparing the gap between the original channel estimation information and the information restored by the network device based on the terminal report, thereby ensuring the successful monitoring of the AI ​​model.

[0070] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0071] In response to the input information of the AI ​​model deployed on the terminal side being the same as the precoding vector determined by the precoding matrix index PMI in the second CSI, at least one of the input information of the AI ​​model, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information is not reported.

[0072] In the above embodiment, when the input information of the AI ​​model deployed on the terminal side is the same as the precoding vector determined by the PMI in the second CSI, the network device obtains the second CSI, and after determining the precoding vector based on the PMI in the second CSI, it is equivalent to that the network device has known the input information of the AI ​​model. At this time, the network device can directly monitor the performance of the AI ​​model by comparing the difference between the input information of the AI ​​model and the information restored by the network device based on the terminal report, without the need for the terminal to report at least one of the input information of the AI ​​model, channel estimation information, eigenvector corresponding to the channel estimation information, angle domain information obtained by preprocessing of the channel estimation information, and angle and delay domain information obtained by preprocessing of the channel estimation information, thereby saving communication resources.

[0073] In conjunction with some embodiments of the first aspect, in some embodiments, after reporting at least one of the first CSI and the second CSI to the network device, the method further includes at least one of the following:

[0074] receiving recovery information sent by the network device, where the recovery information is information output by the AI ​​model deployed on the network device side based on the first CSI;

[0075] In response to the input information of the AI ​​model being a feature vector corresponding to the channel estimation information, determining a first monitoring value based on the recovered information and the input information of the AI ​​model deployed on the terminal side;

[0076] determining a second monitoring value based on the recovery information;

[0077] determining a precoding vector based on the PMI in the second CSI;

[0078] In response to the input information of the AI ​​model being a feature vector corresponding to the channel estimation information, determining a third monitoring value based on the precoding vector and the input information of the AI ​​model deployed on the terminal side;

[0079] determining a fourth monitoring value based on the precoding vector;

[0080] Report at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value to the network device, wherein at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is used to perform performance monitoring on the AI ​​model.

[0081] In combination with some embodiments of the first aspect, in some embodiments, at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is reported using the same CSI report; or, at least one of the first monitoring value and the second monitoring value is reported using the fifth CSI report, and at least one of the third monitoring value and the fourth monitoring value is reported using the sixth CSI report.

[0082] In the above embodiment, another method for performance monitoring of the AI ​​model is provided. When using the above method to perform performance monitoring on the AI ​​model, reference is also made to the "CSI generated based on the codebook parameters (i.e., the aforementioned second CSI)" and combined with the CSI generated by the AI ​​model (i.e., the aforementioned first CSI) to more accurately monitor the performance of the AI ​​model, thereby ensuring the successful execution and accuracy of the AI ​​model monitoring.

[0083] In conjunction with some embodiments of the first aspect, in some embodiments, after reporting at least one of the first CSI and the second CSI to the network device, the method further includes:

[0084] receiving at least one CSI-RS resource sent by the network device, where the at least one CSI-RS resource includes at least one of a first CSI-RS resource and a second CSI-RS resource; wherein the first CSI-RS resource is sent by the network device using a first beam, the first beam is determined based on the first CSI, and the second CSI-RS resource is sent by the network device using a second beam, the second beam is determined based on the second CSI;

[0085] Determine a fifth monitoring value by measuring effective channel information of the first CSI-RS resource;

[0086] Determine a sixth monitoring value by measuring effective channel information of the second CSI-RS resource;

[0087] Report at least one of the fifth monitoring value and the sixth monitoring value to the network device, wherein at least one of the fifth monitoring value and the sixth monitoring value is used to perform performance monitoring on the AI ​​model.

[0088] In combination with some embodiments of the first aspect, in some embodiments, at least one of the fifth monitoring value and the sixth monitoring value is reported using the same CSI report; or, the fifth monitoring value and the sixth monitoring value are reported using different CSI reports.

[0089] In the above embodiment, another method for performance monitoring of an AI model is provided. When using the above method to perform performance monitoring on an AI model, reference is also made to the "CSI generated based on the codebook parameters (i.e., the aforementioned second CSI)" and combined with the CSI generated by the AI ​​model (i.e., the aforementioned first CSI) to more accurately monitor the performance of the AI ​​model, thereby ensuring the successful execution and accuracy of AI model monitoring.

[0090] In a second aspect, an embodiment of the present disclosure provides a reporting method, the method comprising:

[0091] The network device receives at least one of the first CSI and the second CSI reported by the terminal; wherein the first CSI is determined based on the AI ​​model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to perform performance monitoring on the AI ​​model.

[0092] In the above embodiment, the terminal reports the CSI generated by the AI ​​model (i.e., the aforementioned first CSI) and / or the CSI generated based on the codebook parameters (i.e., the aforementioned second CSI) to the network device. The network device can then monitor the performance of the AI ​​model (e.g., the AI ​​model deployed on the terminal side and / or the AI ​​model deployed on the network device side) based on the “CSI generated by the AI ​​model”. Alternatively, the network device can refer to the “CSI generated based on the codebook parameters (i.e., the aforementioned second CSI)” and combine it with the “CSI generated by the AI ​​model (i.e., the aforementioned first CSI)” to more accurately monitor the performance of the AI ​​model. It can be seen that the present disclosure provides a CSI reporting method that can improve the accuracy of monitoring the performance of the AI ​​model.

[0093] In conjunction with some embodiments of the second aspect, in some embodiments, the input information of the AI ​​model includes at least one of the following:

[0094] channel estimation information;

[0095] Angle domain information obtained by preprocessing the channel estimation information;

[0096] Angle and delay domain information obtained by preprocessing the channel estimation information;

[0097] The eigenvector corresponding to the channel estimation information.

[0098] In combination with some embodiments of the second aspect, in some embodiments, the first CSI and the second CSI are included in a first CSI report.

[0099] In combination with some embodiments of the second aspect, in some embodiments, the first CSI report includes a first indication, where the first indication is used to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector used when calculating the first CSI, or the first indication is used to indicate at least one second spatial basis vector and / or at least one second frequency domain basis vector used when calculating the second CSI, wherein the first spatial basis vector is the same as the second spatial basis vector, and / or the first frequency domain basis vector is the same as the second frequency domain basis vector; or

[0100] The first CSI report includes a second indication and a third indication, wherein the second indication is used to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector, and the third indication is used to indicate at least one second spatial basis vector in the at least one first spatial basis vector and / or to indicate at least one second frequency domain basis vector in the at least one first frequency domain basis vector; or

[0101] The first CSI report includes a fourth indication and a fifth indication, the fourth indication is used to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector, and the fifth indication is used to indicate at least one second spatial basis vector and / or at least one second frequency domain basis vector.

[0102] In combination with some embodiments of the second aspect, in some embodiments, the first CSI is included in a second CSI report, and the second CSI is included in a third CSI report; the second CSI report and the third CSI report are associated with the same CSI-RS resource.

[0103] In combination with some embodiments of the second aspect, in some embodiments, the first CSI also includes at least one of the combination coefficient information corresponding to the first spatial basis vector and the combination coefficient information of the first frequency domain basis vector; the second CSI also includes at least one of the combination coefficient information corresponding to the second spatial basis vector and the combination coefficient information of the second frequency domain basis vector.

[0104] In combination with some embodiments of the second aspect, in some embodiments, the absolute value of the reporting overhead difference between the second CSI report and the third CSI report is less than a first threshold.

[0105] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0106] Receiving at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, a feature vector corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information, reported by the terminal; wherein at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the feature vector corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information is included in the first CSI report, or included in the second CSI report, or included in the third CSI report, or included in a fourth CSI report different from the first CSI report, the second CSI report, and the third CSI report;

[0107] The first CSI report and the fourth CSI report are associated with the same CSI-RS resource, or the second CSI report, the third CSI report, and the fourth CSI report are associated with the same CSI-RS resource.

[0108] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0109] Determine recovery information based on the first CSI using the AI ​​model deployed on the network device side;

[0110] sending the restoration information to the terminal;

[0111] Receive at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value reported by the terminal; wherein, at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is used to perform performance monitoring on the AI ​​model.

[0112] In combination with some embodiments of the second aspect, in some embodiments, at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is included in the same CSI report; or, at least one of the first monitoring value and the second monitoring value is included in the fifth CSI report, and at least one of the third monitoring value and the fourth monitoring value is included in the sixth CSI report.

[0113] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0114] Sending at least one CSI-RS resource to the terminal based on the first CSI and / or the second CSI, where the at least one CSI-RS resource includes at least one of a first CSI-RS resource and a second CSI-RS resource; wherein the first CSI-RS resource is sent by the network device using a first beam, and the first beam is determined based on the first CSI; and the second CSI-RS resource is sent by the network device using a second beam, and the second beam is determined based on the second CSI;

[0115] Receive at least one of the fifth monitoring value and the sixth monitoring value reported by the terminal; wherein, at least one of the fifth monitoring value and the sixth monitoring value is used to perform performance monitoring on the AI ​​model.

[0116] In combination with some embodiments of the second aspect, in some embodiments, at least one of the fifth monitoring value and the sixth monitoring value is included in the same CSI report; or, the fifth monitoring value and the sixth monitoring value are respectively included in different CSI reports.

[0117] In a third aspect, an embodiment of the present disclosure provides a reporting method for a communication system, wherein the communication system includes a terminal and a network device, and the method includes at least one of the following:

[0118] The terminal reports at least one of first channel state information (CSI) and second CSI to the network device; wherein the first CSI is determined based on the AI ​​model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to monitor the performance of the AI ​​model;

[0119] The network device receives at least one of the first CSI and the second CSI reported by the terminal;

[0120] The network device performs performance monitoring on the AI ​​model based on at least one of the first CSI and the second CSI.

[0121] In a fourth aspect, an embodiment of the present disclosure provides a terminal, including:

[0122] A sending module, configured for a terminal to report at least one of first channel state information (CSI) and second CSI to a network device; wherein the first CSI is determined based on an AI model deployed on the terminal side, and the second CSI is determined based on codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to perform performance monitoring on the AI ​​model.

[0123] In conjunction with some embodiments of the fourth aspect, in some embodiments, before the terminal reports at least one of the first CSI and the second CSI to the network device, the apparatus is further configured to do at least one of the following:

[0124] Performing downlink channel estimation to obtain channel estimation information;

[0125] Determining input information of an AI model deployed on the terminal side based on the channel estimation information, and inputting the input information into the AI ​​model deployed on the terminal side to obtain the first CSI;

[0126] The second CSI is determined based on the channel estimation information and a codebook parameter configured by the network device.

[0127] In conjunction with some embodiments of the fourth aspect, in some embodiments, the input information of the AI ​​model includes at least one of the following:

[0128] channel estimation information;

[0129] Angle domain information obtained by preprocessing the channel estimation information;

[0130] Angle and delay domain information obtained by preprocessing the channel estimation information;

[0131] The eigenvector corresponding to the channel estimation information.

[0132] In combination with some embodiments of the fourth aspect, in some embodiments, the first CSI and the second CSI are included in a first CSI report.

[0133] In conjunction with some embodiments of the fourth aspect, in some embodiments, the device is further used to:

[0134] If the input information of the AI ​​model deployed on the terminal side is angle domain information or angle and delay domain information, determine at least one first spatial domain basis vector and / or at least one first frequency domain basis vector used when calculating the first CSI, and determine at least one second spatial domain basis vector and / or at least two second frequency domain basis vectors used when calculating the second CSI;

[0135] Determine indication information based on at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector, where the indication information is used to indicate at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector;

[0136] The indication information is included in the first CSI report.

[0137] In conjunction with some embodiments of the fourth aspect, in some embodiments, the device is further used to:

[0138] If the first spatial domain basis vector is the same as the second spatial domain basis vector, and / or the first frequency domain basis vector is the same as the second frequency domain basis vector, determining a first indication, where the first indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector; or, the first indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector;

[0139] If the at least one second spatial domain basis vector is a proper subset of the at least one first spatial domain basis vector, and / or the at least one second frequency domain basis vector is a proper subset of the at least one first frequency domain basis vector, determining a second indication and a third indication, wherein the second indication is used to indicate the at least one first spatial domain basis vector and / or the at least one first frequency domain basis vector, and the third indication is used to indicate the at least one second spatial domain basis vector in the at least one first spatial domain basis vector, and / or, to indicate the at least one second frequency domain basis vector in the at least one first frequency domain basis vector;

[0140] If the at least one second spatial domain basis vector is not a proper subset of the at least one first spatial domain basis vector, and the first spatial domain basis vector is different from the second spatial domain basis vector, and / or if the at least one second frequency domain basis vector is not a proper subset of the at least one first frequency domain basis vector, and the first frequency domain basis vector is different from the second frequency domain basis vector, determine a fourth indication and a fifth indication, the fourth indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector, and the fifth indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector.

[0141] In combination with some embodiments of the fourth aspect, in some embodiments, the first CSI is included in the second CSI report, and the second CSI is included in the third CSI report; the second CSI report and the third CSI report are associated with the same CSI-RS resource.

[0142] In combination with some embodiments of the fourth aspect, in some embodiments, the first CSI also includes at least one of the combination coefficient information corresponding to the first spatial basis vector and the combination coefficient information of the first frequency domain basis vector; the second CSI also includes at least one of the combination coefficient information corresponding to the second spatial basis vector and the combination coefficient information of the second frequency domain basis vector.

[0143] In combination with some embodiments of the fourth aspect, in some embodiments, the absolute value of the reporting overhead difference between the second CSI report and the third CSI report is less than a first threshold.

[0144] In conjunction with some embodiments of the fourth aspect, in some embodiments, the device is further used to:

[0145] Reporting to the network device at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information; wherein, at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information is included in the first CSI report, or included in the second CSI report, or included in the third CSI report, or included in a fourth CSI report different from the first CSI report, the second CSI report, and the third CSI report;

[0146] The first CSI report and the fourth CSI report are associated with the same CSI-RS resource, or the second CSI report, the third CSI report, and the fourth CSI report are associated with the same CSI-RS resource.

[0147] In conjunction with some embodiments of the fourth aspect, in some embodiments, the device is further used to:

[0148] In response to the input information of the AI ​​model deployed on the terminal side being the same as the precoding vector determined by the precoding matrix index PMI in the second CSI, at least one of the input information of the AI ​​model, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information is not reported.

[0149] In conjunction with some embodiments of the fourth aspect, in some embodiments, after reporting at least one of the first CSI and the second CSI to the network device, the apparatus is further configured to:

[0150] receiving recovery information sent by the network device, where the recovery information is information output by the AI ​​model deployed on the network device side based on the first CSI;

[0151] In response to the input information of the AI ​​model being a feature vector corresponding to the channel estimation information, determining a first monitoring value based on the recovered information and the input information of the AI ​​model deployed on the terminal side;

[0152] determining a second monitoring value based on the recovery information;

[0153] determining a precoding vector based on the PMI in the second CSI;

[0154] In response to the input information of the AI ​​model being a feature vector corresponding to the channel estimation information, determining a third monitoring value based on the precoding vector and the input information of the AI ​​model deployed on the terminal side;

[0155] determining a fourth monitoring value based on the precoding vector;

[0156] Report at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value to the network device, wherein at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is used to perform performance monitoring on the AI ​​model.

[0157] In combination with some embodiments of the fourth aspect, in some embodiments, at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is reported using the same CSI report; or, at least one of the first monitoring value and the second monitoring value is reported using the fifth CSI report, and at least one of the third monitoring value and the fourth monitoring value is reported using the sixth CSI report.

[0158] In conjunction with some embodiments of the fourth aspect, in some embodiments, after reporting at least one of the first CSI and the second CSI to the network device, the apparatus is further configured to:

[0159] receiving at least one CSI-RS resource sent by the network device, where the at least one CSI-RS resource includes at least one of a first CSI-RS resource and a second CSI-RS resource; wherein the first CSI-RS resource is sent by the network device using a first beam, the first beam is determined based on the first CSI, and the second CSI-RS resource is sent by the network device using a second beam, the second beam is determined based on the second CSI;

[0160] Determine a fifth monitoring value by measuring effective channel information of the first CSI-RS resource;

[0161] Determine a sixth monitoring value by measuring effective channel information of the second CSI-RS resource;

[0162] Report at least one of the fifth monitoring value and the sixth monitoring value to the network device, wherein at least one of the fifth monitoring value and the sixth monitoring value is used to perform performance monitoring on the AI ​​model.

[0163] In combination with some embodiments of the fourth aspect, in some embodiments, at least one of the fifth monitoring value and the sixth monitoring value is reported using the same CSI report; or, the fifth monitoring value and the sixth monitoring value are reported using different CSI reports.

[0164] In a fifth aspect, an embodiment of the present disclosure provides a network device, including:

[0165] A receiving module, configured to receive, by a network device, at least one of a first CSI and a second CSI reported by a terminal; wherein the first CSI is determined based on an AI model deployed on the terminal side, the second CSI is determined based on codebook parameters configured by the network device, and the first CSI and / or the second CSI is used to perform performance monitoring on the AI ​​model.

[0166] In conjunction with some embodiments of the fifth aspect, in some embodiments, the input information of the AI ​​model includes at least one of the following:

[0167] channel estimation information;

[0168] Angle domain information obtained by preprocessing the channel estimation information;

[0169] Angle and delay domain information obtained by preprocessing the channel estimation information;

[0170] The eigenvector corresponding to the channel estimation information.

[0171] In combination with some embodiments of the fifth aspect, in some embodiments, the first CSI and the second CSI are included in a first CSI report.

[0172] In combination with some embodiments of the fifth aspect, in some embodiments, the first CSI report includes a first indication, where the first indication is used to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector used when calculating the first CSI, or the first indication is used to indicate at least one second spatial basis vector and / or at least one second frequency domain basis vector used when calculating the second CSI, wherein the first spatial basis vector is the same as the second spatial basis vector, and / or the first frequency domain basis vector is the same as the second frequency domain basis vector; or

[0173] The first CSI report includes a second indication and a third indication, wherein the second indication is used to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector, and the third indication is used to indicate at least one second spatial basis vector in the at least one first spatial basis vector and / or to indicate at least one second frequency domain basis vector in the at least one first frequency domain basis vector; or

[0174] The first CSI report includes a fourth indication and a fifth indication, the fourth indication is used to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector, and the fifth indication is used to indicate at least one second spatial basis vector and / or at least one second frequency domain basis vector.

[0175] In combination with some embodiments of the fifth aspect, in some embodiments, the first CSI is included in the second CSI report, and the second CSI is included in the third CSI report; the second CSI report and the third CSI report are associated with the same CSI-RS resource.

[0176] In combination with some embodiments of the fifth aspect, in some embodiments, the first CSI also includes at least one of the combination coefficient information corresponding to the first spatial basis vector and the combination coefficient information of the first frequency domain basis vector; the second CSI also includes at least one of the combination coefficient information corresponding to the second spatial basis vector and the combination coefficient information of the second frequency domain basis vector.

[0177] In combination with some embodiments of the fifth aspect, in some embodiments, the absolute value of the reporting overhead difference between the second CSI report and the third CSI report is less than a first threshold.

[0178] In conjunction with some embodiments of the fifth aspect, in some embodiments, the device is further used to:

[0179] Receiving at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, a feature vector corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information, reported by the terminal; wherein at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the feature vector corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information is included in the first CSI report, or included in the second CSI report, or included in the third CSI report, or included in a fourth CSI report different from the first CSI report, the second CSI report, and the third CSI report;

[0180] The first CSI report and the fourth CSI report are associated with the same CSI-RS resource, or the second CSI report, the third CSI report, and the fourth CSI report are associated with the same CSI-RS resource.

[0181] In conjunction with some embodiments of the fifth aspect, in some embodiments, the device is further used to:

[0182] Determine recovery information based on the first CSI using the AI ​​model deployed on the network device side;

[0183] sending the restoration information to the terminal;

[0184] Receive at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value reported by the terminal; wherein, at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is used to perform performance monitoring on the AI ​​model.

[0185] In combination with some embodiments of the fifth aspect, in some embodiments, at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is included in the same CSI report; or, at least one of the first monitoring value and the second monitoring value is included in the fifth CSI report, and at least one of the third monitoring value and the fourth monitoring value is included in the sixth CSI report.

[0186] In conjunction with some embodiments of the fifth aspect, in some embodiments, the device is further used to:

[0187] Sending at least one CSI-RS resource to the terminal based on the first CSI and / or the second CSI, where the at least one CSI-RS resource includes at least one of a first CSI-RS resource and a second CSI-RS resource; wherein the first CSI-RS resource is sent by the network device using a first beam, and the first beam is determined based on the first CSI; and the second CSI-RS resource is sent by the network device using a second beam, and the second beam is determined based on the second CSI;

[0188] Receive at least one of the fifth monitoring value and the sixth monitoring value reported by the terminal; wherein, at least one of the fifth monitoring value and the sixth monitoring value is used to perform performance monitoring on the AI ​​model.

[0189] In combination with some embodiments of the fifth aspect, in some embodiments, at least one of the fifth monitoring value and the sixth monitoring value is included in the same CSI report; or, the fifth monitoring value and the sixth monitoring value are respectively included in different CSI reports.

[0190] In the sixth aspect, an embodiment of the present disclosure proposes a communication device, which includes: one or more processors; one or more memories for storing instructions; wherein the processor is used to call the instructions so that the communication device executes the reporting method described in the first aspect, the optional implementation of the first aspect, the second aspect, and the optional implementation of the second aspect.

[0191] In the seventh aspect, an embodiment of the present disclosure proposes a communication system, which includes: a terminal and a network device; wherein the terminal is configured to execute the method described in the first aspect and the optional implementation of the first aspect, and the network device is configured to execute the method described in the second aspect and the optional implementation of the second aspect.

[0192] In an eighth aspect, an embodiment of the present disclosure proposes a storage medium, which stores instructions. When the instructions are executed on a communication device, the communication device executes the method described in the first aspect, the optional implementation of the first aspect, the second aspect, and the optional implementation of the second aspect.

[0193] In a ninth aspect, an embodiment of the present disclosure proposes a program product. When the program product is executed by a communication device, the communication device executes the method described in the first aspect, the optional implementation of the first aspect, the second aspect, and the optional implementation of the second aspect.

[0194] In a tenth aspect, an embodiment of the present disclosure proposes a computer program, which, when executed on a computer, enables the computer to execute the method described in the first aspect, the optional implementation of the first aspect, the second aspect, and the optional implementation of the second aspect.

[0195] It is understandable that the above-mentioned terminals, network devices, communication devices, communication systems, storage media, program products, and computer programs are all used to execute the methods proposed in the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding methods and will not be repeated here.

[0196] The present disclosure provides invention titles. In some embodiments, the terms "reporting method" and "information reporting method," "information sending method," and "information receiving method" are interchangeable; the terms "communication device" and "information processing device," "information sending device," and "information receiving device" are interchangeable; and the terms "information processing system," "communication system," "information sending system," and "information receiving system" are interchangeable.

[0197] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0198] In each embodiment of the present disclosure, unless otherwise specified or provided for by logic, the terms and / or descriptions between the embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form a new embodiment based on their inherent logical relationships.

[0199] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0200] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "said", "the", "the", etc., may mean "one and only one", or "one or more", "at least one", etc. For example, when using articles such as "a", "an", "the" in English in translation, the noun following the article may be understood as a singular expression or a plural expression.

[0201] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0202] In some embodiments, the terms "at least one of", "at least one of", "at least on eof", "one or more", "a plurality of", "multiple", etc. can be used interchangeably.

[0203] In the embodiments of the present disclosure, descriptions such as “at least one of A, B, C…”, “A and / or B and / or C…”, etc. include the situation where any one of A, B, C… exists alone, and also include any combination of any multiple of A, B, C…, and each situation can exist alone; for example, “at least one of A, B, C” includes the situation where A exists alone, B exists alone, C exists alone, the combination of A and B, the combination of A and C, the combination of B and C, and the combination of A, B, and C; for example, A and / or B includes the situation where A exists alone, B exists alone, and the combination of A and B.

[0204] In some embodiments, descriptions such as "in one case A, in another case B," or "in response to one case A, in response to another case B," may include the following technical solutions depending on the situation: executing A independently of B (in some embodiments, A); executing B independently of A (in some embodiments, B); selectively executing A and B (in some embodiments, selecting between A and B); and executing both A and B (in some embodiments, A and B). The same applies when there are more branches, such as A, B, and C.

[0205] The prefixes such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different description objects and do not constitute any restriction on the position, order, priority, quantity or content of the description objects. For the statement of the description object, please refer to the description in the context of the claims or embodiments, and no unnecessary restriction should be constituted by the use of prefixes. For example, if the description object is a "field", the ordinal number before the "field" in the "first field" and the "second field" does not limit the position or order between the "fields". "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of the "first field" and the "second field". For another example, if the description object is a "level", the ordinal number before the "level" in the "first level" and the "second level" does not limit the priority between the "levels". For another example, the number of description objects is not limited by the ordinal number and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, the objects modified by different prefixes can be the same or different. For example, if the description object is "device", then the "first device" and the "second device" can be the same device or different devices, and their types can be the same or different; for another example, if the description object is "information", then the "first information" and the "second information" can be the same information or different information, and their contents can be the same or different.

[0206] In some embodiments, “including A,” “comprising A,” “used to indicate A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0207] In some embodiments, terms such as "in response to...", "in response to determining...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. can be used interchangeably.

[0208] In some embodiments, terms such as "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not less than", and "above" can be replaced with each other, and terms such as "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", and "below" can be replaced with each other.

[0209] In some embodiments, devices, etc. can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", and "subject" can be used interchangeably.

[0210] In some embodiments, "network" can be interpreted as devices included in the network (eg, access network equipment, core network equipment, etc.).

[0211] In some embodiments, the terms "access network device (AN device)", "radio access network device (RAN device)", "base station (BS)", "radio base station" "fixed station", "node", "access point", "transmission point (TP)", "reception point (RP)", "transmission / reception point (TRP)", "panel", "antenna panel", "antenna array", "cell", "macro cell", "small cell", "femto cell", "pico cell", "sector", "cell group", "carrier", "component carrier", "bandwidth part (BWP)" and the like may be used interchangeably.

[0212] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, etc. can be used interchangeably.

[0213] In some embodiments, the access network device, the core network device, or the network device can be replaced by a terminal. For example, the various embodiments of the present disclosure can also be applied to a structure in which the communication between the access network device, the core network device, or the network device and the terminal is replaced by communication between multiple terminals (for example, it can also be called device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, it can also be set as a structure in which the terminal has all or part of the functions of the access network device. In addition, language such as "uplink" and "downlink" can also be replaced by language corresponding to communication between terminals (for example, "side"). For example, uplink channels, downlink channels, etc. can be replaced by side channels, and uplinks, downlinks, etc. can be replaced by side links.

[0214] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, the core network device, or the network device may have a structure that has all or part of the functions of the terminal.

[0215] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0216] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0217] In addition, each element, each row, or each column in the table of the embodiment of the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0218] The correspondences shown in the tables of the present disclosure can be configured or predefined. The values ​​of the information in each table are merely examples and can be configured to other values, which are not limited by the present disclosure. When configuring the correspondences between information and parameters, it is not necessarily required to configure all the correspondences shown in each table. For example, in the tables of the present disclosure, the correspondences shown in certain rows may not be configured. For another example, appropriate deformation adjustments can be made based on the above tables, such as splitting, merging, etc. The names of the parameters shown in the titles of the above tables may also adopt other names that can be understood by the communication device, and the values ​​or representations of the parameters may also adopt other values ​​or representations that can be understood by the communication device. When implementing the above tables, other data structures may also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables or hash tables, etc.

[0219] The predefined in the present disclosure may be understood as defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.

[0220] FIG1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure. As shown in FIG1A , a communication system 100 may include a terminal 101 and a network device 102 . Optionally, the network device may be at least one of an access network device and a core network device.

[0221] In some embodiments, the terminal 101 may include, for example, a mobile phone, a wearable device, an Internet of Things device, a car with communication function, a smart car, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, and at least one of a wireless terminal device in a smart home, but is not limited thereto.

[0222] In some embodiments, the access network device is, for example, a node or device that accesses a terminal to a wireless network. The access network device may include an evolved NodeB (eNB), a next generation evolved NodeB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved nodeB (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open base station (Open RAN), a cloud base station (Cloud RAN), a base station in other communication systems, and at least one of an access node in a wireless fidelity (WiFi) system, but is not limited thereto.

[0223] In some embodiments, the technical solution of the present disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within the access network devices involved in the embodiments of the present disclosure can be transformed into internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0224] In some embodiments, the access network device can be composed of a centralized unit (CU) and a distributed unit (DU), where the CU can also be called a control unit. The CU-DU structure can be used to split the protocol layer of the access network device, with the functions of some protocol layers centrally controlled by the CU, and the functions of the remaining part or all of the protocol layers distributed in the DU, which is centrally controlled by the CU, but is not limited to this.

[0225] In some embodiments, a core network device may be a single device comprising one or more network elements, or may be a plurality of devices or a group of devices, each comprising all or part of one or more network elements. A network element may be virtual or physical. The core network may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC).

[0226] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution proposed in the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution proposed in the embodiment of the present disclosure is also applicable to similar technical problems.

[0227] The following embodiments of the present disclosure may be applied to the communication system 100 shown in FIG1A , or a portion thereof, but are not limited thereto. The entities shown in FIG1A are illustrative only. The communication system may include all or part of the entities shown in FIG1A , or may include other entities other than those shown in FIG1A . The number and form of the entities may be arbitrary. The connection relationship between the entities is illustrative only. The entities may be connected or disconnected, and the connection may be in any manner, including direct or indirect, wired or wireless.

[0228] The embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), future radio access (FRA), new radio access technology (RAT), new radio (NR), new radio access (NX), future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X), systems utilizing other reporting methods, and next-generation systems based on and extending these systems. Furthermore, multiple systems may be combined (for example, a combination of LTE or LTE-A with 5G).

[0229] Optionally, Figure 1B is a structural block diagram of a method for “compressed reporting and recovery of CSI based on a bilateral AI model” described in the above-mentioned background technology provided in an embodiment of the present disclosure, wherein the UE in Figure 1B is the terminal in the present disclosure, and the gNB in ​​Figure 1B is the network device in the present disclosure. Optionally, referring to Figure 1B, the method for “compressed reporting and recovery of CSI based on a bilateral AI model” may include: deploying AI models on both the terminal and the network device, wherein the AI ​​model deployed on the terminal side may be a partial model for generating the CSI in Figure 1B, and the AI ​​model deployed on the network device side may be a partial model for recovering the CSI in Figure 1B. Optionally, both the AI ​​model deployed on the terminal side and the AI ​​model deployed on the network device side may be obtained by training using collected data sets. In addition, the terminal can first perform downlink channel estimation to obtain channel estimation information (i.e., the downlink channel H in Figure 1B or referred to as downlink channel information H), and can input the channel estimation information into the AI ​​model deployed on the terminal side to compress and quantize it into CSI in the form of a binary bit stream, and then report the CSI to the network device. After receiving the CSI, the network device can input the CSI into the AI ​​model deployed on the network device side to restore information that is similar to the original channel estimation information (i.e., the restored downlink channel H' in Figure 1B), thereby realizing CSI reporting.

[0230] Optionally, performance monitoring is usually required for the above-mentioned AI models (i.e., the AI ​​models deployed on the terminal side, and / or the AI ​​models deployed on the network device side). Currently, the method for performance monitoring of AI models is not clear.

[0231] Optionally, in addition to the above-mentioned “CSI compression reporting and recovery based on the bilateral AI model” method, the terminal can also implement compressed reporting of CSI based on codebook parameters (for example, codebook parameters of Type I codebook and / or codebook parameters of Type II codebook, etc.). Optionally, the network device can configure at least one codebook parameter to the terminal. After the terminal obtains the channel estimation information through measurement, it can compress the channel estimation information based on the codebook parameter to generate CSI, and report the CSI to the network device. After receiving the CSI, the network device can restore information that is similar to the original channel estimation information in combination with the codebook parameter configured to the terminal, thereby realizing CSI reporting.

[0232] Optionally, in a communication system, when monitoring the performance of an AI model, the relevant performance monitoring information of the method of "CSI reporting based on codebook parameters" can be referred to. In this case, the terminal is required to report the CSI generated by the AI ​​model and the CSI generated based on the codebook parameters to the network device, so that the network device can monitor the performance of the AI ​​model based on these two types of CSI. However, it is currently unclear how the network device monitors the performance of the AI ​​model through the CSI determined by the terminal based on the AI ​​model and / or codebook parameters.

[0233] FIG2A is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG2A , the present disclosure embodiment relates to a reporting method for a communication system 100, the method comprising:

[0234] Step 2101: The terminal performs downlink channel estimation to obtain channel estimation information.

[0235] Optionally, in some embodiments, the terminal may perform downlink channel estimation by measuring and estimating a downlink signal sent by a network device.

[0236] Optionally, the downlink signal may be, for example, a channel-state information reference signal (CSI-RS).

[0237] Step 2102: The terminal determines input information of the AI ​​model deployed on the terminal side based on the channel estimation information.

[0238] Optionally, in some embodiments, one or more AI models may be deployed on the terminal side, and the AI ​​model may be used to generate CSI. Optionally, input information of the AI ​​model deployed on the terminal side may be determined so that the input information is input into the AI ​​model so that the AI ​​model can output CSI, thereby realizing CSI reporting.

[0239] Optionally, in some embodiments, the input information of the AI ​​model deployed on the terminal side may include at least one of the following:

[0240] channel estimation information;

[0241] Angle domain information obtained by preprocessing the channel estimation information;

[0242] Angle and delay domain information obtained by preprocessing the channel estimation information;

[0243] The eigenvector corresponding to the channel estimation information.

[0244] Optionally, in some embodiments, the above-mentioned channel estimation information may be full channel information in the space-frequency domain.

[0245] Optionally, in some embodiments, the angle domain information may be full channel information in the angle domain, or one or more angle domain precoding vector information.

[0246] Optionally, in some embodiments, the above-mentioned angle and delay domain information may be full channel information in the angle and delay domain, or one or more angle and delay domain precoding vector information.

[0247] Optionally, in some embodiments, the eigenvector corresponding to the channel estimation information may refer to one or more precoding vectors in the space-frequency domain.

[0248] Optionally, in some embodiments, when the input information of the AI ​​model is: angle and delay domain information, the input information of the AI ​​model needs to be calculated using Formula 1. Formula 1 is as follows:

[0249] Optionally, W is the input information of the AI ​​model (i.e., angle and delay domain information), W1 is composed of at least one first spatial basis vector (SD basis), W f Composed of at least one first frequency domain basis vector (FD basis), W2 includes the combination coefficient information of the first spatial basis vector and / or the combination coefficient information of the first frequency domain basis vector. Optionally, the angle and delay domain information W used as input information of the AI ​​model can be obtained by discrete Fourier transform (DFT) of the channel estimation information using the first spatial basis vector and the first frequency domain basis vector.

[0250] Optionally, the above-mentioned first spatial basis vector can be selected by the terminal from a spatial basis vector candidate set, and the above-mentioned first frequency domain basis vector can be selected by the terminal from a frequency domain basis vector candidate set. Optionally, the spatial basis vector candidate set can be configured by a network device to the terminal, and the spatial basis vector candidate set includes multiple candidate spatial basis vectors. The frequency domain basis vector candidate set can be configured by a network device to the terminal, and the frequency domain basis vector candidate set includes multiple candidate frequency domain basis vectors. Optionally, each first spatial basis vector or each first frequency domain basis vector can be represented by an eigenvector or by a DFT vector. And, the at least one first frequency domain basis vector can be an independent frequency domain basis vector corresponding to each transmission layer (or called a transmission rank), or it can be the same frequency domain basis vector corresponding to all transmission layers (or called a transmission rank). The at least one first spatial basis vector can be an independent spatial basis vector corresponding to each transmission layer (or called a transmission rank), or it can be the same spatial basis vector corresponding to all transmission layers (or called a transmission rank).

[0251] Optionally, in another embodiment, when the input information of the AI ​​model is angle domain information, the input information of the AI ​​model can also be calculated using the above formula 1. However, when using the above formula 1 to determine the input information of the AI ​​model, the above-mentioned first frequency domain basis vector is not required, but the first spatial domain basis vector is required.

[0252] Optionally, the above-mentioned “AI model” is only an exemplary name, and it can also be a machine learning (ML) model or other models with similar functions, which is not limited in this disclosure.

[0253] Step 2103: The terminal inputs the input information into the AI ​​model deployed on the terminal side to obtain the first CSI.

[0254] Optionally, in some embodiments, multiple AI models may be deployed on the terminal side, and the terminal may select one or more AI models to generate the first CSI.

[0255] Optionally, in some embodiments, when the input information of the AI ​​model deployed on the terminal side is angle domain information or angle and delay domain information, the first CSI may also indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector for generating the first CSI. The first CSI may also include at least one of the combination coefficient information of the first spatial basis vector and the combination coefficient information of the first frequency domain basis vector, so that the network device can subsequently recover information similar to the original channel estimation information (i.e., the channel estimation information actually measured by the terminal in the above step 2101) based on the first CSI, at least one first spatial basis vector, at least one first frequency domain basis vector, the combination coefficient information of the first spatial basis vector, and at least one of the combination coefficient information of the first frequency domain basis vector, and perform performance monitoring of the AI ​​model based on the recovered information. How to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector is introduced in the subsequent step 2105.

[0256] Step 2104: The terminal determines a second CSI based on the channel estimation information and the codebook parameters configured by the network device.

[0257] Optionally, in some embodiments, before determining the second CSI based on the channel estimation information and the codebook parameters, the terminal may also use the above formula 1 to preprocess the channel estimation information to obtain angle and delay domain information, and then determine the second CSI based on the angle and delay domain information and the codebook parameters. Optionally, when using the above formula 1 to preprocess the channel estimation information to obtain angle and delay domain information, W1 in the above formula 1 is composed of at least one second spatial basis vector, W fW2 may include the combination coefficient information of the second spatial basis vector and / or the combination coefficient information of the second frequency domain basis vector, which is composed of at least one second frequency domain basis vector. Optionally, each second spatial basis vector or each second frequency domain basis vector may be represented by an eigenvector or by a DFT vector. Furthermore, the at least one second frequency domain basis vector may be an independent frequency domain basis vector corresponding to each transmission layer (or referred to as a transmission rank), or may be the same frequency domain basis vector corresponding to all transmission layers (or referred to as transmission ranks). The at least one second spatial domain basis vector may be an independent spatial domain basis vector corresponding to each transmission layer (or referred to as a transmission rank), or may be the same spatial domain basis vector corresponding to all transmission layers (or referred to as transmission ranks). Optionally, the second frequency domain basis vector may be the same as the first frequency domain basis vector, and / or the second spatial domain basis vector may be the same as the first spatial domain basis vector; or, optionally, the at least one second spatial domain basis vector may be a proper subset of at least one first spatial domain basis vector, and / or the at least one second frequency domain basis vector may be a proper subset of at least one first frequency domain basis vector, or, optionally, the at least one second spatial domain basis vector may not be a proper subset of at least one first spatial domain basis vector, and the first spatial domain basis vector is different from the second spatial domain basis vector, and / or the at least one second frequency domain basis vector may not be a proper subset of at least one first frequency domain basis vector, and the first frequency domain basis vector is different from the second frequency domain basis vector.

[0258] Optionally, in another embodiment, before determining the second CSI based on the channel estimation information and the codebook parameters, the terminal may also preprocess the channel estimation information using Formula 1 to obtain angle domain information, and then determine the second CSI based on the angle domain information and the codebook parameters. Optionally, when determining the angle domain information using Formula 1, the second frequency domain basis vectors are not required, but the second spatial domain basis vectors are required.

[0259] Optionally, in some embodiments, the second CSI may also indicate at least one second spatial basis vector and / or at least one second frequency domain basis vector for generating the second CSI. The second CSI may also include at least one of the combination coefficient information of the second spatial basis vector and the combination coefficient information of the second frequency domain basis vector, so that the network device can subsequently recover information similar to the original channel estimation information based on the second CSI, at least one second spatial basis vector, at least one second frequency domain basis vector, the combination coefficient information of the second spatial basis vector, and at least one of the combination coefficient information of the second frequency domain basis vector, and perform performance monitoring of the AI ​​model based on the recovered information. How to indicate at least one second spatial basis vector and / or at least one second frequency domain basis vector is introduced in the subsequent step 2105.

[0260] Optionally, in some embodiments, the codebook parameter used by the terminal when determining the second CSI may be a codebook parameter selected from at least one codebook parameter configured by the network device. Optionally, as can be seen from the content of the aforementioned step 2103, the terminal also needs to select an AI model for generating the first CSI.

[0261] Based on this, the following introduces the terminal's selection criteria for "the AI ​​model used to generate the first CSI and the codebook parameters used to generate the second CSI":

[0262] Optionally, in some embodiments, the "codebook parameters for generating the second CSI and the AI ​​model for generating the first CSI" selected by the terminal may satisfy the following conditions: the absolute value of the difference between the load value of the second CSI generated by the terminal based on the selected codebook parameters (or the bit length value of the second CSI) and the load value of the second CSI generated by the terminal based on the selected AI model (or the bit length value of the second CSI) is less than a first threshold. Optionally, the first threshold may be predefined, network configured (for example, configured by Radio Resource Control (RRC)) and / or determined autonomously by the terminal. Optionally, when the first threshold is autonomously determined by the terminal, the terminal may report the first threshold to the network device. For example, the first threshold may be 5 (bits) bits or 10 bits.

[0263] Alternatively, in other embodiments, the network device may configure only one codebook parameter for the terminal, and the terminal may directly determine the second CSI based on the codebook parameter configured by the network device. In this case, the terminal does not need to select the codebook parameter for generating the second CSI, but must select the AI ​​model for generating the first CSI. In this case, the AI ​​model selected by the terminal must meet the following conditions: the absolute difference between the load value of the first CSI generated based on the selected AI model and the load value of the second CSI generated based on the codebook parameter configured by the network device is minimized, or is less than a first threshold.

[0264] Alternatively, in some further embodiments, the network device may configure only one codebook parameter to the terminal, but the codebook parameter configured by the network device satisfies the following conditions: the absolute value of the difference between the load value of the second CSI generated based on the one codebook parameter configured by the network device and the load value of the first CSI generated using one or more AI models currently being used by the terminal is less than a first threshold. In this case, the terminal does not need to select the codebook parameter for generating the second CSI, nor does it need to select the AI ​​model for generating the first CSI.

[0265] Optionally, in other embodiments, the specific codebook parameters used to generate the second CSI and the specific AN model used to generate the first CSI may be predefined and / or preconfigured in advance by the network device, and the predefined and / or preconfigured codebook parameters and AI model may meet the following conditions: the absolute value of the difference between the load value (or bit length value of the second CSI) of the second CSI generated by the terminal based on the predefined and / or preconfigured codebook parameters and the load value (or bit length value of the second CSI) of the second CSI generated by the terminal based on the predefined and / or preconfigured AI model is less than a first threshold. In this case, the terminal does not need to select the codebook parameters for generating the second CSI, nor does it need to select the AI ​​model for generating the first CSI.

[0266] Optionally, in some embodiments, the second CSI may further include a precoding matrix index (PMI), which is used to determine a precoding vector, and the precoding vector may be used to perform performance monitoring on the method of “reporting CSI based on codebook parameters”, or the PMI may be understood as relevant performance monitoring information of the aforementioned method of “reporting CSI based on codebook parameters”. Optionally, by including the PMI in the second CSI, the network device may subsequently perform performance monitoring based on the PMI in the second CSI. For example, the network device may determine a precoding vector based on the PMI and perform performance monitoring on the AI ​​model with reference to the precoding vector.

[0267] In addition, in some embodiments, the transmission rank condition when calculating the above-mentioned first CSI may be the same as the transmission rank condition when calculating the above-mentioned second CSI. For example, the transmission rank condition when calculating the first CSI and the transmission rank condition when calculating the second CSI may both be 1 or 2.

[0268] Step 2105: The terminal reports at least one of the first CSI and the second CSI.

[0269] Optionally, in some embodiments, the terminal may report at least one of the first CSI and the second CSI to the network device. Optionally, the terminal may report one or more first CSIs and / or the terminal may report one or more second CSIs. Optionally, the first CSI is determined based on an AI model deployed on the terminal side, and different first CSIs may be determined by different AI models. The second CSI is determined based on codebook parameters configured by the network device, and different second CSIs may be determined by different codebook parameters. The first CSI and / or second CSI may be used to monitor the performance of the AI ​​model.

[0270] Optionally, in some embodiments, the first CSI and the second CSI are included in a first CSI report. That is, the terminal reports the first CSI and the second CSI using the same CSI report.

[0271] Optionally, in some embodiments, when the first CSI and the second CSI are both included in the first CSI report, if the input information of the AI ​​model deployed on the terminal side is angle domain information or angle and delay domain information, the terminal will determine at least one first spatial domain basis vector and / or at least one first frequency domain basis vector used when calculating the first CSI, and determine at least one second spatial domain basis vector and / or at least two second frequency domain basis vectors used when calculating the second CSI, and will determine indication information based on at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector. The indication information is used to indicate at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector. Afterwards, the terminal can include the indication information in the first CSI report to indicate at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector.

[0272] Optionally, in some embodiments, the method in which the terminal determines the indication information based on at least one of the first spatial basis vector, the first frequency domain basis vector, the second spatial basis vector, and the second frequency domain basis vector may include at least one of the following:

[0273] If the first spatial domain basis vector is the same as the second spatial domain basis vector, and / or the first frequency domain basis vector is the same as the second frequency domain basis vector, determining a first indication, where the first indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector; alternatively, the first indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector;

[0274] If the at least one second spatial domain basis vector is a proper subset of the at least one first spatial domain basis vector, and / or the at least one second frequency domain basis vector is a proper subset of the at least one first frequency domain basis vector, determining a second indication and a third indication, the second indication being used to indicate the at least one first spatial domain basis vector and / or the at least one first frequency domain basis vector, and the third indication being used to indicate the at least one second spatial domain basis vector in the at least one first spatial domain basis vector and / or, for indicating the at least one second frequency domain basis vector in the at least one first frequency domain basis vector;

[0275] If at least one second spatial domain basis vector is not a proper subset of at least one first spatial domain basis vector, and the first spatial domain basis vector is different from the second spatial domain basis vector, and / or if at least one second frequency domain basis vector is not a proper subset of at least one first frequency domain basis vector, and the first frequency domain basis vector is different from the second frequency domain basis vector, determine a fourth indication and a fifth indication, the fourth indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector, and the fifth indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector.

[0276] Optionally, in some other embodiments, the first CSI may be included in the second CSI report, and the second CSI may be included in the third CSI report, that is, the terminal reports the first CSI and the second CSI using the same CSI report.

[0277] Optionally, in some embodiments, when the first CSI is included in the second CSI report and the second CSI is included in the third CSI report, if the input information of the AI ​​model deployed on the terminal side is delay domain information or angle and delay domain information, and if at least one first spatial domain basis vector used to calculate the first CSI is the same as at least one second spatial domain basis vector used to calculate the second CSI, and / or, at least one first frequency domain basis vector used to calculate the first CSI is the same as at least one second frequency domain basis vector used to calculate the second CSI, then the above-mentioned first indication may be included in at least one of the second CSI report and the third CSI report. Optionally, when the above-mentioned first indication is included in either the second CSI report or the third CSI report, for example, when the second CSI report includes the first indication and the third CSI report does not include the first indication, an association relationship can be established between the second CSI report and the third CSI report. At this time, information can be shared between the two CSI reports with the association relationship, that is, even if the first indication is not included in the third CSI report, the third CSI report can share and use the first indication in the second CSI report.

[0278] Optionally, in some embodiments, when the first CSI is included in the second CSI report and the second CSI is included in the third CSI report, if the input information of the AI ​​model deployed on the terminal side is angle domain information or angle and delay domain information, and if the at least one second spatial basis vector is a proper subset of the at least one first spatial basis vector, and / or the at least one second frequency domain basis vector is a proper subset of the at least one first frequency domain basis vector, then both the second CSI report and the third CSI report may include the second indication and the third indication, or the second CSI report may include the third indication and the third CSI report may include the second indication. Optionally, when the second CSI report includes one of the second and third indications, or when the third CSI report includes one of the second and third indications, an association relationship may be established between the second CSI report and the third CSI report, in which case the two associated CSI reports may share information. For example, when the second CSI report includes the third indication and the third CSI report includes the second indication, if an association relationship is established between the second CSI report and the third CSI report, although the second indication is not included in the second CSI report, the second CSI report can still share and use the second indication in the third CSI report. At the same time, although the third CSI report does not include the third indication, the third CSI report can still share and use the third indication in the second CSI report.

[0279] Optionally, in some embodiments, when the first CSI is included in the second CSI report and the second CSI is included in the third CSI report, if the input information of the AI ​​model deployed on the terminal side is angle domain information or angle and delay domain information, and if the at least one second spatial domain basis vector is not a proper subset of the at least one first spatial domain basis vector, and the first spatial domain basis vector is different from the second spatial domain basis vector, and / or, if the at least one second frequency domain basis vector is not a proper subset of the at least one first frequency domain basis vector, and the first frequency domain basis vector is different from the second frequency domain basis vector, the first CSI report and the second CSI report may both include the fourth indication and the fifth indication, or the second CSI report may include the fourth indication and the third CSI report may include the fifth indication.

[0280] Optionally, in some embodiments, when the first CSI is included in the second CSI report and the second CSI is included in the third CSI report, the second CSI report and the third CSI report are associated with the same CSI-RS resource, that is, the second CSI report and the third CSI report can be obtained by measuring the same CSI-RS resource.

[0281] Step 2106: The terminal reports at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information.

[0282] Optionally, in some embodiments, the terminal may report to the network device at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, feature vectors corresponding to the channel estimation information, angle domain information obtained after preprocessing of the channel estimation information, and angle and delay domain information obtained after preprocessing of the channel estimation information.

[0283] Optionally, in some embodiments, the terminal reports to the network device at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information, so that the network device can determine the original channel estimation information based on at least one of the input information of the AI ​​model, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information, and monitor the performance of the AI ​​model by comparing the gap between the original channel estimation information and the information restored by the network device based on the terminal report.

[0284] Optionally, at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information may be included in the above-mentioned first CSI report, or may be included in the above-mentioned second CSI report, or may be included in the above-mentioned third CSI report, or may be included in a fourth CSI report that is different from the above-mentioned first CSI report, second CSI report, and third CSI report.

[0285] Optionally, the first CSI report and the fourth CSI report are associated with the same CSI-RS resource, or the second CSI report, the third CSI report, and the fourth CSI report are associated with the same CSI-RS resource.

[0286] It should be noted that in some embodiments, step 2106 may not be performed. Optionally, when the input information of the AI ​​model deployed on the terminal side is the same as the precoding vector determined by the PMI in the second CSI, the input information of the AI ​​model, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and at least one of the angle and delay domain information obtained by preprocessing the channel estimation information may not be reported. Optionally, in some embodiments, the terminal and the network device may pre-agree that the input information of the AI ​​model is the precoding vector determined by the PMI in the second CSI. Thus, when the network device obtains the second CSI and determines the precoding vector based on the PMI in the second CSI, it is equivalent to that the network device has known the input information of the AI ​​model. At this time, the network device can directly monitor the performance of the AI ​​model by comparing the difference between the input information of the AI ​​model and the information restored by the network device based on the terminal report, without having to determine the original channel estimation information based on at least one of the input information of the AI ​​model reported by the terminal, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information for performance monitoring. Therefore, there is no need to report at least one of the input information of the AI ​​model reported by the terminal, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information, thereby saving communication resources.

[0287] Step 2107: The network device performs performance monitoring on the AI ​​model based on at least one of the first CSI and the second CSI.

[0288] Optionally, in some embodiments, when the terminal reports the first CSI in the above step 2105, the network device in this step 2107 may perform performance monitoring on the AI ​​model based on the first CSI; when the terminal reports the first CSI and the second CSI in the above step 2105, the network device in this step 2107 may perform performance monitoring on the AI ​​model based on the first CSI and the second CSI; when the terminal reports the second CSI in the above step 2105, the network device in this step 2107 may perform performance monitoring based on the second CSI.

[0289] Optionally, in some embodiments, the method of “a network device performing performance monitoring on an AI model based on the first CSI and the second CSI” may include:

[0290] Step a: The network device determines recovery information based on the first CSI using an AI model deployed on the network device side.

[0291] Optionally, the first CSI can be input into the AI ​​model deployed on the network device side so that the AI ​​model deployed on the network device side outputs the recovery information; optionally, the recovery information can be understood as: information similar to the original channel estimation information recovered by the network device based on the first CSI.

[0292] Step b: The network device determines a precoding vector based on the PMI included in the second CSI.

[0293] For a detailed description of the precoding vector, please refer to the above embodiment description.

[0294] Step c, the network device determines the original channel estimation information based on at least one of the input information of the AI ​​model, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information.

[0295] The method for determining the original channel estimation information may refer to the introduction of step 2106 above.

[0296] Step d: The network device determines the performance results of the AI ​​model (i.e., the AI ​​model deployed on the network device side and / or the AI ​​model deployed on the terminal side) based on the recovered information and / or the original channel estimation information.

[0297] Step e: The network device determines a performance result of the codebook parameters based on the precoding vector and / or the original channel estimation information.

[0298] Step f: The network device monitors the performance of the AI ​​model by comparing the performance results of the AI ​​model with the performance results of the codebook parameters.

[0299] Optionally, in some embodiments, the above-mentioned method of "network device monitoring the performance of AI model based on the first CSI" may include: when the terminal reports one or more first CSIs, the network device can use one or more AI models deployed on the network device side to respectively recover recovery information similar to the original channel estimation information based on the one or more first CSIs, and can determine the original channel estimation information (wherein, the method for determining the original channel estimation information can refer to the introduction of the above-mentioned step 2106), and by comparing the gap between the multiple recovered recovery information and the original channel estimation information, the performance results of one or more AI models (i.e., one or more AI models deployed on the terminal side, and / or, one or more AI models deployed on the network device side) can be respectively obtained. Afterwards, the performance results of the one or more AI models can be compared with a preset threshold to achieve performance monitoring of the AI ​​model, or the performance results of the multiple AI models can be compared to achieve performance monitoring of the AI ​​model.

[0300] Optionally, in some embodiments, the above-mentioned method of "network device performing performance monitoring based on the second CSI" may include: when the terminal reports one or more second CSIs, the network device may use the codebook parameters on the network device side to respectively recover recovery information similar to the original channel estimation information based on the one or more second CSIs, and may determine the original channel estimation information (wherein, the method for determining the original channel estimation information may refer to the introduction of step 2106 above), and by comparing the gap between the multiple recovered recovery information and the original channel estimation information to respectively obtain the performance results of the one or more codebook parameters, thereafter, the performance monitoring of the codebook parameters may be achieved by comparing the performance results of the one or more codebook parameters with a preset threshold, or the performance monitoring of the codebook parameters may be achieved by comparing the performance results of the multiple codebook parameters.

[0301] It should be noted that the above-mentioned method of performance monitoring performed by the network device based on the first CSI and / or the second CSI is only an example provided by an embodiment of the present disclosure. It should be understood that other methods of performance monitoring based on the first CSI and / or the second CSI should also be within the scope of protection of the present disclosure.

[0302] Optionally, after monitoring the performance of the AI ​​model, the network device can activate, deactivate, update, switch the model, etc. based on the final monitoring results.

[0303] The reporting method involved in the embodiment of the present disclosure may include at least one of steps S2101 to S2107. For example, step S2101 may be implemented as an independent embodiment, step S2102 may be implemented as an independent embodiment, and step S2103 may be implemented as an independent embodiment, but are not limited thereto.

[0304] Optionally, the above step 2106 is an optional step, which can be optionally executed or not executed.

[0305] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0306] FIG2B is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG2B , the embodiment of the present disclosure relates to a reporting method for a communication system 100, the method comprising:

[0307] Step 2201: The terminal performs downlink channel estimation to obtain channel estimation information.

[0308] Step 2202: The terminal determines input information of the AI ​​model deployed on the terminal side based on the channel estimation information.

[0309] Step 2203: The terminal inputs the input information into the AI ​​model deployed on the terminal side to obtain the first CSI.

[0310] Step 2204: The terminal determines a second CSI based on the channel estimation information and the codebook parameters configured by the network device.

[0311] Step 2205: The terminal reports at least one of the first CSI and the second CSI.

[0312] Step 2206: The terminal reports at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information.

[0313] Step 2207: The network device determines recovery information based on the first CSI.

[0314] For a detailed description of steps 2201 - 2207 , please refer to the above embodiment description.

[0315] Step 2208: The network device sends the recovery information.

[0316] Optionally, in some embodiments, the network device may send the restoration information to the terminal. Optionally, the terminal may receive the restoration information.

[0317] Step 2209: The terminal determines at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value.

[0318] Optionally, at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is used to monitor the performance of the AI ​​model.

[0319] Optionally, the method for the terminal to calculate the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value may include at least one of the following:

[0320] In response to the input information of the AI ​​model being a feature vector corresponding to the channel estimation information, the terminal determines a first monitoring value based on the recovery information and the input information of the AI ​​model deployed on the terminal side; for example, the terminal can determine the first monitoring value by calculating the correlation between the recovery information and the input information of the AI ​​model deployed on the terminal side.

[0321] The terminal determines a second monitoring value based on the recovery information;

[0322] In response to the input information of the AI ​​model being a characteristic vector corresponding to the channel estimation information, the terminal determines a precoding vector based on the PMI in the second CSI, and the terminal determines a third monitoring value based on the precoding vector and the input information of the AI ​​model deployed on the terminal side; for example, the terminal can determine the third monitoring value by calculating the correlation between the precoding vector and the input information of the AI ​​model deployed on the terminal side.

[0323] The terminal determines a fourth monitoring value based on the precoding vector.

[0324] Optionally, in some embodiments, the first monitoring value and the third monitoring value may be the square generalized cosine similarity (SGCS) or intermediate key performance indicators (KPIs). Optionally, the first monitoring value may be the SGCS or intermediate KPI corresponding to the method of “CSI compression reporting and recovery based on bilateral AI model”, and the third monitoring value may be the SGCS or intermediate KPI corresponding to the method of “CSI reporting based on codebook parameters”.

[0325] Optionally, the second monitoring value and the fourth monitoring value may be at least one of throughput, block error rate (BLER), assumed BLER, negative acknowledgment (NACK), and positive acknowledgment (ACK). Optionally, the second monitoring value and the fourth monitoring value may also be referred to as the final KPI. Optionally, the second monitoring value may be at least one of throughput, BLER, assumed BLER, NACK, ACK, and final KPI corresponding to the method of “CSI compression reporting and recovery based on bilateral AI model”. The fourth monitoring value may be at least one of throughput, BLER, assumed BLER, NACK, ACK, and final KPI corresponding to the method of “CSI reporting based on codebook parameters”.

[0326] Step 2210: The terminal reports based on at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value.

[0327] Optionally, in some embodiments, the terminal may report to the network device.

[0328] Optionally, in some embodiments, the terminal may directly report at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value; and / or, in other embodiments, the terminal reports at least one of the first calculated value obtained by calculating the first monitoring value and the third monitoring value via the first function, and the second calculated value obtained by calculating the second monitoring value and the fourth monitoring value via the second function; optionally, the first function may be used, for example, to calculate the difference or ratio between the first monitoring value and the third monitoring value, and the second function may be used, for example, to calculate the difference or ratio between the second monitoring value and the fourth monitoring value.

[0329] Optionally, in some embodiments, the terminal may use the same CSI report to report at least one of the first monitoring value, the second monitoring value, the third monitoring value, the fourth monitoring value, the first calculation value, and the second calculation value; or, the terminal may use the fifth CSI report to report at least one of the first monitoring value, the second monitoring value, and the first calculation value, and use the sixth CSI report to report at least one of the third monitoring value, the fourth monitoring value, and the second calculation value.

[0330] Optionally, in some embodiments, when at least one of the first monitoring value, the second monitoring value, the third monitoring value, the fourth monitoring value, the first calculation value, and the second calculation value is reported using the same CSI report, the bit width for carrying at least one of the first monitoring value, the second monitoring value, and the first calculation value can be predefined, as well as the bit width for carrying at least one of the third monitoring value, the fourth monitoring value, and the second calculation value.

[0331] Step 2211: The network device monitors the performance of the AI ​​model based on the terminal's report.

[0332] Optionally, the network device can perform performance monitoring on the AI ​​model based on at least one of the first monitoring value, the second monitoring value, the third monitoring value, the fourth monitoring value, the first calculation value, and the second calculation value reported by the terminal.

[0333] Optionally, the network device may monitor the performance of the AI ​​model by comparing the first monitoring value and the third monitoring value, or the network device may monitor the performance of the AI ​​model by comparing the second monitoring value and the fourth monitoring value, or the network device may monitor the performance of the AI ​​model by comparing the first calculated value and the second calculated value. Alternatively, the network device may monitor the performance of the AI ​​model by comparing at least one of the first monitoring value, the third monitoring value, and the first calculated value with a preset threshold, or the network device may monitor the performance of the AI ​​model by comparing at least one of the second monitoring value, the fourth monitoring value, and the second calculated value with a preset threshold, but is not limited thereto.

[0334] The reporting method involved in the embodiment of the present disclosure may include at least one of steps S2201 to S2211. For example, step S2201 may be implemented as an independent embodiment, step S2202 may be implemented as an independent embodiment, and step S2203 may be implemented as an independent embodiment, but are not limited thereto.

[0335] Optionally, the above step 2206 is an optional step, which can be optionally executed or not executed.

[0336] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0337] FIG2C is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG2C , the present disclosure embodiment relates to a reporting method for a communication system 100, the method comprising:

[0338] Step 2301: The terminal performs downlink channel estimation to obtain channel estimation information.

[0339] Step 2302: The terminal determines input information of the AI ​​model deployed on the terminal side based on the channel estimation information.

[0340] Step 2303: The terminal inputs the input information into the AI ​​model deployed on the terminal side to obtain the first CSI.

[0341] Step 2304: The terminal determines a second CSI based on the channel estimation information and the codebook parameters configured by the network device.

[0342] Step 2305: The terminal reports at least one of the first CSI and the second CSI.

[0343] Step 2306: The terminal reports at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information.

[0344] For a detailed description of steps 2301 - 2306 , please refer to the above embodiment description.

[0345] Step 2307: The network device sends at least one CSI-RS resource based on the first CSI and / or the second CSI.

[0346] Optionally, in some embodiments, the at least one CSI-RS resource may include at least one of a first CSI-RS resource and a second CSI-RS resource; optionally, the first CSI-RS resource may be transmitted by the network device using a first beam, and the second CSI-RS resource may be transmitted by the network device using a second beam. Optionally, the first beam may be determined based on the first CSI, and the second beam may be determined based on the second CSI.

[0347] Optionally, the method for a network device to send at least one CSI-RS resource based on the first CSI and the second CSI may include the following steps:

[0348] Step 1: The network device determines recovery information based on the first CSI.

[0349] Regarding how the network device specifically determines the restoration information, reference may be made to the description in the above embodiment.

[0350] Step 2: The network device determines the precoding matrix V1 based on the recovered information.

[0351] Step 3: The network device determines a precoding vector based on the PMI in the second CSI, and determines a precoding matrix V2 based on the precoding vector.

[0352] Step 4: The network device sends a beamformed CSI-RS to the terminal through at least one CSI-RS resource based on the precoding matrix V1 and the precoding matrix V2.

[0353] Optionally, in some embodiments, the beamformed CSI-RS may be sent via a CSI-RS port, and the beam of the CSI-RS port may be v1,l or v 2,l , where v 1,l or v 2,l are the vectors corresponding to the lth column in the precoding matrix V1 and the precoding matrix V2 respectively. 1,l The CSI-RS resource sent by the beam (i.e. the aforementioned first beam) can be the aforementioned first CSI-RS resource, through v 2,l The CSI-RS resource sent by the beam (ie, the aforementioned second beam) may be the aforementioned second CSI-RS resource.

[0354] For example, assuming that the maximum transmission rank configured by the network device for the terminal is 2, then l = 2. At this time, the input information of the AI ​​model deployed on the terminal side should contain two vectors, assuming that they are v′ and 1,1 or v′ 1,2 , and the precoding matrix V1 and precoding matrix V2 determined by the network device also include two vectors respectively. Assume that the two vectors included in the precoding matrix V1 are v 1,1 and v 1,2 , the two vectors included in the precoding matrix V2 are v 2,1 and v 2,2 , the network device can use the obtained v 1,1 、v 1,2 、v 2,1 and v 2,2 Each is used as a 4-port CSI-RS beam and sent to the terminal using one or more CSI-RS resources. 1,1 、v 1,2 The CSI-RS resource sent by the beam (i.e. the aforementioned first beam) can be the aforementioned first CSI-RS resource, through v 2,1 、v 2,2 The CSI-RS resource sent by the beam (ie, the aforementioned second beam) may be the aforementioned second CSI-RS resource.

[0355] Optionally, in some embodiments, if the network device sends a beam-formed CSI-RS resource, the CSI-RS resource includes at least two CSI-RS ports, and the beams of some of the CSI-RS ports are predefined to correspond to the above-mentioned first CSI-RS resource, and the beams of the remaining CSI-RS ports correspond to the above-mentioned second CSI-RS resource.

[0356] Optionally, if the network device sends multiple beam-formed CSI-RS resources, the multiple CSI-RS resources can be sent in the same time domain unit (such as a symbol or time slot), and the CSI-RS resources corresponding to a part of the CSI-RS resource IDs can be predefined as the above-mentioned first CSI-RS resources, and the CSI-RS resources corresponding to the other part of the CSI-RS resource IDs can be predefined as the above-mentioned second CSI-RS resources.

[0357] Optionally, in some embodiments, if each CSI-RS resource is a plurality of CSI-RS ports, the beams of different CSI-RS ports may use the same or different beams.

[0358] Step 2308: The terminal determines a fifth monitoring value by measuring effective channel information of the first CSI-RS resource, and / or determines a sixth monitoring value by measuring effective channel information of the second CSI-RS resource.

[0359] Optionally, in some embodiments, the terminal may measure the effective channel information of the first CSI-RS resource and calculate the fifth monitoring value, and / or measure the effective channel information of the second CSI-RS resource and calculate the sixth monitoring value.

[0360] Optionally, in some embodiments, the terminal may first measure the effective channel information of the first CSI-RS resource, and perform calculation based on the measurement result to obtain the above-mentioned fifth monitoring value; and / or, the terminal may first measure the effective channel information of the second CSI-RS resource, and perform calculation based on the measurement result to obtain the above-mentioned sixth monitoring value.

[0361] Optionally, at least one of the fifth monitoring value and the sixth monitoring value is used to monitor the performance of the AI ​​model.

[0362] Optionally, in some embodiments, the fifth monitoring value and the sixth monitoring value may be at least one of throughput, BLER, assumed BLER, NACK, and ACK. Optionally, the fifth monitoring value and the sixth monitoring value may also be referred to as the final KPI. Optionally, the fifth monitoring value is the throughput, BLER, assumed BLER, NACK, ACK, and final KPI corresponding to the method of “CSI compression reporting and recovery based on bilateral AI model”, and the sixth monitoring value is the throughput, BLER, assumed BLER, NACK, ACK, and final KPI corresponding to the method of “CSI reporting based on codebook parameters”.

[0363] Step 2309: The terminal reports based on at least one of the fifth monitoring value and the sixth monitoring value.

[0364] Optionally, the terminal may report to the network device.

[0365] Optionally, in some embodiments, the terminal may directly report at least one of the fifth monitoring value and the sixth monitoring value; and / or, in other embodiments, the terminal may report a third calculated value obtained by calculating the fifth monitoring value and the sixth monitoring value using a third function. Optionally, the third function may be used to calculate a difference or ratio between the fifth monitoring value and the sixth monitoring value.

[0366] Optionally, the terminal may use the same CSI report to report at least one of the fifth monitoring value, the sixth monitoring value, and the third calculated value; or, may use different CSI reports to report at least one of the fifth monitoring value, the sixth monitoring value, and the third calculated value.

[0367] Optionally, in some embodiments, when at least one of the fifth monitoring value, the sixth monitoring value, and the third calculated value is reported using the same CSI report, a bit width for carrying at least one of the fifth monitoring value, the sixth monitoring value, and the third calculated value can be predefined.

[0368] Step 2310: The network device monitors the performance of the AI ​​model based on the terminal's report.

[0369] Optionally, the network device may perform performance monitoring on the AI ​​model based on at least one of the fifth monitoring value, the sixth monitoring value, and the third calculated value.

[0370] Optionally, the network device may monitor the performance of the AI ​​model by comparing the fifth monitoring value and the sixth monitoring value, or the network device may monitor the performance of the AI ​​model by comparing at least one of the fifth monitoring value, the sixth monitoring value, and the third calculated value with a preset threshold, but is not limited thereto.

[0371] The reporting method involved in the embodiment of the present disclosure may include at least one of steps S2301 to S2310. For example, step S2301 may be implemented as an independent embodiment, step S2302 may be implemented as an independent embodiment, and step S2303 may be implemented as an independent embodiment, but is not limited thereto.

[0372] Optionally, the above step 2306 is an optional step, which can be optionally executed or not executed.

[0373] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0374] FIG3A is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG3A , the present disclosure embodiment relates to a reporting method for terminal 101, the method comprising:

[0375] Step 3101: The terminal performs downlink channel estimation to obtain channel estimation information.

[0376] Step 3102: The terminal determines input information of the AI ​​model deployed on the terminal side based on the channel estimation information;

[0377] Step 3103: The terminal inputs the input information into the AI ​​model deployed on the terminal side to obtain the first CSI;

[0378] Step 3104: The terminal determines a second CSI based on the channel estimation information and the codebook parameters configured by the network device;

[0379] Step 3105: The terminal reports at least one of the first CSI and the second CSI;

[0380] Step 3106: The terminal reports at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information.

[0381] For a detailed description of steps 3101 - 3106 , please refer to the above embodiment description.

[0382] The reporting method involved in the embodiment of the present disclosure may include at least one of steps S3101 to S3106. For example, step S3101 may be implemented as an independent embodiment, and step S3102 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0383] Optionally, the above step 3106 may be an optional step and may be performed optionally, for example, may be performed or not performed.

[0384] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0385] FIG3B is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG3B , the present disclosure embodiment relates to a reporting method for terminal 101, the method comprising:

[0386] Step 3201: The terminal performs downlink channel estimation to obtain channel estimation information.

[0387] Step 3202: The terminal determines input information of the AI ​​model deployed on the terminal side based on the channel estimation information;

[0388] Step 3203: The terminal inputs the input information into the AI ​​model deployed on the terminal side to obtain the first CSI;

[0389] Step 3204: The terminal determines a second CSI based on the channel estimation information and the codebook parameters configured by the network device;

[0390] Step 3205: The terminal reports at least one of the first CSI and the second CSI;

[0391] Step 3206: The terminal reports at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information.

[0392] Step 3207: The terminal receives the recovery information.

[0393] Step 3208: The terminal determines at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value.

[0394] Step 3209: The terminal reports based on at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value.

[0395] For a detailed description of steps 3201 - 3209 , please refer to the above embodiment description.

[0396] The reporting method involved in the embodiment of the present disclosure may include at least one of steps S3201 to S3209. For example, step S3201 may be implemented as an independent embodiment, and step S3202 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0397] Optionally, the above step 3206 may be an optional step and may be performed optionally, for example, may be performed or not performed.

[0398] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0399] FIG3C is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG3C , the present disclosure embodiment relates to a reporting method for terminal 101, the method comprising:

[0400] Step 3301: The terminal performs downlink channel estimation to obtain channel estimation information.

[0401] Step 3302: The terminal determines input information of the AI ​​model deployed on the terminal side based on the channel estimation information;

[0402] Step 3303: The terminal inputs the input information into the AI ​​model deployed on the terminal side to obtain the first CSI;

[0403] Step 3304: The terminal determines a second CSI based on the channel estimation information and the codebook parameters configured by the network device.

[0404] Step 3305: The terminal reports at least one of the first CSI and the second CSI;

[0405] Step 3306: The terminal reports at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained after preprocessing of the channel estimation information, and the angle and delay domain information obtained after preprocessing of the channel estimation information.

[0406] Step 3307: The terminal receives at least one CSI-RS resource.

[0407] Step 3308: The terminal determines a fifth monitoring value by measuring effective channel information of the first CSI-RS resource, and / or determines a sixth monitoring value by measuring effective channel information of the second CSI-RS resource.

[0408] Step 3309: The terminal reports based on at least one of the fifth monitoring value and the sixth monitoring value.

[0409] For a detailed description of steps 3301 - 3309 , please refer to the above embodiment description.

[0410] The reporting method involved in the embodiment of the present disclosure may include at least one of steps S3301 to S3309. For example, step S3301 may be implemented as an independent embodiment, and step S3302 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0411] Optionally, the above step 3306 may be an optional step and may be performed optionally, for example, it may be performed or not performed.

[0412] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0413] FIG3D is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG3D , the present disclosure embodiment relates to a reporting method for terminal 101, the method comprising:

[0414] Step 3401: The terminal reports at least one of the first CSI and the second CSI to the network device.

[0415] Optionally, the first CSI is determined based on the artificial intelligence AI model deployed on the terminal side, the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to monitor the performance of the AI ​​model.

[0416] Optionally, before the terminal reports at least one of the first CSI and the second CSI to the network device, the method further includes at least one of the following:

[0417] Performing downlink channel estimation to obtain channel estimation information;

[0418] Determining input information of an AI model deployed on the terminal side based on the channel estimation information, and inputting the input information into the AI ​​model deployed on the terminal side to obtain the first CSI;

[0419] The second CSI is determined based on the channel estimation information and a codebook parameter configured by the network device.

[0420] Optionally, the input information of the AI ​​model includes at least one of the following:

[0421] channel estimation information;

[0422] Angle domain information obtained by preprocessing the channel estimation information;

[0423] Angle and delay domain information obtained by preprocessing the channel estimation information;

[0424] The eigenvector corresponding to the channel estimation information.

[0425] Optionally, the first CSI and the second CSI are included in a first CSI report.

[0426] Optionally, the method further includes:

[0427] If the input information of the AI ​​model deployed on the terminal side is angle domain information or angle and delay domain information, determine at least one first spatial domain basis vector and / or at least one first frequency domain basis vector used when calculating the first CSI, and determine at least one second spatial domain basis vector and / or at least two second frequency domain basis vectors used when calculating the second CSI;

[0428] Determine indication information based on at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector, where the indication information is used to indicate at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector;

[0429] The indication information is included in the first CSI report.

[0430] Optionally, the determining the indication information based on at least one of the first spatial basis vector, the first frequency domain basis vector, the second spatial basis vector, and the second frequency domain basis vector includes at least one of the following:

[0431] If the first spatial domain basis vector is the same as the second spatial domain basis vector, and / or the first frequency domain basis vector is the same as the second frequency domain basis vector, determining a first indication, where the first indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector; or, the first indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector;

[0432] If the at least one second spatial domain basis vector is a proper subset of the at least one first spatial domain basis vector, and / or the at least one second frequency domain basis vector is a proper subset of the at least one first frequency domain basis vector, determining a second indication and a third indication, wherein the second indication is used to indicate the at least one first spatial domain basis vector and / or the at least one first frequency domain basis vector, and the third indication is used to indicate the at least one second spatial domain basis vector in the at least one first spatial domain basis vector, and / or, to indicate the at least one second frequency domain basis vector in the at least one first frequency domain basis vector;

[0433] If the at least one second spatial domain basis vector is not a proper subset of the at least one first spatial domain basis vector, and the first spatial domain basis vector is different from the second spatial domain basis vector, and / or if the at least one second frequency domain basis vector is not a proper subset of the at least one first frequency domain basis vector, and the first frequency domain basis vector is different from the second frequency domain basis vector, determine a fourth indication and a fifth indication, the fourth indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector, and the fifth indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector.

[0434] Optionally, the first CSI is included in a second CSI report, and the second CSI is included in a third CSI report; the second CSI report and the third CSI report are associated with the same CSI-RS resource.

[0435] Optionally, the first CSI also includes at least one of the combination coefficient information corresponding to the first spatial basis vector and the combination coefficient information of the first frequency domain basis vector; the second CSI also includes at least one of the combination coefficient information corresponding to the second spatial basis vector and the combination coefficient information of the second frequency domain basis vector.

[0436] Optionally, an absolute value of a reporting overhead difference between the second CSI report and the third CSI report is less than a first threshold.

[0437] Optionally, the method further includes:

[0438] Reporting to the network device at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information; wherein, at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information is included in the first CSI report, or included in the second CSI report, or included in the third CSI report, or included in a fourth CSI report different from the first CSI report, the second CSI report, and the third CSI report;

[0439] The first CSI report and the fourth CSI report are associated with the same CSI-RS resource, or the second CSI report, the third CSI report, and the fourth CSI report are associated with the same CSI-RS resource.

[0440] Optionally, the method further includes:

[0441] In response to the input information of the AI ​​model deployed on the terminal side being the same as the precoding vector determined by the precoding matrix index PMI in the second CSI, at least one of the input information of the AI ​​model, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information is not reported.

[0442] Optionally, after reporting at least one of the first CSI and the second CSI to the network device, the method further includes at least one of the following:

[0443] receiving recovery information sent by the network device, where the recovery information is information output by the AI ​​model deployed on the network device side based on the first CSI;

[0444] In response to the input information of the AI ​​model being a feature vector corresponding to the channel estimation information, determining a first monitoring value based on the recovered information and the input information of the AI ​​model deployed on the terminal side;

[0445] determining a second monitoring value based on the recovery information;

[0446] determining a precoding vector based on the PMI in the second CSI;

[0447] In response to the input information of the AI ​​model being a feature vector corresponding to the channel estimation information, determining a third monitoring value based on the precoding vector and the input information of the AI ​​model deployed on the terminal side;

[0448] determining a fourth monitoring value based on the precoding vector;

[0449] Report at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value to the network device, wherein at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is used to perform performance monitoring on the AI ​​model.

[0450] Optionally, at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is reported using the same CSI report; or, at least one of the first monitoring value and the second monitoring value is reported using the fifth CSI report, and at least one of the third monitoring value and the fourth monitoring value is reported using the sixth CSI report.

[0451] Optionally, after reporting at least one of the first CSI and the second CSI to the network device, the method further includes at least one of the following:

[0452] receiving at least one CSI-RS resource sent by the network device, where the at least one CSI-RS resource includes at least one of a first CSI-RS resource and a second CSI-RS resource; wherein the first CSI-RS resource is sent by the network device using a first beam, the first beam is determined based on the first CSI, and the second CSI-RS resource is sent by the network device using a second beam, the second beam is determined based on the second CSI;

[0453] Determine a fifth monitoring value by measuring effective channel information of the first CSI-RS resource;

[0454] Determine a sixth monitoring value by measuring effective channel information of the second CSI-RS resource;

[0455] Report at least one of the fifth monitoring value and the sixth monitoring value to the network device, wherein at least one of the fifth monitoring value and the sixth monitoring value is used to perform performance monitoring on the AI ​​model.

[0456] Optionally, at least one of the fifth monitoring value and the sixth monitoring value is reported using the same CSI report; or, the fifth monitoring value and the sixth monitoring value are reported using different CSI reports.

[0457] For a detailed description of step 3401, please refer to the above embodiment description.

[0458] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0459] FIG4A is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG4A , the present disclosure embodiment relates to a reporting method for a network device 102, the method comprising:

[0460] Step 4101: The network device receives at least one of the first CSI and the second CSI.

[0461] Step 4102: The network device receives at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, feature vectors corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information.

[0462] Step 4103: The network device performs performance monitoring based on at least one of the first CSI and the second CSI.

[0463] For a detailed description of steps 4101-4103, please refer to the above embodiment description.

[0464] The reporting method involved in the embodiment of the present disclosure may include at least one of steps S4101 and S4102. For example, step S4101 may be implemented as an independent embodiment, and step S4102 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0465] Optionally, the above step 4102 may be an optional step and may be performed optionally, for example, it may be performed or not performed.

[0466] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0467] FIG4B is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG4B , the present disclosure embodiment relates to a reporting method for a network device 102, the method comprising:

[0468] Step 4201: The network device receives at least one of the first CSI and the second CSI.

[0469] Step 4202: The network device receives at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, feature vectors corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information.

[0470] Step 4203: The network device determines recovery information based on the first CSI.

[0471] Step 4204: The network device sends the recovery information.

[0472] Step 4205: The network device receives the report from the terminal.

[0473] Optionally, in some embodiments, the network device may be a receiving terminal that reports based on at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value.

[0474] Step 4206: The network device monitors the performance of the AI ​​model based on the terminal's report.

[0475] For a detailed description of steps 4201-4206, please refer to the above embodiment description.

[0476] The reporting method involved in the embodiment of the present disclosure may include at least one of steps S4201 to S4206. For example, step S4201 may be implemented as an independent embodiment, and step S4202 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0477] Optionally, the above step 4202 may be an optional step and may be performed optionally, for example, may be performed or not performed.

[0478] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0479] FIG4C is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG4C , the present disclosure embodiment relates to a reporting method for a network device 102, the method comprising:

[0480] Step 4301: The network device receives at least one of the first CSI and the second CSI.

[0481] Step 4302: The network device receives at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, feature vectors corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information.

[0482] Step 4303: The network device sends at least one CSI-RS resource based on the first CSI and / or the second CSI.

[0483] Step 4304: The network device receives the report from the terminal.

[0484] Optionally, in some embodiments, the network device may receive a report from the terminal based on at least one of the fifth monitoring value and the sixth monitoring value.

[0485] Step 4305: The network device monitors the performance of the AI ​​model based on the terminal's report.

[0486] For a detailed description of steps 4301-4305, please refer to the above embodiment description.

[0487] The reporting method involved in the embodiment of the present disclosure may include at least one of steps S4301 to S4305. For example, step S4301 may be implemented as an independent embodiment, and step S4302 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0488] Optionally, the above step 4302 may be an optional step and may be performed optionally, for example, it may be performed or not performed.

[0489] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0490] FIG4D is an interactive diagram of a reporting method according to an embodiment of the present disclosure. As shown in FIG4D , the present disclosure embodiment relates to a reporting method for a network device 102, the method comprising:

[0491] Step 4401: The network device receives at least one of the first CSI and the second CSI reported by the terminal.

[0492] Optionally, the input information of the AI ​​model includes at least one of the following:

[0493] channel estimation information;

[0494] Angle domain information obtained by preprocessing the channel estimation information;

[0495] Angle and delay domain information obtained by preprocessing the channel estimation information;

[0496] The eigenvector corresponding to the channel estimation information.

[0497] Optionally, the first CSI and the second CSI are included in a first CSI report.

[0498] Optionally, the first CSI report includes a first indication, where the first indication is used to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector used when calculating the first CSI, or the first indication is used to indicate at least one second spatial basis vector and / or at least one second frequency domain basis vector used when calculating the second CSI, wherein the first spatial basis vector is the same as the second spatial basis vector, and / or the first frequency domain basis vector is the same as the second frequency domain basis vector; or

[0499] The first CSI report includes a second indication and a third indication, wherein the second indication is used to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector, and the third indication is used to indicate at least one second spatial basis vector in the at least one first spatial basis vector and / or to indicate at least one second frequency domain basis vector in the at least one first frequency domain basis vector; or

[0500] The first CSI report includes a fourth indication and a fifth indication, the fourth indication is used to indicate at least one first spatial basis vector and / or at least one first frequency domain basis vector, and the fifth indication is used to indicate at least one second spatial basis vector and / or at least one second frequency domain basis vector.

[0501] Optionally, the first CSI is included in a second CSI report, and the second CSI is included in a third CSI report; the second CSI report and the third CSI report are associated with the same CSI-RS resource.

[0502] Optionally, the first CSI also includes at least one of the combination coefficient information corresponding to the first spatial basis vector and the combination coefficient information of the first frequency domain basis vector; the second CSI also includes at least one of the combination coefficient information corresponding to the second spatial basis vector and the combination coefficient information of the second frequency domain basis vector.

[0503] Optionally, an absolute value of a reporting overhead difference between the second CSI report and the third CSI report is less than a first threshold.

[0504] Optionally, the method further includes:

[0505] Receiving at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, a feature vector corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information, reported by the terminal; wherein at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the feature vector corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information is included in the first CSI report, or included in the second CSI report, or included in the third CSI report, or included in a fourth CSI report different from the first CSI report, the second CSI report, and the third CSI report;

[0506] The first CSI report and the fourth CSI report are associated with the same CSI-RS resource, or the second CSI report, the third CSI report, and the fourth CSI report are associated with the same CSI-RS resource.

[0507] Optionally, the method further includes:

[0508] Determine recovery information based on the first CSI using the AI ​​model deployed on the network device side;

[0509] sending the restoration information to the terminal;

[0510] Receive at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value reported by the terminal; wherein, at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is used to perform performance monitoring on the AI ​​model.

[0511] Optionally, at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is included in the same CSI report; or, at least one of the first monitoring value and the second monitoring value is included in the fifth CSI report, and at least one of the third monitoring value and the fourth monitoring value is included in the sixth CSI report.

[0512] Optionally, the method further includes:

[0513] Sending at least one CSI-RS resource to the terminal based on the first CSI and / or the second CSI, where the at least one CSI-RS resource includes at least one of a first CSI-RS resource and a second CSI-RS resource; wherein the first CSI-RS resource is sent by the network device using a first beam, and the first beam is determined based on the first CSI; and the second CSI-RS resource is sent by the network device using a second beam, and the second beam is determined based on the second CSI;

[0514] Receive at least one of the fifth monitoring value and the sixth monitoring value reported by the terminal; wherein, at least one of the fifth monitoring value and the sixth monitoring value is used to perform performance monitoring on the AI ​​model.

[0515] Optionally, at least one of the fifth monitoring value and the sixth monitoring value is included in the same CSI report; or, the fifth monitoring value and the sixth monitoring value are respectively included in different CSI reports.

[0516] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0517] FIG5A is a flow chart of a reporting method according to an embodiment of the present disclosure. As shown in FIG5A , an embodiment of the present disclosure relates to a reporting method for a communication system, wherein the method includes at least one of the following:

[0518] Step 5101: The terminal reports at least one of first channel state information (CSI) and second CSI to a network device; wherein the first CSI is determined based on an artificial intelligence (AI) model deployed on the terminal side, and the second CSI is determined based on a codebook parameter configured by the network device, and the first CSI and / or the second CSI is used to monitor the performance of the AI ​​model.

[0519] Step 5102: The network device receives at least one of the first CSI and the second CSI reported by the terminal;

[0520] Step 5103: The network device performs performance monitoring on the AI ​​model based on at least one of the first CSI and the second CSI.

[0521] Optional implementations of steps 5101 to 5103 may refer to the description of the above embodiment.

[0522] In some embodiments, the above method may include the methods of the above embodiments of the communication system side, terminal side, network terminal side, etc., which will not be repeated here.

[0523] The reporting method involved in the embodiment of the present disclosure may include at least one of steps S5101 to S5103. For example, step S5101 may be implemented as an independent embodiment, and step S5102 may be implemented as an independent embodiment, but the present invention is not limited thereto.

[0524] In this embodiment or example, unless there is any contradiction, each step can be independent, arbitrarily combined or exchanged in order, the optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other embodiments or other examples.

[0525] The following is an exemplary introduction to the above method.

[0526] The present disclosure provides a certain correlation and correspondence between AI-based CSI feedback and existing CSI feedback when reporting, so that the network side can accurately monitor AI / ML performance when using the CSI obtained by the existing CSI feedback method as a reference.

[0527] 2.2 The complete content of the disclosed technical solution

[0528] When the network monitors the performance of AI / ML models and uses the CSI feedback from existing CSI methods as a performance reference, the CSI reporting methods based on AI CSI feedback and existing CSI feedback methods are as follows:

[0529] Alt1:

[0530] By including CSI feedback based on the AI / ML method and CSI feedback of the existing solution in one CSI report, the SD basis / FD basis reporting is indicated according to the following method, and the remaining information can be reported independently.

[0531] Alt1-1: If the AI / ML model input information of the AI / ML-based CSI feedback method is angle delay domain information, only one SD basis and / or FD basis indication information I1 is reported.

[0532] Alt1-2: The SD basis and / or FD basis included in the existing CSI feedback is determined by indication information I2, where I2 is determined based on indication information I1. For example, the SD basis and / or FD basis determined by I1 is used as candidate bases, and then all or part of the bases are selected from the candidate bases and indicated through indication information I2. I1 is the SD basis and / or FD basis used by the AI / ML-based CSI feedback method indicated in Alt1-1 above.

[0533] Alt2: CSI feedback based on the AI / ML method and CSI feedback based on the existing solution are reported through CSI report 1 and CSI report 2, respectively. The two CSI reports are associated with the same CSI-RS resource. Among them, the CSI feedback overhead in CSI report 1 after compression by the AI / ML model of the CSI generation part should be equal to or equivalent to the CSI feedback overhead in CSI report 2. The so-called equivalent means that the difference in feedback overhead between the two is limited to a certain range R. The range value can be determined by predefinition, network configuration reporting, or UE reporting.

[0534] For Alt1 and Alt2, the UE optionally also reports the input information of the CSI generation model, or the UE-estimated downlink channel information, or the eigenvector corresponding to the downlink channel information, to the gNB. This input information can be included in Alt1 and reported together, or reported independently in CSI report 3. If the input information of the CSI generation model is the same as the precoding vector determined by the PMI included in the existing CSI feedback report CSI, CSI report 3 does not need to be reported.

[0535] Alt3: The UE calculates the intermediate KPI or final KPI as K1 or E1 based on the AI / ML method, and calculates the intermediate KPI as K2 or E2 based on the existing CSI feedback solution. In a CSI report, K1 or E1 is placed in part of the bit width of the CSI report according to a predefined method, and K2 or E2 is placed in another part of the bit width. Optionally, the method described in Alt2 above is used to report K1 or E1 and K2 or E2 in different CSI reports.

[0536] Alt4: The gNB receives the precoding matrix V2 determined by the compressed information based on the CSI generation model and the precoding indication information contained in the CSI reported by the existing CSI feedback method according to Alt1 or Alt2. Then, the gNB determines the precoding matrix V1 based on the CSI recovered by the CSI recovery model. Finally, the gNB sends the beamformed CSI-RS to the UE using one or two CSI-RS resources. The beam of the CSI-RS port is v 1,l or v 2,l , where v 1,l or v 2,l These are the vectors corresponding to the lth column in V1 and V2, respectively, i.e., the precoding vectors for layer l. Based on the received beamformed CSI-RS, the UE calculates the final KPI values ​​E1 and E2. E1 and E2 represent the final KPIs corresponding to using V1 and V2 as the CSI-RS beams, respectively. The UE sends E1 and E2 to the gNB using the method described in Alt3.

[0537] If only one beam-formed CSI-RS resource is sent, one CSI-RS resource refers to a CSI-RS port including at least two ports, and the beams of some CSI-RS ports are predefined as beams obtained based on the AI / ML model method, and the beams of the remaining CSI-RS ports are beams determined based on the existing CSI method.

[0538] If multiple beamformed CSI-RS resources are to be transmitted in the same time slot, the CSI-RS resource ID determines which CSI-RS resources use the beams derived using the AI / ML model method. The remaining CSI-RS resources use beams determined using existing CSI methods. If each CSI-RS resource has multiple CSI-RS ports, the beams of different CSI-RS ports can use the same or different beams.

[0539] Alt5: If the UE has multiple CSI generation models with different compressed information feedback payload sizes, and the gNB also configures the UE with a CSI generation model based on existing CSI feedback method parameter information and codebook type, the UE determines the feedback CSI payload size L1 based on the codebook parameter information. When used for network monitoring, the UE selects an AI / ML model corresponding to a CSI generation model where the CSI payload size L2 determined by the CSI generation model is not greater than L1, or where the absolute value of the difference between L2 and L1 is minimized. Optionally, the gNB configures the UE with an AI / ML model based on existing CSI feedback method parameter information such that the CSI payload size L1 determined by the parameter information is equal to L1, or where the absolute value of the difference between L2 and L1 is minimized, when inference is performed with the CSI generation model currently in use by the UE.

[0540] Note: The above comparison of the CSI load size between the AI-based CSI feedback load and the CSI load size based on the existing CSI feedback method is under the same transmission rank condition.

[0541] Alternatively, in addition to directly reporting intermediate or final KPI values, a function f(K1, K2) or f(E1, E2) can be defined to report these values ​​to the gNB. This function can be defined as the difference or ratio of the intermediate or final KPIs. When the corresponding transmission rank is greater than 1, the two methods are compared based on the same transmission layer.

[0542] Example 1 (Alt1):

[0543] The UE estimates the downlink channel information of different frequency domain units based on the downlink reference signal, and then calculates L SD basis and M FD basis based on the existing CSI feedback method such as the Rel-16 Type II codebook method. Each basis can be represented by an eigenvector or a DFT vector. The M FD basis can be an independent FD basis for each transmission layer or the same FD basis for all transmission layers. The input information of the CSI generation model is defined as Input-CSI-UE. Input-CSI-UE is W determined based on the Rel-16 Type II codebook algorithm. W can be written as

[0544] Among them, W1 consists of L SD basis, W f It consists of M FD basis layers, and W2 is the combined coefficient corresponding to the SD basis and FD basis layers. Accordingly, W can be the precoding vector information corresponding to each layer or the downlink channel vector information corresponding to different receive antennas. The angle delay domain channel information is obtained by performing a DFT transformation on the downlink space-frequency domain channel information using L SD basis layers and M FD basis layers.

[0545] Based on AI CSI feedback, the network side needs to obtain the above-mentioned Input-CSI-UE in order to monitor the model performance. Therefore, the UE needs to report L SD basis and M FD basis indication information. When the L SD basis and M FD basis reported by the UE are exactly the same as the SD basis and FD basis that need to be reported when the Rel-16 Type II codebook is fed back, at this time, only one SD basis and FD basis indication information I1 needs to be reported. Therefore, the SD basis / FD basis indication feedback overhead based on the Rel-16 Type II codebook feedback can be reduced. Optionally,

[0546] When L1 < L SD bases and M1 < M FD bases are reported based on the Rel-16 Type II codebook, in this case, in addition to reporting the indication information I1 of L SD bases and M FD bases, the indication information I2 of L1 SD bases and M1 FD bases also needs to be reported. To reduce the feedback overhead of the UE, the UE only selects L1 SD bases from L SD bases instead of from all candidate L’ (L’ > L) SD bases. Similarly, the UE selects M1 FD bases from M FD bases. Because when selecting L SD bases and M FD bases, the main SD bases / FD bases have already been selected. Therefore, even if L1 / M1 SD bases / FD bases are selected from this part of the bases, there will be no performance degradation.

[0547] Embodiment 2 (Alt2):

[0548] The gNB configures 3 CSI reportings for the UE, and these three CSI reportings are associated with the same CSI-RS resource ID1. The UE estimates the downlink channel based on the received CSI-RS resource ID1, and then calculates the reported CSI based on the AI-based CSI feedback method and the existing CSI method respectively. The reported CSI is included in CSI reporting 1 and CSI reporting 2 respectively. Among them, the existing CSI method is determined based on the codebook parameters and codebook type configured by the gNB. When there are multiple AI / ML models deployed on the UE or gNB side used in the AI-based CSI feedback, the AI / ML model used during inference can be determined according to the gNB configuration or UE selection.

[0549] Assume that the gNB calculates the corresponding SGCS by using the CSI reported based on the AI-based CSI feedback and the existing CSI feedback method received respectively. Calculating the SGCS requires the UE to report the Input-CSI-UE described in Embodiment 1. The Input-CSI-UE can be sent to the gNB through CSI reporting 3, but the Input-CSI-UE is also determined based on the same CSI-RS resource ID1. Therefore, CSI reporting 3 also needs to be associated with the CSI-RS resource ID1. Optionally, FIG. 5B shows the association relationship between CSI reporting 1 (i.e., the aforementioned second CSI report), CSI reporting 2 (i.e., the aforementioned third CSI report), CSI reporting 3 (i.e., the aforementioned fourth CSI report) and the CSI-RS resource ID1 provided by an embodiment of the present disclosure.

[0550] Assume that the AI-based CSI feedback payload is L1, and the existing CSI feedback payload is L2. To ensure fairness between the two feedback methods, the sizes of L1 and L2 can be equal, or the difference between them can be minimal, ensuring that the payload sizes are equal. One approach is to ensure that the difference between L2-L1 or L1-L2 is less than R. For example, R = 5 bits or 10 bits. The value of R can be configured to the UE by the gNB through RRC signaling.

[0551] Example 3 (Alt4):

[0552] Assume that Input-CSI-UE is the eigenvector of each frequency domain unit and the gNB configures the UE with a maximum transmission rank of 2. The AI-based CSI feedback method inputs the model of the CSI generation part Input-CSI-UE as two eigenvectors corresponding to different frequency domain units. Without loss of generality, define the eigenvector as v′ 1,1 or v′ 1,2 , where the index information of the frequency domain unit is omitted. Accordingly, the CSI recovery model can output two decompressed feature vectors v corresponding to different frequency domain units 1,1 and v 1,2 If the existing CSI feedback method is used, such as Rel-16 Type II codebook feedback, the UE can send the precoding matrix indication information to the gNB according to the configured codebook parameter combination. The gNB determines the two precoding vectors v with a transmission rank of 2 based on the indication information. 2,1 and v 2,2 .

[0553] gNB uses the obtained v 1,1 、v 1,2 、v 2,1 and v 2,2 Each of them is used as a 4-port CSI-RS beam. The UE estimates the effective channel information corresponding to the port based on the received beamformed CSI-RS and calculates the throughput E1 corresponding to the AI-based CSI feedback and the throughput E2 corresponding to the existing CSI feedback method. The UE reports the values ​​of E1 and E2 to the gNB, or reports the difference or ratio between the two to the gNB. Alternatively, the method described in Alt3 is used, through a CSI reporting report, and E1 and E2 are respectively indicated to the gNB by two indication messages of a certain bit width length. Optionally,

[0554] The gNB configures two CSI-RS resources for the UE and transmits beamformed CSI-RS to the UE using precoding vectors obtained using different methods. These two CSI-RS resources must be transmitted in the same time slot.

[0555] The proposed CSI reporting display indication and parameter information method implicitly indicates the relationship between AI / ML-based CSI feedback and existing CSI feedback solutions, ensuring reliable AI / ML model performance monitoring when the network side uses the existing CSI feedback solution as a reference.

[0556] The embodiments of the present disclosure further provide an apparatus for implementing any of the above methods. For example, an apparatus is provided, comprising units or modules for implementing each step performed by a terminal in any of the above methods. For another example, another apparatus is provided, comprising units or modules for implementing each step performed by a network device (e.g., an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0557] It should be understood that the division of the various units or modules in the above device is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a physical entity, or they may be physically separated. In addition, the units or modules in the device may be implemented in the form of a processor calling software: for example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or implement the functions of the various units or modules of the above device, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the device or a memory outside the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units or modules can be realized by designing the hardware circuits. The above-mentioned hardware circuits can be understood as one or more processors; for example, in one implementation, the above-mentioned hardware circuit is an application-specific integrated circuit (ASIC), which realizes the functions of some or all of the above units or modules by designing the logical relationship of the components in the circuit; for example, in another implementation, the above-mentioned hardware circuit can be realized by a programmable logic device (PLD). Taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by configuring the configuration file, thereby realizing the functions of some or all of the above units or modules. All units or modules of the above devices can be realized in the form of software called by the processor, or in the form of hardware circuits, or in part by the form of software called by the processor, and the rest by hardware circuits.

[0558] In the embodiments of the present disclosure, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationship of the hardware circuit. The logical relationship of the above-mentioned hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and implementing the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0559] Figure 6A is a structural diagram of the terminal proposed in an embodiment of the present disclosure. As shown in Figure 6A, it includes: a sending module, which is used for the terminal to report at least one of the first channel state information CSI and the second CSI to the network device; wherein, the first CSI is determined based on the AI ​​model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to monitor the performance of the AI ​​model. Optionally, the above-mentioned sending module is used to execute the steps related to "sending" performed in any of the above methods, and optionally, it also includes at least one of a processing module and a receiving module. The above-mentioned processing module is used to execute the steps related to "processing" performed in any of the above methods, and the above-mentioned receiving module is used to execute the steps related to receiving performed in any of the above methods, which will not be repeated here.

[0560] Figure 6B is a structural diagram of the network device proposed in an embodiment of the present disclosure. As shown in Figure 6B, it includes: a receiving module, which is used for the network device to receive at least one of the first CSI and the second CSI reported by the terminal; wherein, the first CSI is determined based on the AI ​​model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to monitor the performance of the AI ​​model. Optionally, the above-mentioned receiving module is used to execute the steps related to "receiving" performed in any of the above methods, and optionally, it also includes at least one of a processing module and a sending module. The above-mentioned processing module is used to execute the steps related to "processing" performed in any of the above methods, and the above-mentioned sending module is used to execute the steps related to sending performed in any of the above methods, which will not be repeated here.

[0561] Figure 7A is a schematic diagram of the structure of a communication device 7100 proposed in an embodiment of the present disclosure. Communication device 7100 can be a network device (e.g., an access network device, a core network device, etc.), a terminal (e.g., a user equipment, etc.), a chip, a chip system, or a processor that supports a network device to implement any of the above methods, or a chip, a chip system, or a processor that supports a terminal to implement any of the above methods. Communication device 7100 can be used to implement the methods described in the above method embodiments. For details, please refer to the description of the above method embodiments.

[0562] As shown in Figure 7A, the communication device 7100 includes one or more processors 7101. The processor 7101 can be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device (such as a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process program data. The processor 7101 is used to call instructions to enable the communication device 7100 to perform any of the above methods.

[0563] In some embodiments, the communication device 7100 further includes one or more memories 7102 for storing instructions. Optionally, all or part of the memories 7102 may be located outside the communication device 7100.

[0564] In some embodiments, the communication device 7100 further includes one or more transceivers 7103. When the communication device 7100 includes one or more transceivers 7103, the communication steps such as sending and receiving in the above method are performed by the transceiver 7103, and the other steps are performed by the processor 7101.

[0565] In some embodiments, a transceiver may include a receiver and a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, and transceiver circuit may be used interchangeably; the terms transmitter, transmitting unit, transmitter, and transmitting circuit may be used interchangeably; and the terms receiver, receiving unit, receiver, and receiving circuit may be used interchangeably.

[0566] Optionally, the communication device 7100 further includes one or more interface circuits 7104, which are connected to the memory 7102. The interface circuits 7104 may be configured to receive signals from the memory 7102 or other devices, and may be configured to send signals to the memory 7102 or other devices. For example, the interface circuits 7104 may read instructions stored in the memory 7102 and send the instructions to the processor 7101.

[0567] The communication device 7100 described in the above embodiment may be a network device or a terminal, but the scope of the communication device 7100 described in the present disclosure is not limited thereto, and the structure of the communication device 7100 may not be limited by FIG. 7a. The communication device may be an independent device or may be part of a larger device. For example, the communication device may be: 1) an independent integrated circuit IC, or a chip, or a chip system or subsystem; (2) a collection of one or more ICs, optionally, the above IC collection may also include a storage component for storing data or programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, an intelligent terminal device, a cellular phone, a wireless device, a handheld device, a mobile unit, an in-vehicle device, a network device, a cloud device, an artificial intelligence device, etc.; (6) others, etc.

[0568] 7B is a schematic diagram of the structure of a chip 7200 proposed in an embodiment of the present disclosure. If the communication device 7100 can be a chip or a chip system, please refer to the schematic diagram of the structure of the chip 7200 shown in FIG7B , but the present disclosure is not limited thereto.

[0569] The chip 7200 includes one or more processors 7201 , and the processor 7201 is used to call instructions so that the chip 7200 executes any of the above methods.

[0570] In some embodiments, chip 7200 further includes one or more interface circuits 7202, which are connected to memory 7203. Interface circuit 7202 can be used to receive signals from memory 7203 or other devices, and can be used to send signals to memory 7203 or other devices. For example, interface circuit 7202 can read instructions stored in memory 7203 and send the instructions to processor 7201. Optionally, the terms interface circuit, interface, transceiver pin, and transceiver are interchangeable.

[0571] In some embodiments, the chip 7200 further includes one or more memories 7203 for storing instructions. Alternatively, all or part of the memories 7203 may be located outside the chip 7200.

[0572] The present disclosure also proposes a storage medium having instructions stored thereon. When the instructions are executed on the communication device 7100, the communication device 7100 executes any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto and may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto and may also be a temporary storage medium.

[0573] The present disclosure also provides a program product, which, when executed by the communication device 7100, enables the communication device 7100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0574] The present disclosure also proposes a computer program, which, when executed on a computer, causes the computer to perform any one of the above methods.

[0575] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0576] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and 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 this disclosure.

[0577] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0578] The above description is merely a specific embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A reporting method, characterized in that: The method comprises: The terminal reports at least one of the first channel state information CSI and the second CSI to the network device; wherein the first CSI is determined based on the artificial intelligence AI model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to perform performance monitoring on the AI ​​model.

2. The method according to claim 1, characterized in that Before the terminal reports at least one of the first CSI and the second CSI to the network device, the method further includes at least one of the following: Performing downlink channel estimation to obtain channel estimation information; Determine input information of an AI model deployed on the terminal side based on the channel estimation information, and input the input information into the AI ​​model deployed on the terminal side to obtain the first CSI; The second CSI is determined based on the channel estimation information and a codebook parameter configured by the network device.

3. The method according to claim 1 or 2, characterized in that The input information of the AI ​​model includes at least one of the following: channel estimation information; Angle domain information obtained by preprocessing the channel estimation information; The angle and delay domain information obtained by preprocessing the channel estimation information; The eigenvector corresponding to the channel estimation information.

4. The method according to any one of claims 1 to 3, characterized in that: The first CSI and the second CSI are included in a first CSI report.

5. The method according to claim 4, characterized in that The method further comprises: If the input information of the AI ​​model deployed on the terminal side is angle domain information or angle and delay domain information, determine at least one first spatial domain basis vector and / or at least one first frequency domain basis vector used when calculating the first CSI, and determine at least one second spatial domain basis vector and / or at least two second frequency domain basis vectors used when calculating the second CSI; Determine indication information based on at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector, wherein the indication information is used to indicate at least one of the first spatial domain basis vector, the first frequency domain basis vector, the second spatial domain basis vector, and the second frequency domain basis vector; The indication information is included in the first CSI report.

6. The method according to claim 5, characterized in that The determining of the indication information based on at least one of the first spatial basis vector, the first frequency domain basis vector, the second spatial basis vector, and the second frequency domain basis vector comprises at least one of the following: If the first spatial domain basis vector is the same as the second spatial domain basis vector, and / or the first frequency domain basis vector is the same as the second frequency domain basis vector, determine a first indication, wherein the first indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector; or, the first indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector; If the at least one second spatial domain basis vector is a proper subset of the at least one first spatial domain basis vector, and / or the at least one second frequency domain basis vector is a proper subset of the at least one first frequency domain basis vector, determine a second indication and a third indication, wherein the second indication is used to indicate the at least one first spatial domain basis vector and / or the at least one first frequency domain basis vector, and the third indication is used to indicate the at least one second spatial domain basis vector in the at least one first spatial domain basis vector, and / or, to indicate the at least one second frequency domain basis vector in the at least one first frequency domain basis vector; If the at least one second spatial domain basis vector is not a proper subset of the at least one first spatial domain basis vector, and the first spatial domain basis vector is different from the second spatial domain basis vector, and / or if the at least one second frequency domain basis vector is not a proper subset of the at least one first frequency domain basis vector, and the first frequency domain basis vector is different from the second frequency domain basis vector, determine a fourth indication and a fifth indication, the fourth indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector, and the fifth indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector.

7. The method according to any one of claims 1 to 3, characterized in that: The first CSI is included in a second CSI report, and the second CSI is included in a third CSI report; the second CSI report and the third CSI report are associated with the same CSI-RS resource.

8. The method according to any one of claims 5 to 7, characterized in that: The first CSI also includes at least one of the combination coefficient information corresponding to the first spatial basis vector and the combination coefficient information of the first frequency domain basis vector; the second CSI also includes at least one of the combination coefficient information corresponding to the second spatial basis vector and the combination coefficient information of the second frequency domain basis vector.

9. The method according to claim 7, characterized in that An absolute value of a reporting overhead difference between the second CSI report and the third CSI report is less than a first threshold.

10. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: Reporting to the network device at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the feature vector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information; wherein, at least one of the input information of the AI ​​model deployed on the terminal side, the channel estimation information, the feature vector corresponding to the channel estimation information, the angle domain information obtained by preprocessing the channel estimation information, and the angle and delay domain information obtained by preprocessing the channel estimation information is included in the first CSI report, or included in the second CSI report, or included in the third CSI report, or included in a fourth CSI report different from the first CSI report, the second CSI report, and the third CSI report; The first CSI report and the fourth CSI report are associated with the same CSI-RS resource, or the second CSI report, the third CSI report, and the fourth CSI report are associated with the same CSI-RS resource.

11. The method according to claim 10, characterized in that The method further comprises: In response to the input information of the AI ​​model deployed on the terminal side being the same as the precoding vector determined by the precoding matrix index PMI in the second CSI, at least one of the input information of the AI ​​model, the channel estimation information, the eigenvector corresponding to the channel estimation information, the angle domain information obtained after preprocessing of the channel estimation information, and the angle and delay domain information obtained after preprocessing of the channel estimation information is not reported.

12. The method according to any one of claims 1 to 11, characterized in that: After reporting at least one of the first CSI and the second CSI to the network device, the method further includes at least one of the following: receiving recovery information sent by the network device, where the recovery information is information output by the AI ​​model deployed on the network device side based on the first CSI; In response to the input information of the AI ​​model being a feature vector corresponding to the channel estimation information, determining a first monitoring value based on the recovery information and the input information of the AI ​​model deployed on the terminal side; determining a second monitoring value based on the recovery information; Determine a precoding vector based on the PMI in the second CSI; In response to the input information of the AI ​​model being a feature vector corresponding to the channel estimation information, determining a third monitoring value based on the precoding vector and the input information of the AI ​​model deployed on the terminal side; Determining a fourth monitoring value based on the precoding vector; Report at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value to the network device, wherein at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is used to perform performance monitoring on the AI ​​model.

13. The method according to claim 12, characterized in that Reporting at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value using the same CSI report; Alternatively, the fifth CSI report is used to report at least one of the first monitoring value and the second monitoring value, and the sixth CSI report is used to report at least one of the third monitoring value and the fourth monitoring value.

14. The method according to any one of claims 1 to 11, characterized in that: After reporting at least one of the first CSI and the second CSI to the network device, the method further includes at least one of the following: receiving at least one CSI-RS resource sent by the network device, wherein the at least one CSI-RS resource includes at least one of a first CSI-RS resource and a second CSI-RS resource; wherein the first CSI-RS resource is sent by the network device using a first beam, the first beam is determined based on the first CSI, and the second CSI-RS resource is sent by the network device using a second beam, and the second beam is determined based on the second CSI; Determine a fifth monitoring value by measuring effective channel information of the first CSI-RS resource; Determine a sixth monitoring value by measuring effective channel information of the second CSI-RS resource; Report at least one of the fifth monitoring value and the sixth monitoring value to the network device, wherein at least one of the fifth monitoring value and the sixth monitoring value is used to perform performance monitoring on the AI ​​model.

15. The method according to claim 14, characterized in that At least one of the fifth monitoring value and the sixth monitoring value is reported using the same CSI report; or, the fifth monitoring value and the sixth monitoring value are reported using different CSI reports.

16. A reporting method, characterized in that: The method comprises: The network device receives at least one of the first CSI and the second CSI reported by the terminal; wherein the first CSI is determined based on the AI ​​model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to perform performance monitoring on the AI ​​model.

17. The method according to claim 16, characterized in that The input information of the AI ​​model includes at least one of the following: channel estimation information; Angle domain information obtained by preprocessing the channel estimation information; The angle and delay domain information obtained by preprocessing the channel estimation information; The eigenvector corresponding to the channel estimation information.

18. The method according to claim 16 or 17, characterized in that The first CSI and the second CSI are included in a first CSI report.

19. The method according to claim 18, characterized in that The first CSI report includes a first indication, where the first indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector used when calculating the first CSI, or the first indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector used when calculating the second CSI, wherein the first spatial domain basis vector is the same as the second spatial domain basis vector, and / or the first frequency domain basis vector is the same as the second frequency domain basis vector; or The first CSI report includes a second indication and a third indication, the second indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector, and the third indication is used to indicate at least one second spatial domain basis vector in at least one first spatial domain basis vector and / or, used to indicate at least one second frequency domain basis vector in at least one first frequency domain basis vector; or The first CSI report includes a fourth indication and a fifth indication, the fourth indication is used to indicate at least one first spatial domain basis vector and / or at least one first frequency domain basis vector, and the fifth indication is used to indicate at least one second spatial domain basis vector and / or at least one second frequency domain basis vector.

20. The method according to claim 16 or 17, characterized in that The first CSI is included in a second CSI report, and the second CSI is included in a third CSI report; the second CSI report and the third CSI report are associated with the same CSI-RS resource.

21. The method according to claim 19 or 20, characterized in that The first CSI also includes at least one of the combination coefficient information corresponding to the first spatial basis vector and the combination coefficient information of the first frequency domain basis vector; the second CSI also includes at least one of the combination coefficient information corresponding to the second spatial basis vector and the combination coefficient information of the second frequency domain basis vector.

22. The method of claim 20, wherein: An absolute value of a reporting overhead difference between the second CSI report and the third CSI report is less than a first threshold.

23. The method according to any one of claims 16 to 22, characterized in that: The method further comprises: Receive at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, feature vectors corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information, reported by the terminal; wherein at least one of the input information of the AI ​​model deployed on the terminal side, channel estimation information, feature vectors corresponding to the channel estimation information, angle domain information obtained by preprocessing the channel estimation information, and angle and delay domain information obtained by preprocessing the channel estimation information is included in the first CSI report, or included in the second CSI report, or included in the third CSI report, or included in a fourth CSI report different from the first CSI report, the second CSI report, and the third CSI report; The first CSI report and the fourth CSI report are associated with the same CSI-RS resource, or the second CSI report, the third CSI report, and the fourth CSI report are associated with the same CSI-RS resource.

24. The method according to any one of claims 16 to 23, characterized in that: The method further comprises: Determine recovery information based on the first CSI using the AI ​​model deployed on the network device side; sending the restoration information to the terminal; Receive at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value reported by the terminal; wherein at least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is used to perform performance monitoring on the AI ​​model.

25. The method of claim 24, wherein: At least one of the first monitoring value, the second monitoring value, the third monitoring value, and the fourth monitoring value is included in the same CSI report; or, at least one of the first monitoring value and the second monitoring value is included in the fifth CSI report, and at least one of the third monitoring value and the fourth monitoring value is included in the sixth CSI report.

26. The method according to any one of claims 16 to 23, characterized in that: The method further comprises: Sending at least one CSI-RS resource to the terminal based on the first CSI and / or the second CSI, where the at least one CSI-RS resource includes at least one of a first CSI-RS resource and a second CSI-RS resource; wherein the first CSI-RS resource is sent by the network device using a first beam, the first beam is determined based on the first CSI, and the second CSI-RS resource is sent by the network device using a second beam, and the second beam is determined based on the second CSI; Receive at least one of the fifth monitoring value and the sixth monitoring value reported by the terminal; wherein, at least one of the fifth monitoring value and the sixth monitoring value is used to perform performance monitoring on the AI ​​model.

27. The method of claim 26, wherein: At least one of the fifth monitoring value and the sixth monitoring value is included in the same CSI report; or, the fifth monitoring value and the sixth monitoring value are respectively included in different CSI reports.

28. A reporting method, characterized in that: Used in a communication system, the communication system comprising a terminal and a network device, the method comprising at least one of the following: The terminal reports at least one of the first channel state information CSI and the second CSI to the network device; wherein the first CSI is determined based on the AI ​​model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to monitor the performance of the AI ​​model; The network device receives at least one of the first CSI and the second CSI reported by the terminal; The network device performs performance monitoring on the AI ​​model based on at least one of the first CSI and the second CSI.

29. A terminal, comprising: A sending module, used for the terminal to report at least one of the first channel state information CSI and the second CSI to the network device; wherein the first CSI is determined based on the AI ​​model deployed on the terminal side, and the second CSI is determined based on the codebook parameters configured by the network device, and the first CSI and / or the second CSI are used to perform performance monitoring on the AI ​​model.

30. A network device comprising: A receiving module, used for a network device to receive at least one of a first CSI and a second CSI reported by a terminal; wherein the first CSI is determined based on an AI model deployed on the terminal side, and the second CSI is determined based on a codebook parameter configured by the network device, and the first CSI and / or the second CSI are used to perform performance monitoring on the AI ​​model.

31. A communication device, characterized in that: include: One or more processors; The processor is used to call instructions so that the communication device executes the reporting method described in any one of claims 1-15 and 16-27.

32. A communication system, characterized in that: It comprises a terminal and a network device, wherein the terminal is configured to implement the reporting method according to any one of claims 1 to 15, and the network device is configured to implement the reporting method according to any one of claims 16 to 27.

33. A storage medium storing instructions, characterized in that: When the instruction is executed on the communication device, the communication device executes the reporting method as described in any one of claims 1-15 and 16-27.

Images