Communication method and apparatus

Abstract

Embodiments of the invention disclose a communication method and apparatus. The method is applied to a terminal device, and comprises: receiving configuration information, wherein the configuration information is used for determining a performance evaluation result of a first model, the first model is an artificial intelligence model or a machine learning model, and the first model is used for predicting channel information and / or channel state information (CSI); on the basis of the configuration information, determining a performance evaluation result of the first model. The mode allows the terminal device to perform performance evaluation on the first model used for predicting the channel information and / or the channel state information (CSI), so that the accuracy of the prediction by the first model of the channel information and / or the channel state information (CSI) is improved.

Description

Communication method and device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on August 14, 2023, with application number 2023110245644 and application name “A Communication Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a communication method and device. Background Art

[0003] Artificial intelligence (AI) technology has been introduced into communication systems. For example, intelligent models, such as AI or machine learning (ML) models, are used to predict channel information and / or channel state information (CSI). This allows for CSI predictions to be generated, ensuring that the CSI fed back by terminal devices to network equipment is more accurate, thereby better matching the channel environment for subsequent transmissions.

[0004] However, when the terminal device uses the intelligent model, the performance of the intelligent model may change. Therefore, how the terminal device monitors the performance of the intelligent model is an urgent problem to be solved.

[0005] Summary of the Invention

[0006] Embodiments of the present application provide a communication method and apparatus that enable a terminal device to perform performance evaluation on a first model for predicting channel information and / or channel state information CSI.

[0007] In a first aspect, embodiments of the present application provide a communication method. The method includes: a terminal device receiving configuration information, where the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information (CSI). The terminal device determines the performance evaluation result of the first model based on the configuration information.

[0008] It can be seen that in an embodiment of the present application, the terminal device performs performance evaluation on the first model for predicting channel information and / or CSI based on the received configuration information, which is beneficial to improving the accuracy of the first model in predicting channel information and / or CSI.

[0009] In an optional embodiment, the configuration information includes a first channel state CSI reporting configuration and a second CSI reporting configuration associated with the first CSI reporting configuration, wherein the first CSI reporting configuration is configured to use a first model to predict channel information and / or CSI, and the second CSI reporting configuration is configured to evaluate the performance of the first model.

[0010] In an optional embodiment, if the configuration information includes a first CSI report configuration and a second CSI report configuration, the terminal device determines the performance evaluation result of the first model based on the configuration information, including: predicting the channel information and / or CSI based on the first CSI report configuration and the first model to obtain first information, where the first information is the first CSI and / or first channel information; and performing a performance evaluation on the first model based on the second CSI report configuration and the first information to obtain a first performance evaluation result.

[0011] In an optional embodiment, the first performance evaluation result is represented by the accuracy of the first information and / or the similarity between the first information and the second information. The second information is obtained by the terminal device without using the first model, and the second information is the second CSI and / or the second channel information.

[0012] In an optional implementation, if the first information is the first CSI, the second information is the second CSI; if the first information is the first channel information, the second information is the second channel information.

[0013] In an optional implementation, the terminal device reports a first CSI report and a second CSI report, the first CSI report includes the first CSI, and the second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information.

[0014] In another optional embodiment, if the accuracy of the first information is greater than a first preset value, and / or the similarity between the first information and the second information is greater than a second preset value, the terminal device reports a first CSI report and a second CSI report, the first CSI report includes the first CSI, and the second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information.

[0015] In another optional embodiment, if the accuracy of the first information is less than or equal to a first preset value, and / or the similarity between the first information and the second information is less than or equal to a second preset value, the terminal device reports a second CSI report, and the second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information.

[0016] In another optional embodiment, the configuration information includes a third CSI report configuration, and the third CSI report configuration is associated with the first resource set and the second resource set. The first resource set is used to predict channel information and / or CSI using the first model, and the second resource set is used to evaluate the performance of the first model.

[0017] In an optional embodiment, if the configuration information includes a third CSI report configuration, the terminal device determines the performance evaluation result of the first model based on the configuration information, including: predicting the channel information and / or CSI based on the first resource set and the first model to obtain third information, where the third information is third CSI and / or third channel information; and performing a performance evaluation on the first model based on the second resource set and the third information to obtain a second performance evaluation result.

[0018] In an optional embodiment, the second performance evaluation result is represented by the accuracy of the third information and / or the similarity between the third information and the fourth information. The fourth information is obtained by the terminal device based on the second resource set and not using the first model, and the fourth information is fourth CSI and / or fourth channel information.

[0019] In an optional implementation, if the third information is third CSI, the fourth information is fourth CSI; if the third information is third channel information, the fourth information is fourth channel information.

[0020] In an optional implementation, the first resource set and the second resource set are periodic or semi-persistent resource sets; or, the first resource set is a periodic or semi-persistent resource set, and the second resource set is a non-periodic resource set; or, the first resource set and the second resource set are non-periodic resource sets.

[0021] In an optional embodiment, the terminal device reports a third CSI report. If the accuracy of the third information is greater than a first preset value and / or the similarity between the third information and the fourth information is greater than a second preset value, the third CSI report includes the third CSI and / or the second performance evaluation result and / or the fourth CSI and / or the fourth channel information.

[0022] In an optional embodiment, if the accuracy of the third information is less than or equal to a first preset value, and / or the similarity between the third information and the fourth information is less than or equal to a second preset value, the third CSI report includes the second performance evaluation result and / or the fourth CSI and / or the fourth channel information.

[0023] In another optional implementation, the configuration information includes a fourth CSI report configuration, the fourth CSI report configuration is associated with a third resource set, and the third resource set is used to perform performance evaluation on the first model.

[0024] In an optional implementation, if the configuration information includes a fourth CSI reporting configuration, the terminal device determines, based on the configuration information, a performance evaluation result of the first model, including: performing a performance evaluation on the first model based on resources in a third resource set that are adjacent to resources used for reporting the CSI report, to obtain a third performance evaluation result. The third resource set is a periodic or semi-persistent periodic resource set, or an aperiodic resource set.

[0025] In an optional embodiment, the third performance evaluation result is represented by the accuracy of the fifth information and / or the similarity between the fifth information and the sixth information. The fifth information is fifth CSI and / or fifth channel information, the fifth information is obtained by the terminal device using the first model, the sixth CSI or sixth channel information is obtained by the terminal device without using the first model, and the sixth information is sixth CSI and / or sixth channel information.

[0026] In an optional implementation, if the fifth information is the fifth CSI, the sixth information is the sixth CSI; if the fifth information is the fifth channel information, the sixth information is the sixth channel information.

[0027] In an optional implementation, the terminal device reports a fourth CSI report. If the accuracy of the fifth information is greater than a first preset value and / or the similarity between the fifth information and the sixth information is greater than a second preset value, the fourth CSI report includes the fifth CSI and / or the third performance evaluation result and / or the sixth CSI and / or the sixth channel information.

[0028] In an optional embodiment, if the accuracy of the fifth information is less than or equal to a first preset value, and / or the similarity between the fifth information and the sixth information is less than or equal to a second preset value, the fourth CSI report includes the third performance evaluation result and / or the sixth CSI and / or the sixth channel information.

[0029] In a second aspect, embodiments of the present application further provide a communication method. The method is applied to a network device and includes: determining configuration information, the configuration information being used to determine a performance evaluation result of a first model, the first model being an artificial intelligence model or a machine learning model, the first model being used to predict channel information and / or channel state information (CSI); and sending the configuration information.

[0030] It can be seen that the network device determines the configuration information for evaluating the performance of the first model, which is beneficial for the terminal device to perform performance evaluation on the first model for predicting channel information and / or CSI based on the configuration information, thereby facilitating improving the accuracy of channel information and / or CSI prediction.

[0031] In an optional embodiment, the configuration information includes a first CSI reporting configuration and a second CSI reporting configuration associated with the first CSI reporting configuration, wherein the first CSI reporting configuration is configured to use a first model to predict channel information and / or CSI, and the second CSI reporting configuration is configured to evaluate the performance of the first model.

[0032] In an optional embodiment, a network device receives a first CSI report and a second CSI report, where the first CSI report includes the first CSI, and the second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information. The first CSI is obtained by the terminal device by predicting the channel information and / or CSI based on the first CSI report configuration and the first model; the first performance evaluation result is obtained by the terminal device by performing a performance evaluation of the first model based on the second CSI report configuration and the first CSI; and the second CSI or the second channel information is obtained by the terminal device without using the first model.

[0033] In another optional embodiment, the network device receives a second CSI report, which includes the first performance evaluation result and / or the second CSI and / or the second channel information. The first performance evaluation result is obtained by the terminal device performing a performance evaluation on the first model based on the second CSI report configuration and the first CSI; the first CSI is obtained by the terminal device predicting the channel information and / or CSI based on the first CSI report configuration and the first model; and the second CSI or the second channel information is obtained by the terminal device without using the first model.

[0034] In an optional implementation, the first performance evaluation result is represented by the accuracy of the first information and / or the similarity between the first information and the second information.

[0035] The first information is first CSI and / or first channel information, and the first channel information is obtained by the terminal device by predicting the channel information and / or CSI based on the first CSI reporting configuration and the first model. The second information is obtained by the terminal device without using the first model, and the second information is second CSI and / or second channel information.

[0036] In an optional implementation, if the first information is the first CSI, the second information is the second CSI; if the first information is the first channel information, the second information is the second channel information.

[0037] In another optional embodiment, the configuration information includes a third CSI report configuration, and the third CSI report configuration is associated with the first resource set and the second resource set. The first resource set is used to predict channel information and / or CSI using the first model, and the second resource set is used to evaluate the performance of the first model.

[0038] In an optional implementation, the first resource set and the second resource set are periodic or semi-persistent resource sets; or, the first resource set is a periodic or semi-persistent resource set, and the second resource set is a non-periodic resource set; or, the first resource set and the second resource set are non-periodic resource sets.

[0039] In an optional embodiment, the network device receives a third CSI report, the third CSI includes the third CSI and / or the second performance evaluation result and / or the fourth CSI and / or the fourth channel information, or the third CSI report includes the second performance evaluation result and / or the fourth CSI and / or the fourth channel information.

[0040] Among them, the third CSI is obtained by the terminal device predicting the channel information and / or CSI based on the first resource set and the first model; the second performance evaluation result is obtained by the terminal device performing a performance evaluation on the first model based on the second resource set and the third CSI; the fourth CSI or fourth channel information is obtained by the terminal device based on the second resource set and without using the first model.

[0041] In an optional implementation, the second performance evaluation result is represented by the accuracy of the third information and / or by the similarity between the third information and the fourth information.

[0042] The third information is third CSI and / or third channel information. The third channel information is obtained by the terminal device by predicting the channel information and / or CSI based on the first resource set and the first model. The fourth information is obtained by the terminal device based on the second resource set and not using the first model. The fourth information is fourth CSI and / or fourth channel information.

[0043] In an optional implementation, if the third information is third CSI, the fourth information is fourth CSI; if the third information is third channel information, the fourth information is fourth channel information.

[0044] In another optional embodiment, the configuration information includes a fourth CSI reporting configuration, the fourth CSI reporting configuration is associated with a third resource set, and the third resource set is used to perform performance evaluation on the first model. The third resource set is a periodic or semi-persistent periodic resource set, or an aperiodic resource set.

[0045] In an optional implementation, the network device receives a fourth CSI report. The fourth CSI report includes the fifth CSI and / or the third performance evaluation result and / or the sixth CSI and / or the sixth channel information; or the fourth CSI report includes the third performance evaluation result and / or the sixth CSI and / or the sixth channel information.

[0046] Among them, the fifth CSI or fifth channel information is obtained by the terminal device predicting the channel information and / or CSI based on the fourth CSI report configuration and the first model; the third performance evaluation result is obtained by the terminal device performing a performance evaluation on the first model based on the fourth CSI report configuration; the sixth CSI or sixth channel information is obtained by the terminal device without using the first model.

[0047] In an optional implementation, the third performance evaluation result is represented by the accuracy of the fifth information and / or the similarity between the fifth information and the sixth information.

[0048] The fifth information is the fifth CSI and / or the fifth channel information. The fifth information is obtained by the terminal device using the first model. The sixth information is obtained by the terminal device without using the first model. The sixth information is the sixth CSI and / or the sixth channel information.

[0049] In an optional implementation, if the fifth information is the fifth CSI, the sixth information is the sixth CSI; if the fifth information is the fifth channel information, the sixth information is the sixth channel information.

[0050] In a third aspect, an embodiment of the present application provides a communication device, which is applied to a terminal device, and includes:

[0051] a communication unit, configured to receive configuration information for determining a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is configured to predict channel information and / or channel state information (CSI);

[0052] A determining unit is configured to determine a performance evaluation result of the first model based on the configuration information.

[0053] In addition, in this aspect, other optional implementations of the communication device can refer to the relevant content of the first aspect mentioned above and will not be described in detail here.

[0054] In a fourth aspect, an embodiment of the present application further provides a communication device, which is applied to a network device, and includes:

[0055] a determining unit, configured to determine configuration information, where the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information (CSI);

[0056] A communication unit is configured to send the configuration information.

[0057] In addition, in this aspect, other optional implementations of the communication device can refer to the relevant content of the second aspect above and will not be described in detail here.

[0058] In a fifth aspect, an embodiment of the present application provides a terminal device, the terminal device including a memory and a processor; optionally, the terminal device further includes a communication interface;

[0059] Memory for storing computer programs;

[0060] Communication interface, used to receive or send data;

[0061] The processor is configured to call program instructions stored in the memory.

[0062] In an optional embodiment, the processor calls a computer program to perform the following operations:

[0063] Receive configuration information, where the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information CSI; based on the configuration information, determine a performance evaluation result of the first model.

[0064] In addition, in this aspect, other optional implementations of the terminal device can refer to the relevant content of the first aspect above and will not be described in detail here.

[0065] In a sixth aspect, an embodiment of the present application provides a network device, the network device including a memory and a processor; optionally, the terminal device further includes a communication interface;

[0066] Memory for storing computer programs;

[0067] Communication interface, used to receive or send data;

[0068] The processor is configured to call program instructions stored in the memory.

[0069] In an optional embodiment, the processor calls a computer program to perform the following operations:

[0070] Determine configuration information, where the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information CSI; and send the configuration information.

[0071] In addition, in this aspect, other optional implementations of the network device can refer to the relevant content of the second aspect above and will not be described in detail here.

[0072] In a seventh aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is used to receive or send data;

[0073] In an optional implementation, the processor is configured to cause the chip to execute:

[0074] Receive configuration information, where the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information CSI; based on the configuration information, determine a performance evaluation result of the first model.

[0075] In addition, in this aspect, other optional implementations of the chip can refer to the relevant content of the first aspect above and will not be described in detail here.

[0076] In another optional implementation, the processor is configured to cause the chip to execute:

[0077] Determine configuration information, where the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information CSI; and send the configuration information.

[0078] In addition, in this aspect, other optional implementations of the chip can refer to the relevant content of the second aspect above and will not be described in detail here.

[0079] In an eighth aspect, an embodiment of the present application provides a module device, comprising a communication module, a power module, a storage module, and a chip, wherein:

[0080] The power supply module is used to provide electrical energy to the module device;

[0081] The storage module is used to store data and instructions;

[0082] The communication module is used for internal communication within the module device, or for communication between the module device and an external device;

[0083] The chip is used to execute the methods described in the first and second aspects above.

[0084] In a ninth aspect, an embodiment of the present application provides a computer-readable storage medium for storing computer software instructions used by the above-mentioned terminal, which includes a program for executing any of the methods described in the first and second aspects above.

[0085] In the tenth aspect, an embodiment of the present application further provides a computer program product, which, when running on a processor, is used to implement the method flow described in any one of the first and second aspects above. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] FIG1 is a schematic diagram of the system structure of a communication system provided in an embodiment of the present application;

[0087] FIG2 is a flow chart of a communication method provided in an embodiment of the present application;

[0088] FIG3 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0089] FIG4 is a schematic structural diagram of another communication device provided in an embodiment of the present application;

[0090] FIG5 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application;

[0091] FIG6 is a schematic structural diagram of a module device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0092] The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0093] Among them, the terms "first" and "second" in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. "First" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this embodiment, unless otherwise specified, "multiple" means two or more.

[0094] Furthermore, the terms "include," "comprise," and "have," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0095] It should be understood that in this application, "multiple" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. "When" and "if" both mean that corresponding processing will be carried out under certain objective circumstances. It does not limit the time, nor does it require a judgment action when it is implemented, nor does it mean that there are other limitations.

[0096] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner to facilitate understanding.

[0097] In order to better understand the communication method disclosed in the embodiment of the present application, the system architecture applicable to the embodiment of the present application is described.

[0098] The communication system involved in the embodiment of the present application is shown in Figure 1. The communication system may include but is not limited to a network device and a terminal device. The number and form of the devices shown in Figure 1 are used for example and do not constitute a limitation on the embodiment of the present application. In actual applications, more than one network device and more than one terminal device may be included. The communication system shown in Figure 1 is explained using the network device 101 and the terminal device 102 as an example. The network device 101 can provide network services for the terminal device 102, and the network device 101 can communicate with the terminal device 102. In the embodiment of the present application, the communication system may also include other devices that communicate with the network device 101 or with the terminal device 102, which is not limited by the embodiment of the present application.

[0099] The terminal device in the embodiments of the present application may also be referred to as a terminal, and may refer to various forms of user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), remote station, remote terminal, mobile device, user terminal, wireless communication device, user agent or user device. The terminal device may also be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in a fifth generation mobile communication (5G) network, or a terminal device in a future evolved public land mobile network (PLMN), etc., and the embodiments of the present application are not limited to this.

[0100] In the embodiment of the present application, the terminal device may also have artificial intelligence (AI) processing capabilities, and the network device may also have AI processing capabilities. For example, the terminal device may have neural network training capabilities, reasoning capabilities, etc.

[0101] In an embodiment of the present application, the terminal device may include a prediction module (e.g., an artificial intelligence (AI) module). The prediction module may be used to predict downlink channel information. For example, the second channel information may be predicted or determined based on the first channel information, so that the second channel information may not rely on the downlink reference signal, thereby saving network resources occupied by the downlink reference signal. The prediction module may have learning capabilities, such as machine learning (ML) and / or deep learning (DL) capabilities, to learn the first channel information and thus predict or determine the second channel information.

[0102] Optionally, the prediction module may be a software unit and / or hardware unit that predicts channel information using some algorithms, such as convolutional neural network algorithms, deep neural network algorithms, etc. Optionally, the prediction module may be a chip, a chip module, etc.

[0103] Optionally, in an embodiment of the present application, the network device may include a prediction module to implement prediction of uplink channel information.

[0104] In the embodiments of the present application, the network device may be a device with receiving and / or transmitting functions, which can be used to communicate with terminal devices. In some possible implementations, the network device is a physical entity connected to the network, and the network device includes a base station and a base station controller of the access network.

[0105] The base station (BS) in the embodiments of the present application, which may also be referred to as a base station device, is a device deployed in a wireless access network (RAN) to provide wireless communication functions. For example, the device that provides base station functions in a second generation mobile communication (2G) network includes a base transceiver station (BTS). The device that provides base station functions in a third generation mobile communication (3G) network includes a node B (NodeB). The device that provides base station functions in a fourth generation mobile communication (4G) network includes an evolved node B (eNB). In a wireless local area network (WLAN), the device that provides base station functions is an access point (AP). The gNB, a device providing base station functions in 5G new radio (NR), and the evolved Node B (ng-eNB), wherein the gNB and the terminal device communicate using NR technology, and the ng-eNB and the terminal use evolved universal terrestrial radio access (E-UTRA) technology for communication. Both the gNB and the ng-eNB can be connected to the 5G core network. The base station in the embodiment of the present application also includes a device that provides base station functions in a future new communication system.

[0106] The base station controller in the embodiments of the present application, also referred to as a base station controller device, is a device that manages base stations. For example, it can be a base station controller (BSC) in a 2G network, a radio network controller (RNC) in a 3G network, or a device that controls and manages base stations in future communication systems.

[0107] The present application can be applied to 5G communication systems, 4G communication systems, 3G communication systems, and various new communication systems in the future, such as the sixth generation (6G) mobile communication, the seventh generation (7G) mobile communication, etc., but the embodiments of the present application are not limited to this.

[0108] The following is an introduction to the relevant concepts involved in the embodiments of this application:

[0109] 1. Channel information.

[0110] In the embodiments of the present application, channel information can be used to characterize channel characteristics or features. For example, the channel information can be channel matrix information, and / or CSI, and / or channel eigenvectors. Alternatively, the channel information can be a CSI report. Alternatively, the channel information can be time domain information, frequency domain information, time-frequency domain information, or delay-Doppler domain channel information, etc., without specific limitation. The channel matrix information and CSI are described below.

[0111] The channel matrix information can be used to describe information related to the channel matrix. For example, the channel matrix information may include one or more of the following: channel matrix H, equivalent channel matrix, precoding matrix W (precoding matrix W can be derived from channel matrix H), right singular vector V of channel matrix H, square matrix H T The eigenvector v of H i , vectors associated with the channel matrix H (e.g., vectors of the channel matrix H under certain deformation, etc.), and the channel matrix H T H associated vector (e.g., channel matrix H T The vector of H under some deformation, etc.

[0112] 2. Channel state information CSI.

[0113] In embodiments of the present application, CSI can be used to describe information related to channel quality. For example, CSI describes the propagation process of a wireless signal between a transmitter and a receiver, including the effects of distance, scattering, fading, and other factors on the signal. For downlink transmission, CSI can be used by a terminal device to provide feedback on downlink channel quality to a network device, allowing the network device to perform beam management, mobility management, and other processes based on the CSI. The CSI sent by the terminal device to the network device can be included in a CSI report. For example, CSI may also include at least one of the following items: channel state information-reference signal resource indicator index (CRI), rank indicator index (RI), channel quality indicator index (CQI), precoding matrix indicator index (PMI), layer indicator index (LI), layer 1-reference signal receiving power (L1-RSRP), layer 1-signal to interference plus noise ratio (L1-SINR), capability index (capability index), time-domain channel properties (TDCP), etc.

[0114] In the present application, the terminal device performs channel measurement through a downlink reference signal to obtain channel information. Measurement can also be described as evaluation, detection or estimation, etc. Among them, the downlink reference signal may include but is not limited to a channel state information-reference signal (CSI-RS), a synchronization signal and a physical broadcast channel block (SSB) or a physical broadcast channel demodulation reference signal (PBCH DMRS), etc. For example, the terminal device can perform downlink channel measurement based on the CSI-RS to obtain channel matrix information, and thus can obtain CSI based on the channel matrix information.

[0115] 3.CSI report.

[0116] In an embodiment of the present application, a CSI report (CSI-report) is used to report CSI. For example, a CSI report may include at least one of L1-RSRP, L1-SINR, CSI-related information, etc. Specifically, in some embodiments, the CSI report may be configured by a higher-layer parameter CSI report configuration information (CSI-ReportConfig). CSI-ReportConfig may be configured by a higher-layer parameter CSI-MeasConfig. CSI-MeasConfig may indicate or include the following two higher-layer parameters: CSI report configuration information (CSI-ReportConfig) and CSI resource configuration information (CSI-ResourceConfig).

[0117] CSI-ReportConfig may indicate or include CSI-ResourceConfigId. Through CSI-ResourceConfigId, CSI-ReportConfig may be associated with CSI-ResourceConfig, or CSI-ResourceConfig may be associated with CSI-ReportConfig. Association may also be described as mapping or correspondence, etc. In an embodiment of the present application, CSI-ReportConfig indicates or includes CSI-ResourceConfigId, which may be understood as CSI resource configuration information associated with the CSI report configuration information; CSI-ReportConfig does not indicate or include CSI-ResourceConfigId, which may be understood as CSI resource configuration information not associated with the CSI report configuration information.

[0118] CSI-ResourceConfig can be used to configure CSI-RS resources for CSI measurement. CSI-ResourceConfig can configure a resource set (e.g., ResourceSet), which can include one or more CSI-RS resources (e.g., CSI-RS-Resource).

[0119] CSI-ResourceConfig may indicate or include: a non-zero power-channel state information channel state-information-reference signal (NZP-CSI-RS) resource set (NZP-CSI-RS-ResourceSet), a CSI interference measurement (CSI-IM) resource set (CSI-IM-ResourceSet), or a synchronization signal block (synchronization signal / physical broadcast channel block, SSB) resource set (SSB-ResourceSet).

[0120] Among them, NZP-CSI-RS-ResourceSet can be used for channel measurement and / or interference measurement; CSI-IM-ResourceSet can be used for interference measurement; SSB-ResourceSet can be used for channel measurement.

[0121] The type of CSI-RS resources can be periodic, semi-persistent, or aperiodic.

[0122] The report configuration type (reportConfigType) in CSI-ReportConfig can be used to indicate the report type of the CSI report, which can be a periodic CSI report, an aperiodic CSI report, or a semi-persistent CSI report. The CSI report can be transmitted via the physical uplink control channel (PUCCH) or the physical uplink shared channel (PUSCH).

[0123] In the embodiment of the present application, "prediction" can also be understood as estimating or speculating on information in advance. For example, "predicting channel information and / or channel state information CSI" means: estimating or speculating on channel information and / or channel state information CSI in advance. In order to improve the accuracy of channel state information CSI, AI technology is introduced. Specifically, the channel information and / or CSI are predicted by an AI model or a machine learning (ML) model to obtain CSI. Compared with the terminal device determining the CSI based on the channel state information-reference signal CSI-RS by itself, the method of obtaining CSI based on the AI ​​model or the ML model has higher accuracy, so that the CSI fed back by the terminal device to the network device has higher accuracy, and can better match the channel environment of subsequent transmission.

[0124] However, when a terminal device uses an AI or ML model, its performance may change, which can reduce the accuracy of the predicted channel information and / or CSI. Therefore, how to monitor the performance of AI or ML models is an urgent issue that needs to be studied.

[0125] An embodiment of the present application provides a communication method. In this communication method, a network device determines configuration information, and the configuration information is used to determine a performance evaluation result of a first model. The first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or CSI. The network device sends the configuration information to a terminal device. The terminal device determines the performance evaluation result of the first model based on the configuration information. It can be seen that the terminal device can perform a performance evaluation on the first model based on the configuration information configured by the network device for determining the performance evaluation result of the first model, which is conducive to improving the accuracy of the first model in predicting channel information and / or CSI.

[0126] Based on the above description, the present embodiment provides a communication method 100. FIG2 is a flow chart of the communication method 100. The method includes but is not limited to:

[0127] S101. The network device determines configuration information, where the configuration information is used to determine a performance evaluation result of a first model. The first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information CSI.

[0128] The first model is a model configured within the terminal device for predicting channel information and / or CSI. For example, the first model is configured in a processing module of the terminal device. The first model is obtained by training the terminal device using a large amount of training data, and the training data can be obtained based on the CSI-RS received by the terminal device.

[0129] Optionally, the first model is a model obtained by the network device through training using a large amount of training data and used to predict channel information and / or CSI. The network device sends the trained first model to the terminal device, so that the terminal device predicts the channel information and / or CSI based on the first model.

[0130] In addition, the first model can also be other intelligent models / other models other than the AI ​​model or the ML model, and the embodiments of the present application are not limited to this. In the embodiments of the present application, the first model can also be understood as one or more algorithms. For example, the first model is an AI algorithm. For another example, the first model is an ML algorithm. In the embodiments of the present application, the first model can also be understood as a module based on the AI / ML algorithm. In the embodiments of the present application, the first model can also be understood as a signal processing module based on the AI / ML algorithm. In the embodiments of the present application, the first model can also be understood as an operation based on AI / ML. In the embodiments of the present application, the first model can also be understood as including one or more models / algorithms.

[0131] In an optional embodiment, the configuration information includes a first CSI reporting configuration and a second CSI reporting configuration associated with the first CSI reporting configuration, wherein the first CSI reporting configuration is configured to use a first model to predict channel information and / or CSI, and the second CSI reporting configuration is configured to evaluate the performance of the first model.

[0132] The second CSI report configuration is configured to evaluate the performance of the first model, and may be configured in an explicit manner. For example, the second CSI report configuration is configured to report the performance evaluation result of the first model, such as reporting the squared general cosine similarity (SGCS). Optionally, the second CSI report is configured to evaluate the performance of the first model, and may also be configured in an implicit manner. For example, the second CSI report configuration is configured to terminate the use of the first model when a first condition is met, and the first condition is that the performance evaluation result of the first model is less than a preset value, wherein "terminating the use of the first model" may also be understood as "deactivating" the first model.

[0133] It can be seen that the network device configures the terminal device with a first CSI reporting configuration for predicting channel information and / or CSI using the first model through configuration information, thereby facilitating the terminal device to predict channel information and / or CSI based on the first CSI reporting configuration and the first model. The network device also configures the terminal device with a second CSI reporting configuration for evaluating the performance of the first model through configuration information, thereby facilitating the terminal device to determine the performance of the first model based on the second CSI reporting configuration. This approach enables the terminal device to predict channel information and / or CSI using the first model and monitor the performance of the first model.

[0134] It is understandable that the first CSI reporting configuration is implicitly associated with a first CSI resource configuration identity (ID), and the second CSI reporting configuration is implicitly associated with a second CSI resource configuration ID. This approach facilitates the terminal device determining resources for predicting channel information and / or CSI based on the first CSI resource configuration ID associated with the first CSI reporting configuration, and determining resources for evaluating the performance of the first model based on the second CSI resource configuration ID associated with the second CSI reporting configuration.

[0135] It is understandable that the association between the first CSI reporting configuration and the second CSI reporting configuration can be achieved explicitly or implicitly. For example, the first CSI reporting configuration information includes information #a, where information #a is used to indicate that it is associated with the second CSI reporting configuration. For example, the second CSI reporting configuration information includes information #b, where information #b is used to indicate that it is associated with the first CSI reporting configuration. Information #a and information #b can be the same information. Information #a and information #b can be different information.

[0136] In another optional embodiment, the configuration information includes a third CSI report configuration, and the third CSI report configuration is associated with the first resource set and the second resource set. The first resource set is used to predict channel information and / or CSI using the first model, and the second resource set is used to evaluate the performance of the first model.

[0137] The first resource set includes one or more resources, and the second resource set includes one or more resources.

[0138] In an optional implementation, the first resource set and the second resource set are periodic or semi-persistent resource sets. It is understandable that the resources in the first resource set are periodic resources or semi-persistent resources; and the resources in the second resource set are periodic resources or semi-persistent resources.

[0139] Optionally, the first resource set is a periodic or semi-persistent resource set, and the second resource set is an aperiodic resource set. It is understandable that the resources in the first resource set are periodic resources or semi-persistent resources; and the resources in the second resource set are aperiodic resources.

[0140] Optionally, the first resource set and the second resource set are non-periodic resource sets. It is understandable that the resources in the first resource set and the second resource set are both non-periodic resources.

[0141] It can be seen that the network device configures the first resource set and the second resource set for the terminal device through the configuration information, thereby facilitating the terminal device to predict channel information and / or CSI based on the first resource set and the first model, and to evaluate the performance of the first model based on the second resource set.

[0142] In another optional implementation, the configuration information includes a fourth CSI reporting configuration, the fourth CSI reporting configuration is associated with a third resource set, and the third resource set is used to perform performance evaluation on the first model. The third resource set includes one or more resources.

[0143] Optionally, the third resource set is a periodic or semi-persistent resource set. It is understood that the resources in the third resource set are periodic resources or semi-persistent resources. Optionally, the third resource set is an aperiodic resource set. It is understood that the resources in the third resource set are aperiodic resources.

[0144] It can be seen that the network device configures the third resource set for evaluating the performance of the first model for the terminal device through configuration information, thereby facilitating the terminal device to evaluate the performance of the first model based on the third resource set.

[0145] Optionally, the resource sets mentioned above may also be expressed as resource groups. For example, a first CSI report configuration may be associated with a first resource set, and a second CSI report configuration may be associated with a second resource set. This may mean: the first CSI report configuration is associated with the first resource group, and the second CSI report configuration is associated with the second resource group. The first resource group is used to predict channel information and / or CSI using a first model, and the second resource group is used to evaluate the performance of the first model. The first resource group includes one or more resources, and the second resource group includes one or more resources. Optionally, the first resource group and the second resource group are periodic or semi-persistent resource groups. Alternatively, the first resource group is a periodic or semi-persistent resource group, and the second resource group is an aperiodic resource group. Alternatively, the first resource group and the second resource group are aperiodic resource groups. For another example, a fourth CSI report configuration may be associated with a third resource set. This may mean: the fourth CSI report configuration is associated with the third resource group, the third resource group is used to evaluate the performance of the first model, and the third resource group includes one or more resources. Optionally, the third resource group is a periodic or semi-persistent resource group. Optionally, the third resource group is an aperiodic resource group.

[0146] For example, the fourth CSI reporting configuration is associated with the third resource set, and may be: the third resource set includes a third resource group and a fourth resource group. The third resource group is used to predict channel information and / or CSI, and the third resource group includes one or more resources. Optionally, the third resource group is a periodic or semi-persistent resource group. Optionally, the third resource group is an aperiodic resource group. The fourth resource group is used to perform performance evaluation on the first model, and the fourth resource group includes one or more resources. Optionally, the fourth resource group is a periodic or semi-persistent resource group. Optionally, the fourth resource group is an aperiodic resource group.

[0147] It is understandable that the configuration information determined by the network device may be one piece of configuration information or multiple pieces of configuration information, and this embodiment of the present application does not limit this. For example, if the configuration information includes a third CSI reporting configuration, the network device configures five pieces of configuration information for the terminal device. For another example, if the configuration information includes a first CSI reporting configuration and a second CSI reporting configuration, the network device configures one piece of configuration information for the terminal device.

[0148] S102: The network device sends configuration information to the terminal device. Correspondingly, the terminal device receives the configuration information from the network device.

[0149] S103. The terminal device determines a performance evaluation result of the first model based on the configuration information.

[0150] It is understandable that the configuration information sent by the network device to the terminal device is used to determine the performance evaluation result of the first model. Therefore, the terminal device can determine the performance evaluation result of the first model based on the configuration information.

[0151] The terminal device determines the performance evaluation result of the first model based on the configuration information in the following implementations:

[0152] Implementation method 1: The terminal device determines a first performance evaluation result of the first model based on the first CSI reporting configuration and the second CSI reporting configuration.

[0153] It is understandable that the network configuration information includes a first CSI reporting configuration and a second CSI reporting configuration, and the terminal device determines a first performance evaluation result of the first model based on the first CSI reporting configuration and the second CSI reporting configuration. Specifically, the terminal device predicts channel information and / or CSI based on the first CSI reporting configuration and the first model to obtain first information, where the first information is first CSI and / or first channel information; and the terminal device performs a performance evaluation on the first model based on the second CSI reporting configuration and the first information to obtain a first performance evaluation result of the first model.

[0154] The terminal device predicts the channel information and / or CSI based on the first CSI report configuration and the first model to obtain the first information, including: the terminal device determines the first resource based on the first CSI resource configuration ID associated with the first CSI report configuration; the terminal device uses the first resource to receive the first CSI-RS from the network device; the terminal device obtains the first information based on the first CSI-RS and the first model.

[0155] It can be seen that the terminal device uses the first resource determined based on the first CSI report configuration to receive the first CSI-RS from the network device, and uses the information obtained based on the first CSI-RS as the input of the first model to obtain the channel information and / or CSI predicted by the first model, thereby obtaining the first information.

[0156] The terminal device performs a performance evaluation on the first model based on the second CSI reporting configuration and the first information to obtain a first performance evaluation result of the first model, including: the terminal device determines a second resource based on a second CSI resource configuration ID associated with the second CSI reporting configuration; the terminal device uses the second resource to receive a second CSI-RS from a network device; the terminal device determines second information based on the second CSI-RS; the terminal device performs a performance evaluation on the first model based on the first information and the second information to obtain the first performance evaluation result. The second information may be second CSI and / or second channel information.

[0157] It can be seen that the terminal device can obtain the second information based on the second CSI report configuration and the second resource.

[0158] If the first information is the first CSI, the second information is the second CSI; if the first information is the first channel information, the second information is the second channel information. The second CSI or the second channel information is obtained by the terminal device without using the first model.

[0159] It can be seen that the terminal device uses the second resource determined based on the second CSI report to receive the second CSI-RS from the network device, and determines the second information by itself based on the second CSI-RS, and then obtains the first performance evaluation result of the first model based on the first information and the second information.

[0160] It is understandable that the first performance evaluation result can be used to indicate the operating status of the first model, or can be used to indicate the performance of the first model, or can be used to indicate the accuracy of the result obtained based on the first model, or can be used to indicate the performance of the communication link / communication system obtained based on the first model. In the embodiments of the present application, the first performance evaluation result is not specifically limited, that is, other forms are not restricted.

[0161] In an optional implementation, the first performance evaluation result is represented by the accuracy of the first information. A higher accuracy of the first information indicates that the first information predicted by the terminal device based on the first model is more accurate, and thus the performance of the first model is better.

[0162] Optionally, the first performance evaluation result is represented by the similarity between the first information and the second information. Alternatively, the first performance evaluation result is represented by the similarity between the first information and a confidence label, and the confidence label is the second information obtained by the terminal device without using the first model. Among them, the terminal device may use one or more of general cosine similarity (GCS), SGCS, and mean squared error (MSE) to represent the similarity between the first CSI and the second CSI. The larger the value of GCS or SGCS, the better the performance of the first model; or, the smaller the value of NMSE, the better the performance of the first model. In addition, the embodiment of the present application does not limit the representation method of the similarity between the first information and the second information, that is, the representation method of the similarity between the first information and the second information is not limited to the representation using GCS, SGCS, and MSE.

[0163] The terminal device uses SGCS to represent the similarity between the first information and the second information. The first performance evaluation result can be determined by the following rules: SGCS < 0.5, flag1; 0.5 <= SGCS < 0.7, flag2; 0.7 <= SGCS < 0.8, flag3; 0.8 <= SGCS < 0.9, flag4; 0.9 <= SGCS < 0.95, flag5; 0.95 <= SGCS <= 1, flag6. It is understandable that when the terminal device determines the SGCS values ​​of the first and second information, it determines the range of the SGCS based on the SGCS values ​​of the first and second information. The value corresponding to the range of the SGCS is the first performance evaluation result. For example, the above flag1, flag2, flag3, flag4, flag5, and flag6 are the first performance evaluation results.

[0164] Optionally, the first performance evaluation result is represented by the accuracy of the first information and the similarity between the first information and the second information. The higher the accuracy of the first information and the higher the similarity between the first information and the second information, the better the performance of the first model.

[0165] In an optional embodiment, the terminal device reports a first CSI report and a second CSI report, where the first CSI report includes the first CSI, and the second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information. Accordingly, the network device receives the first CSI report and the second CSI report from the terminal device.

[0166] The way in which the terminal device reports the first CSI report and the second CSI report can enable the network device to know the first CSI obtained by the terminal device using the first model, as well as the performance evaluation result of the first model and / or the second CSI and / or the second channel information. Thus, the network device can determine whether to use the first CSI for signal transmission based on the performance evaluation result of the first model. For example, if the performance evaluation result of the first model is good, the network device uses the first CSI to transmit the signal. For example, if the performance evaluation result of the first model is poor, the network device does not use the first CSI for signal transmission, but uses the second CSI for signal transmission. For another example, if the performance evaluation result of the first model is poor, the network device notifies the terminal device to stop using the first model by means of indication information.

[0167] In another optional implementation, the terminal device reports a second CSI report. Optionally, the terminal device does not report the first CSI report. The second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information and / or the first CSI.

[0168] In another optional embodiment, the terminal device reports a second CSI report based on the first performance evaluation result. Optionally, the terminal device does not report the first CSI report. The second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information and / or the first CSI.

[0169] In another optional embodiment, if the accuracy of the first information is greater than a first preset value, and / or the similarity between the first information and the second information is greater than a second preset value, the terminal device reports the first CSI report and the second CSI report. Accordingly, the network device receives the first CSI report and the second CSI report. The first CSI report and the second CSI report are described above and are not further described.

[0170] The first preset value and the second preset value may be pre-negotiated between the terminal device and the network device, or may be configured by the network device for the terminal device.

[0171] It is understood that if the accuracy of the first information is greater than a first preset value, and / or the similarity between the first information and the second information is greater than a second preset value, it indicates that the performance of the first model is good. Therefore, if the performance of the first model is good, the terminal device reports the first CSI report and the second CSI report, so that the network device is informed of the first CSI obtained based on the first model and the first performance evaluation result of the first model.

[0172] In another optional embodiment, if the accuracy of the first information is less than or equal to a first preset value, and / or the similarity between the first information and the second information is less than or equal to a second preset value, the terminal device reports a second CSI report. Accordingly, the network device receives the second CSI report from the terminal device. The second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information and / or the first CSI.

[0173] If the accuracy of the first information is less than or equal to a first preset value, and / or the similarity between the first information and the second information is less than or equal to a second preset value, it indicates that the performance of the first model is poor. As a result, the accuracy of the first CSI and / or first channel information obtained by the terminal device based on the first model may be poor and cannot be used by the network device. Furthermore, if the performance of the first model is poor, the terminal device reports the second CSI report instead of the first CSI report. If the performance of the first model is poor, the terminal device reports the second CSI instead of the first CSI, which can reduce signaling overhead.

[0174] Optionally, if the network device learns, based on the first performance evaluation result, that the performance of the first model is poor, the network device optimizes the first model using the training data and notifies the terminal device of the optimized first model. Optionally, if the network device learns, based on the first performance evaluation result, that the performance of the first model is poor, the network device instructs the terminal device to terminate use of the first model through instruction information, so that the terminal device no longer uses the first model.

[0175] Implementation method 2: The terminal device determines the second performance evaluation result of the first model based on the third CSI reporting configuration.

[0176] It can be understood that the configuration information includes the third CSI report configuration, and the terminal device determines the performance evaluation result of the first model based on the third CSI report configuration.

[0177] Optionally, the first resource set and the second resource set associated with the third CSI reporting configuration are periodic or semi-periodic resource sets, the first resource set is used to predict channel information and / or CSI using the first model, and the second resource set is used to evaluate the performance of the first model.

[0178] Optionally, if the first resource set associated with the third CSI report configuration is a periodic or semi-periodic resource set, and the second resource set associated with the third CSI report configuration is a non-periodic resource set, the terminal device may, based on predefined rules or protocol specifications, consider that the first resource set is used to predict channel information and / or CSI using the first model, and the second resource set is used to evaluate the performance of the first model.

[0179] Optionally, if the first resource set and the second resource set associated with the third CSI report configuration are non-periodic resource sets, the terminal device may determine, based on predefined rules or protocol specifications, that the first resource set is used to predict channel information and / or CSI using the first model, and the second resource set is used to evaluate the performance of the first model. For example, if the first resource set and the second resource set associated with the third CSI report configuration are non-periodic resource sets, and the time slot offset of the first resource set is less than or equal to a preset value, the terminal device determines that the first resource set is used to predict channel information and / or CSI using the first model; if the first resource set and the second resource set associated with the third CSI report configuration are non-periodic resource sets, and the time slot offset in the second resource set is greater than a preset value, the terminal device determines that the second resource set is used to evaluate the performance of the first model. For another example, if the first resource set and the second resource set associated with the third CSI report configuration are non-periodic resource sets, and the time slot offset of the first resource set is less than or equal to the time slot offset of the second resource set, the first resource set is determined to be used to predict channel information and / or CSI using the first model, and the second resource set is determined to be used to evaluate the performance of the first model.

[0180] Therefore, the terminal device determines the performance evaluation result of the first model based on the third CSI report configuration, including: the terminal device predicts the channel information and / or CSI based on the first resource set and the first model to obtain third information, where the third information is the third CSI and / or third channel information; the terminal device performs performance evaluation on the first model based on the second resource set and the third information to obtain a second performance evaluation result.

[0181] The terminal device predicts channel information and / or CSI based on the first resource set and the first model to obtain third information, including: the terminal device uses resources in the first resource set to receive a first CSI-RS from the network device; the terminal device determines the third information based on the first CSI-RS and / or the first model; the terminal device uses resources in the second resource set to receive a second CSI-RS from the network device, and determines fourth information based on the second CSI-RS; the terminal device compares the third information with the fourth information to obtain a second performance evaluation result of the first model. The fourth information may be fourth CSI and / or fourth channel information.

[0182] It can be seen that the terminal can obtain the fourth information based on the third CSI report configuration and the second resource set.

[0183] If the third information is the third CSI, the fourth information is the fourth CSI; if the third information is the third channel information, the fourth information is the fourth channel information. The fourth CSI or the fourth channel information is obtained by the terminal device based on the second resource set and not using the first model.

[0184] It can be seen that the terminal device obtains the third information based on the first model and the first resource set, and then compares and analyzes the third information and the fourth information to obtain the second performance evaluation result of the first model.

[0185] Optionally, if the third CSI report configuration is associated with the first CSI resource group and the second CSI resource group, the implementation method for the terminal device to determine the second performance evaluation result of the first model can be referred to the implementation method for associating the third CSI report configuration with the first CSI resource set and the second CSI resource set, and the terminal device to determine the second performance evaluation result of the first model, which will not be repeated here.

[0186] It is understandable that the second performance evaluation result can be used to indicate the operating status of the first model, or can be used to indicate the performance of the first model, or can be used to indicate the accuracy of the result obtained based on the first model, or can be used to indicate the performance of the communication link / communication system obtained based on the first model. In the embodiments of the present application, the second performance evaluation result is not specifically limited, that is, other forms are not restricted.

[0187] In an optional embodiment, the second performance evaluation result is represented by the accuracy of the third information and / or the similarity between the third information and the fourth information. Specifically, the representation of the second performance evaluation result is similar to that of the first performance evaluation result and will not be repeated here.

[0188] In an optional manner, the terminal device reports a third CSI report based on the third CSI report configuration, where the third CSI report includes the third CSI and / or the second performance evaluation result and / or the fourth CSI and / or the fourth channel information.

[0189] In an optional implementation, if the accuracy of the third information is greater than a first preset value, and / or the similarity between the third information and the fourth information is greater than a second preset value, the terminal device reports a third CSI report. The third CSI report includes the third CSI and / or the second performance evaluation result and / or the fourth CSI and / or the fourth channel information. The first preset value and the second preset value can be found in the description of Implementation 1 and are not further described.

[0190] It is understandable that if the accuracy of the third information is greater than the first preset value, and / or the similarity between the third information and the fourth information is greater than the second preset value, it indicates that the performance of the first model is better. Thus, the third CSI obtained by the terminal device based on the first model can be used by the network device. Therefore, the terminal device reports the third CSI obtained based on the first model to the network device. Optionally, the terminal device also reports the second performance evaluation result of the first model and / or the fourth CSI and / or the fourth channel information and / or the third CSI, so that the network device is informed of the performance evaluation result of the first model.

[0191] In another optional embodiment, if the accuracy of the third information is less than or equal to the first preset value, and / or the similarity between the third information and the fourth information is less than or equal to the second preset value, the terminal device reports a third CSI report, and the third CSI report includes the second performance evaluation result and / or the fourth CSI and / or the fourth channel information.

[0192] If the accuracy of the third information is less than or equal to a first preset value, and / or the similarity between the third information and the fourth information is less than or equal to a second preset value, this indicates that the performance of the first model is poor. Consequently, the third CSI or third channel information obtained by the terminal device based on the first model may be less accurate and unusable by the network device. Therefore, the terminal device reports the second performance evaluation result of the first model and / or the fourth CSI and / or the fourth channel information, but does not report the third CSI, to save signaling overhead.

[0193] In addition, when the network device determines that the performance of the first model is poor based on the second performance evaluation result, other implementation methods that can be executed can be found in the above implementation method 1 and will not be repeated here.

[0194] Accordingly, the network device receives a third CSI report. If the accuracy of the third information is greater than a first preset value and / or the similarity between the third information and the fourth information is greater than a second preset value, the third CSI report includes the third CSI and / or the second performance evaluation result and / or the fourth CSI and / or the fourth channel information. If the accuracy of the third information is less than or equal to the first preset value and / or the similarity between the third information and the fourth information is less than or equal to the second preset value, the third CSI report includes the second performance evaluation result and / or the fourth CSI and / or the fourth channel information.

[0195] Implementation method 3: The terminal device determines the third performance evaluation result of the first model based on the fourth CSI reporting configuration.

[0196] It is understood that if the configuration information includes a fourth CSI reporting configuration, the terminal device determines a third performance evaluation result for the first model based on the fourth CSI reporting configuration. Specifically, the terminal device performs a performance evaluation on the first model based on resources in the third resource set that are adjacent to the resources used to report the CSI report, and obtains the third performance evaluation result. The fourth CSI reporting configuration is associated with the third resource set.

[0197] The resources used by the terminal device to report the CSI report may be pre-configured by the network device for the terminal device. The resources used by the terminal device to report the CSI report may be resources configured by the network device (e.g., via radio resource control (RRC) signaling and / or media access control (MAC) signaling and / or downlink control information (DCI) information configuration) for the terminal device.

[0198] It is understood that the term "adjacent" is used to describe resources in terms of time. "Resources adjacent to the resources used to report the CSI report" can be understood as "resources that are closest in time to the resources used to report the CSI report."

[0199] It is understandable that the terminal device receives a first CSI-RS from the network device based on all or part of the resources in the third resource set, excluding resources adjacent to the resources used to report the CSI report, and then determines the fifth information based on information obtained from the first CSI-RS and the first model. In addition, the terminal device determines the sixth information based on a second CSI-RS received from the network device in resources in the third resource set adjacent to the resources used to report the CSI report. The terminal device compares the fifth information and the sixth information to obtain a third performance evaluation result of the first model.

[0200] The fifth information is the fifth CSI and / or the fifth channel information. The sixth information is the sixth CSI and / or the sixth channel information. If the fifth information is the fifth CSI, the sixth information is the sixth CSI; if the fifth information is the fifth channel information, the sixth information is the sixth channel information. The fifth CSI or the fifth channel information is obtained by the terminal device using the first model, and the sixth CSI or the sixth channel information is obtained by the terminal device without using the first model.

[0201] Optionally, if the fourth CSI report configuration is associated with the third resource group, the terminal device determines the implementation method of the third performance evaluation result of the first model based on the fourth CSI report configuration. The implementation method is similar to the implementation method of the fourth CSI report configuration being associated with the third resource set, and the terminal device determines the third performance evaluation result of the first model based on the fourth CSI report configuration, and is not repeated here.

[0202] It is understandable that the third performance evaluation result can be used to indicate the operating status of the first model, or can be used to indicate the performance of the first model, or can be used to indicate the accuracy of the results obtained based on the first model, or can be used to indicate the performance of the communication link / communication system obtained based on the first model. In the embodiments of the present application, the third performance evaluation result is not specifically limited, that is, other forms are not restricted.

[0203] In an optional embodiment, the third performance evaluation result is represented by the accuracy of the fifth information and / or the similarity between the fifth information and the sixth information. Specifically, the representation of the third performance evaluation result is similar to that of the first performance evaluation result and will not be repeated here.

[0204] In an optional manner, the terminal device reports the fourth CSI report based on the fourth CSI report configuration, and the fourth CSI report includes the fifth CSI and / or the third performance evaluation result and / or the sixth CSI and / or the sixth channel information.

[0205] In an optional implementation, if the accuracy of the fifth information is greater than a first preset value, and / or the similarity between the fifth information and the sixth information is greater than a second preset value, the terminal device reports a fourth CSI report. The fourth CSI report includes the fifth CSI and / or the third performance evaluation result and / or the sixth CSI and / or the sixth channel information. The first preset value and the second preset value can be found in the description of Embodiment 1 above and are not further described.

[0206] It is understandable that if the accuracy of the fifth information is greater than the first preset value, and / or the similarity between the fifth information and the sixth information is greater than the second preset value, it indicates that the performance of the first model is better. Thus, the fifth CSI obtained by the terminal device based on the first model can be used by the network device. Therefore, the terminal device reports the fifth CSI obtained based on the first model to the network device. Optionally, the terminal device also reports the third performance evaluation result of the first model and / or the sixth CSI and / or the sixth channel information.

[0207] In another optional embodiment, if the accuracy of the fifth information is less than or equal to the first preset value, and / or the similarity between the fifth information and the sixth information is less than or equal to the second preset value, the terminal device reports a fourth CSI report, and the fourth CSI report includes the third performance evaluation result and / or the sixth CSI and / or the sixth channel information.

[0208] It is understandable that if the accuracy of the fifth information is less than or equal to the first preset value, and / or the similarity between the fifth information and the sixth information is less than or equal to the second preset value, it indicates that the performance of the first model is poor. As a result, the accuracy of the fifth information obtained by the terminal device based on the first model may be low and cannot be used by the network device. Therefore, the terminal device reports the third performance evaluation result of the first model and / or the sixth CSI and / or the sixth channel information, but does not report the fifth CSI, to save signaling overhead.

[0209] Accordingly, the network device receives a fourth CSI report. If the accuracy of the fifth information is greater than a first preset value, and / or the similarity between the fifth information and the sixth information is greater than a second preset value, the fourth CSI report includes the fifth CSI and / or the third performance evaluation result and / or the sixth CSI and / or the sixth channel information. If the accuracy of the fifth information is less than or equal to the first preset value, and / or the similarity between the fifth information and the sixth information is less than or equal to the second preset value, the fourth CSI report includes the third performance evaluation result and / or the sixth CSI and / or the sixth channel information.

[0210] As can be seen, in the embodiments of the present application, the terminal device evaluates the performance of the first model based on the configuration information configured by the network device for determining the performance evaluation result of the first model to obtain a performance evaluation result. The first model is a model for predicting channel information and / or CSI, which helps to improve the accuracy of the first model in predicting channel information and / or CSI.

[0211] Referring to FIG. 3 , FIG. 3 is a schematic structural diagram of a communication device 300 provided in an embodiment of the present invention. The communication device 300 may be used in a terminal device.

[0212] In one implementation, the communication device 300 may include:

[0213] A communication unit 301 is configured to receive configuration information for determining a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is configured to predict channel information and / or channel state information (CSI);

[0214] The processing unit 302 is configured to determine a performance evaluation result of the first model based on the configuration information.

[0215] In an optional embodiment, the configuration information includes a first CSI reporting configuration and a second CSI reporting configuration associated with the first CSI reporting configuration; the first CSI reporting configuration is configured to use a first model to predict the channel information and / or the CSI, and the second CSI reporting configuration is configured to evaluate the performance of the first model.

[0216] In an optional embodiment, the processing unit 302 determines the performance evaluation result of the first model based on the configuration information, and is specifically used to: predict the channel information and / or the CSI based on the first CSI report configuration and the first model to obtain first information, where the first information is the first CSI and / or the first channel information; and perform performance evaluation on the first model based on the second CSI report configuration and the first information to obtain a first performance evaluation result.

[0217] In an optional embodiment, the first performance evaluation result is represented by the accuracy of the first information and / or the similarity between the first information and the second information; the second information is obtained by the terminal device without using the first model; the second information is second CSI and / or second channel information.

[0218] In an optional implementation manner, if the first information is the first CSI, if the second information is the second CSI; the first information is the first channel information, and the second information is the second channel information.

[0219] In an optional embodiment, the communication unit 301 is further used to report a first CSI report and a second CSI report, wherein the first CSI report includes the first CSI, and the second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information.

[0220] In another optional embodiment, the communication unit 301 is also used to: if the accuracy of the first information is greater than a first preset value, and / or the similarity between the first information and the second information is greater than a second preset value, report the first CSI report and the second CSI report, the first CSI report including the first CSI, and the second CSI report including the first performance evaluation result and / or the second CSI and / or the second channel information; if the accuracy of the first information is less than or equal to the first preset value, and / or the similarity between the first information and the second information is less than or equal to the second preset value, report the second CSI report.

[0221] In another optional embodiment, the configuration information includes a third CSI report configuration; the third CSI report configuration is associated with a first resource set and a second resource set, the first resource set is used to predict the channel information and / or the CSI using the first model, and the second resource set is used to evaluate the performance of the first model.

[0222] In an optional embodiment, the processing unit 302 determines the performance evaluation result of the first model based on the configuration information, and is specifically used to: predict the channel information and / or the CSI based on the first resource set and the first model to obtain third information, where the third information is third CSI and / or third channel information; and perform performance evaluation on the first model based on the second resource set and the third information to obtain a second performance evaluation result.

[0223] In an optional embodiment, the second performance evaluation result is represented by the accuracy of the third information, and / or, by the similarity between the third information and the fourth information; the fourth information is obtained by the terminal device based on the second resource set and not using the first model; the fourth information is the fourth CSI and / or the fourth channel information.

[0224] In an optional implementation, if the third information is the third CSI, the fourth information is the fourth CSI; if the third information is the third channel information, the fourth information is the fourth channel information.

[0225] In an optional embodiment, the first resource set and the second resource set are periodic or semi-persistent resource sets; or, the first resource set is a periodic or semi-persistent resource set, and the second resource set is a non-periodic resource set; or, the first resource set and the second resource set are non-periodic resource sets.

[0226] In an optional embodiment, the communication unit 301 is also used to report a third CSI report; if the accuracy of the third information is greater than a first preset value, and / or the similarity between the third information and the fourth information is greater than a second preset value, the third CSI report includes the third CSI and / or the second performance evaluation result and / or the fourth CSI and / or the fourth channel information.

[0227] In an optional embodiment, if the accuracy of the third information is less than or equal to the first preset value, and / or the similarity between the third information and the fourth information is less than or equal to the second preset value, the third CSI report includes the second performance evaluation result and / or the fourth CSI and / or the fourth channel information.

[0228] In another optional implementation, the configuration information includes a fourth CSI reporting configuration, the fourth CSI reporting configuration is associated with a third resource set, and the third resource set is used to perform performance evaluation on the first model.

[0229] In another optional embodiment, the processing unit 302 determines the performance evaluation result of the first model based on the configuration information, and is specifically used to: perform a performance evaluation on the first model based on the resources in the third resource set that are adjacent to the resources used for reporting the CSI report, and obtain a third performance evaluation result; the third resource set is a periodic or semi-continuous periodic resource set, or a non-periodic resource set.

[0230] In an optional embodiment, the third performance evaluation result is represented by the accuracy of the fifth information, and / or, by the similarity between the fifth information and the sixth information; the fifth information is the fifth CSI and / or the fifth channel information; the fifth information is obtained by the terminal device using the first model, and the sixth information is obtained by the terminal device not using the first model; the sixth information is the sixth CSI and / or the sixth channel information.

[0231] In an optional implementation, if the fifth information is the fifth CSI, the sixth information is the sixth CSI; if the fifth information is the fifth channel information, the sixth information is the sixth channel information.

[0232] In an optional embodiment, the communication unit 301 is also used to report a fourth CSI report; if the accuracy of the fifth information is greater than a first preset value, and / or the similarity between the fifth information and the sixth information is greater than a second preset value, the fourth CSI report includes the fifth CSI and / or the third performance evaluation result and / or the sixth CSI and / or the sixth channel information.

[0233] In an optional embodiment, if the accuracy of the fifth information is less than or equal to the first preset value, and / or the similarity between the fifth information and the sixth information is less than or equal to the second preset value, the fourth CSI report includes the third performance evaluation result and / or the sixth CSI and / or the sixth channel information.

[0234] The embodiments of the present application and the above-mentioned method embodiments are based on the same concept, and the technical effects they bring are also the same. For the specific principles, please refer to the description of the above-mentioned method embodiments, which will not be repeated here.

[0235] Referring to FIG. 4 , FIG. 4 is a schematic structural diagram of a communication device 400 provided in an embodiment of the present invention. The communication device 400 may be used in a network device.

[0236] In one implementation, the communication device 400 may include:

[0237] A determining unit 401 is configured to determine configuration information used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information (CSI);

[0238] The communication unit 402 is configured to send the configuration information.

[0239] In an optional embodiment, the configuration information includes a first CSI reporting configuration and a second CSI reporting configuration associated with the first CSI reporting configuration; the first CSI reporting configuration is configured to use the first model to predict the channel information and / or the CSI, and the second CSI reporting configuration is configured to evaluate the performance of the first model.

[0240] In an optional embodiment, the communication unit 402 is also used to receive a first CSI report and a second CSI report, wherein the first CSI report includes a first CSI, and the second CSI report includes a first performance evaluation result and / or a second CSI and / or second channel information; the first CSI is obtained by the terminal device predicting the channel information and / or the CSI based on the first CSI report configuration and the first model; the first performance evaluation result is obtained by the terminal device performing a performance evaluation on the first model based on the second CSI report configuration and the first CSI; the second CSI or the second channel information is obtained by the terminal device without using the first model.

[0241] In another optional embodiment, the communication unit 402 is also used to receive a second CSI report, where the second CSI report includes a first performance evaluation result and / or a second CSI and / or second channel information; the first performance evaluation result is obtained by the terminal device performing a performance evaluation on the first model based on the second CSI report configuration and the first CSI; the first CSI is obtained by the terminal device predicting the channel information and / or the CSI based on the first CSI report configuration and the first model; the second CSI or the second channel information is obtained by the terminal device without using the first model.

[0242] In an optional embodiment, the first performance evaluation result is represented by the accuracy of the first information, and / or, by the similarity between the first information and the second information; the first information is the first CSI and / or the first channel information, and the first channel information is obtained by the terminal device by predicting the channel information and / or the CSI based on the first CSI report configuration and the first model; the second information is obtained by the terminal device without using the first model; the second information is the second CSI and / or the second channel information.

[0243] In an optional implementation, if the first information is the first CSI, the second information is the second CSI; if the first information is the first channel information, the second information is the second channel information.

[0244] In another optional embodiment, the configuration information includes a third CSI report configuration, and the third CSI report configuration is associated with the first resource set and the second resource set; the first resource set is used to use the first model to predict the channel information and / or the CSI, and the second resource set is used to evaluate the performance of the first model.

[0245] In an optional embodiment, the first resource set and the second resource set are periodic or semi-persistent resource sets; or, the first resource set is a periodic or semi-persistent resource set, and the second resource set is a non-periodic resource set; or, the first resource set and the second resource set are non-periodic resource sets.

[0246] In an optional embodiment, the communication unit 402 is also used to receive a third CSI report; the third CSI includes the third CSI and / or the second performance evaluation result and / or the fourth CSI and / or the fourth channel information, or the third CSI report includes the second performance evaluation result and / or the fourth CSI and / or the fourth channel information; the third CSI is obtained by the terminal device based on the first resource set and the first model by predicting the channel information and / or the CSI; the second performance evaluation result is obtained by the terminal device based on the second resource set and the third CSI by performing a performance evaluation on the first model; the fourth CSI or the fourth channel information is obtained by the terminal device based on the second resource set and the third CSI.

[0247] In an optional embodiment, the second performance evaluation result is represented by the accuracy of the third information, and / or, by the similarity between the third information and the fourth information; the third information is the third CSI and / or third channel information; the third channel information is obtained by the terminal device based on the first resource set and the first model by predicting the channel information and / or the CSI; the fourth information is obtained by the terminal device based on the second resource set and without using the first model; the fourth information is the fourth CSI and / or fourth channel information.

[0248] In an optional implementation, if the third information is the third CSI, the fourth information is the fourth CSI; if the third information is the third channel information, the fourth information is the fourth channel information.

[0249] In another optional implementation, the configuration information includes a fourth CSI report configuration, and the fourth CSI report configuration is associated with a third resource set; the third resource set is a periodic or semi-periodic resource set, or a non-periodic resource set.

[0250] In an optional embodiment, the communication unit 402 is further used to receive a fourth CSI report; the fourth CSI report includes the fifth CSI and / or the third performance evaluation result and / or the sixth CSI and / or the sixth channel information; or, the fourth CSI report includes the third performance evaluation result and / or the sixth CSI and / or the sixth channel information; the fifth CSI or the fifth channel information is obtained by the terminal device predicting the channel information and / or the CSI based on the fourth CSI report configuration and the first model; the third performance evaluation result is obtained by the terminal device performing a performance evaluation on the first model based on the fourth CSI report configuration; the sixth CSI or the sixth channel information is obtained by the terminal device without using the first model.

[0251] In an optional embodiment, the third performance evaluation result is represented by the accuracy of the fifth information, and / or, by the similarity between the fifth information and the sixth information; the fifth information is the fifth CSI and / or the fifth channel information; the fifth information is obtained by the terminal device using the first model, and the sixth information is obtained by the terminal device not using the first model; the sixth information is the sixth CSI and / or the sixth channel information.

[0252] In an optional implementation, if the fifth information is the fifth CSI, the sixth information is the sixth CSI; if the fifth information is the fifth channel information, the sixth information is the sixth channel information.

[0253] The embodiments of the present application and the above-mentioned method embodiments are based on the same concept, and the technical effects they bring are also the same. For the specific principles, please refer to the description of the above-mentioned method embodiments, which will not be repeated here.

[0254] Please refer to Figure 5, which is a schematic diagram of the structure of a communication device 500 provided in an embodiment of the present application. The communication device 500 can be a terminal device or a network device. The communication device 500 may include a memory 501 and a processor 502. Optionally, it also includes a communication interface 503. The memory 501, processor 502, and communication interface 503 are connected via one or more communication buses. The communication interface 503 is controlled by the processor 502 to send and receive information.

[0255] The memory 501 may include a read-only memory and a random access memory, and provides instructions and data to the processor 502. A portion of the memory 501 may also include a nonvolatile random access memory.

[0256] The communication interface 503 is used to receive or send data.

[0257] The processor 502 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor, or alternatively, the processor 502 may be any conventional processor. Specifically:

[0258] The memory 501 is used to store program instructions.

[0259] The processor 502 is configured to call the program instructions stored in the memory 501 .

[0260] In an optional implementation, when the processor 502 calls the computer program, it is configured to execute:

[0261] receiving configuration information for determining a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information (CSI);

[0262] Based on the configuration information, a performance evaluation result of the first model is determined.

[0263] In another optional implementation, when the processor 502 calls the computer program, it is configured to execute:

[0264] Determining configuration information, where the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information (CSI);

[0265] The configuration information is sent.

[0266] For other implementations of the communication device, please refer to the relevant contents of the above method embodiment, which will not be described in detail here.

[0267] The embodiments of the present application and the above-mentioned method embodiments are based on the same concept, and the technical effects they bring are also the same. For the specific principles, please refer to the description of the above-mentioned method embodiments, which will not be repeated here.

[0268] The present application also provides a chip that can execute the steps of the terminal device or network device described in the aforementioned method embodiment. The chip includes a processor and a communication interface, wherein the communication interface is used to receive or send data;

[0269] In one embodiment, the chip performs the relevant steps in the aforementioned method embodiment:

[0270] The processor is configured to enable the chip to perform the following operations: receiving configuration information, wherein the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information CSI; based on the configuration information, determining a performance evaluation result of the first model.

[0271] In another embodiment, the chip performs the relevant steps in the aforementioned method embodiment:

[0272] The processor is configured to enable the chip to perform the following operations: determine configuration information, wherein the configuration information is used to determine a performance evaluation result of a first model, wherein the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information CSI; and send the configuration information.

[0273] For other implementations of the chip, please refer to the relevant contents of the above method embodiment, which will not be described in detail here.

[0274] The embodiments of the present application and the above-mentioned method embodiments are based on the same concept, and the technical effects they bring are also the same. For the specific principles, please refer to the description of the above-mentioned method embodiments, which will not be repeated here.

[0275] For each device or product applied to or integrated in the chip, each module contained therein can be implemented in the form of hardware such as circuits, or at least some of the modules can be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules can be implemented in the form of hardware such as circuits.

[0276] As shown in Figure 6, Figure 6 is a schematic diagram of the structure of a module device provided in an embodiment of the present application. The module device 600 can execute the relevant steps of the terminal device or network device in the aforementioned method embodiment, and the module device 600 includes: a communication module 601, a power module 602, a storage module 603 and a chip 604.

[0277] Among them, the power module 602 is used to provide power to the module device; the storage module 603 is used to store data and instructions; the communication module 601 is used for internal communication within the module device, or for communication between the module device and external devices; the chip 604 is used to execute the method executed by the terminal device or network device in the above method embodiment.

[0278] The implementation of the module device can refer to the relevant content of the above method embodiment, which will not be described in detail here.

[0279] The embodiments of the present application and the above-mentioned method embodiments are based on the same concept, and the technical effects they bring are also the same. For the specific principles, please refer to the description of the above-mentioned method embodiments, which will not be repeated here.

[0280] An embodiment of the present application also provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is executed on a processor, the method flow of the above method embodiment is implemented.

[0281] An embodiment of the present application further provides a computer program product. When the computer program product is run on a processor, the method flow of the above method embodiment is implemented.

[0282] Regarding the various modules / units contained in the various devices and products described in the above embodiments, they can be software modules / units, hardware modules / units, or partly software modules / units and partly hardware modules / units. For example, for various devices and products applied to or integrated into a chip, the various modules / units contained therein can all be implemented in the form of hardware such as circuits, or at least some of the modules / units can be implemented in the form of software programs, which run on the integrated processor inside the chip, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated into a chip module, the various modules / units contained therein can all be implemented in the form of hardware such as circuits, and different modules / units can be located in the same part of the chip module (such as a chip, circuit module, etc.) or in different components, or at least some of the modules / units can be implemented in the form of software programs. It can be implemented in the form of a software program, which runs on the processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated in the terminal, the modules / units contained therein can all be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal, or, at least some modules / units can be implemented in the form of a software program, which runs on the processor integrated inside the terminal, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits.

[0283] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain operations can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0284] The descriptions of the various embodiments provided in this application can refer to each other. The descriptions of each embodiment have their own focus. For parts not described in detail in a particular embodiment, please refer to the relevant descriptions of other embodiments. For the convenience and brevity of description, for example, the functions and operations performed by the various devices and equipment provided in the embodiments of this application can refer to the relevant descriptions of the method embodiments of this application. The various method embodiments and the various device embodiments can also refer to, be combined with, or quote each other.

[0285] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A communication method, characterized in that: The method comprises: receiving configuration information, where the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information CSI; Based on the configuration information, a performance evaluation result of the first model is determined.

2. The method according to claim 1, characterized in that The configuration information includes a first CSI report configuration, and a second CSI report configuration associated with the first CSI report configuration; The first CSI reporting configuration is configured to adopt a first model to predict the channel information and / or the CSI, and the second CSI reporting configuration is configured to evaluate the performance of the first model.

3. The method according to claim 2, characterized in that The determining, based on the configuration information, a performance evaluation result of the first model includes: Predicting the channel information and / or the CSI based on the first CSI report configuration and the first model to obtain first information, where the first information is first CSI and / or first channel information; Based on the second CSI report configuration and the first information, a performance evaluation is performed on the first model to obtain a first performance evaluation result.

4. The method according to claim 3, characterized in that: The first performance evaluation result is represented by the accuracy of the first information and / or the similarity between the first information and the second information; The second information is obtained by the terminal device without using the first model; The second information is second CSI and / or second channel information.

5. The method according to claim 4, characterized in that If the first information is the first CSI, the second information is the second CSI; if the first information is the first channel information, the second information is the second channel information.

6. The method according to claim 3, or 4, or 5, characterized in that: The method further comprises: A first CSI report and a second CSI report are reported, wherein the first CSI report includes the first CSI, and the second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information.

7. The method according to claim 4 or 5, characterized in that: The method further comprises: If the accuracy of the first information is greater than a first preset value, and / or the similarity between the first information and the second information is greater than a second preset value, the first CSI report and the second CSI report are reported, and the first CSI report includes The first CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information.

8. The method according to claim 4 or 5, characterized in that: The method further comprises: If the accuracy of the first information is less than or equal to the first preset value, and / or the similarity between the first information and the second information is less than or equal to the second preset value, report a second CSI report, and the second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information.

9. The method according to claim 1, characterized in that: The configuration information includes a third CSI report configuration; The third CSI reporting configuration is associated with a first resource set and a second resource set, the first resource set is used to predict the channel information and / or the CSI using the first model, and the second resource set is used to evaluate the performance of the first model.

10. The method according to claim 9, characterized in that The determining, based on the configuration information, a performance evaluation result of the first model includes: Predicting the channel information and / or the CSI based on the first resource set and the first model to obtain third information, where the third information is third CSI and / or third channel information; Based on the second resource set and the third information, a performance evaluation is performed on the first model to obtain a second performance evaluation result.

11. The method according to claim 10, characterized in that The second performance evaluation result is represented by the accuracy of the third information and / or the similarity between the third information and the fourth information; The fourth information is obtained by the terminal device based on the second resource set without using the first model; The fourth information is fourth CSI and / or fourth channel information.

12. The method according to claim 11, characterized in that If the third information is the third CSI, the fourth information is the fourth CSI; if the third information is the third channel information, the fourth information is the fourth channel information.

13. The method according to any one of claims 9 to 12, characterized in that: The first resource set and the second resource set are periodic or semi-persistent resource sets; or, The first resource set is a periodic or semi-persistent resource set, and the second resource set is a non-periodic resource set; or, The first resource set and the second resource set are non-periodic resource sets.

14. The method according to claim 9, characterized in that The method further comprises: Submit the third CSI report; If the accuracy of the third information is greater than a first preset value, and / or the similarity between the third information and the fourth information is greater than a second preset value, the third CSI report includes the third CSI and / or the second performance evaluation result and / or the fourth CSI and / or the fourth channel information.

15. The method according to claim 14, characterized in that If the accuracy of the third information is less than or equal to the first preset value, and / or the similarity between the third information and the fourth information is less than or equal to the second preset value, the third CSI report includes the second performance evaluation result and / or the fourth CSI and / or the fourth channel information.

16. The method according to claim 1, characterized in that The configuration information includes a fourth CSI report configuration, where the fourth CSI report configuration is associated with a third resource set, and the third resource set is used to perform performance evaluation on the first model.

17. The method according to claim 16, characterized in that The determining, based on the configuration information, a performance evaluation result of the first model includes: Based on resources in the third resource set that are adjacent to the resources used to report the CSI report, performing performance evaluation on the first model to obtain a third performance evaluation result; The third resource set is a periodic or semi-persistent periodic resource set, or a non-periodic resource set.

18. The method according to claim 17, characterized in that The third performance evaluation result is represented by the accuracy of the fifth information, and / or represented by the similarity between the fifth information and the sixth information; The fifth information is the fifth CSI and / or the fifth channel information, and the fifth information is obtained by the terminal device using the first model. The sixth information is obtained by the terminal device not using the first model, and the sixth information is the sixth CSI and / or the sixth channel information.

19. The method according to claim 18, characterized in that If the fifth information is the fifth CSI, the sixth information is the sixth CSI; if the fifth information is the fifth channel information, the sixth information is the sixth channel information.

20. The method according to claim 18 or 19, characterized in that The method further comprises: Submit the fourth CSI report; If the accuracy of the fifth information is greater than a first preset value, and / or the similarity between the fifth information and the sixth information is greater than a second preset value, the fourth CSI report includes the fifth CSI and / or the third performance evaluation result and / or the sixth CSI and / or the sixth channel information.

21. The method according to claim 20, characterized in that If the accuracy of the fifth information is less than or equal to the first preset value, and / or the similarity between the fifth information and the sixth information is less than or equal to the second preset value, the fourth CSI report includes the third performance evaluation result and / or the sixth CSI and / or the sixth channel information.

22. A communication method, characterized in that: The method comprises: Determine configuration information, where the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information CSI; The configuration information is sent.

23. The method according to claim 22, characterized in that The configuration information includes a first CSI report configuration, and a second CSI report configuration associated with the first CSI report configuration; The first CSI reporting configuration is configured to adopt the first model to predict the channel information and / or the CSI, and the second CSI reporting configuration is configured to evaluate the performance of the first model.

24. The method according to claim 23, characterized in that The method further comprises: receiving a first CSI report and a second CSI report, wherein the first CSI report includes the first CSI, and the second CSI report includes the first performance evaluation result and / or the second CSI and / or the second channel information; The first CSI is obtained by the terminal device predicting the channel information and / or the CSI based on the first CSI report configuration and the first model; the first performance evaluation result is obtained by the terminal device performing a performance evaluation on the first model based on the second CSI report configuration and the first CSI; the second CSI or the second channel information is obtained by the terminal device without using the first model.

25. The method according to claim 23, characterized in that The method further comprises: receiving a second CSI report, where the second CSI report includes a first performance evaluation result and / or a second CSI and / or second channel information; The first performance evaluation result is obtained by the terminal device performing performance evaluation on the first model based on the second CSI report configuration and the first CSI; the first CSI is obtained by the terminal device predicting the channel information and / or the CSI based on the first CSI report configuration and the first model; the second CSI or the second channel information is obtained by the terminal device without using the first model.

26. The method according to claim 24 or 25, characterized in that The first performance evaluation result is represented by the accuracy of the first information, and / or the first information and the second Similarity representation of information; The first information is the first CSI and / or first channel information, and the first channel information is obtained by the terminal device predicting the channel information and / or the CSI based on the first CSI report configuration and the first model; The second information is obtained by the terminal device without using the first model; the second information is second CSI and / or second channel information.

27. The method according to claim 26, characterized in that If the first information is the first CSI, the second information is the second CSI; if the first information is the first channel information, the second information is the second channel information.

28. The method according to claim 22, characterized in that The configuration information includes a third CSI report configuration, where the third CSI report configuration is associated with the first resource set and the second resource set; The first resource set is used to predict the channel information and / or the CSI using a first model, and the second resource set is used to evaluate the performance of the first model.

29. The method according to claim 28, characterized in that The first resource set and the second resource set are periodic or semi-persistent resource sets; or, The first resource set is a periodic or semi-persistent resource set, and the second resource set is a non-periodic resource set; or, The first resource set and the second resource set are non-periodic resource sets.

30. The method according to claim 28 or 29, characterized in that The method further comprises: receiving a third CSI report; The third CSI includes the third CSI and / or the second performance evaluation result and / or the fourth CSI and / or the fourth channel information, or the third CSI report includes the second performance evaluation result and / or the fourth CSI and / or the fourth channel information; The third CSI is obtained by the terminal device predicting the channel information and / or the CSI based on the first resource set and the first model; the second performance evaluation result is obtained by the terminal device performing performance evaluation on the first model based on the second resource set and the third CSI; The fourth CSI or the fourth channel information is obtained by the terminal device based on the second resource set and without adopting the first model.

31. The method according to claim 30, characterized in that The second performance evaluation result is represented by the accuracy of the third information, and / or represented by the similarity between the third information and the fourth information; The third information is the third CSI and / or third channel information; The third channel information is obtained by the terminal device predicting the channel information and / or the CSI based on the first resource set and the first model; The fourth information is obtained by the terminal device based on the second resource set and without adopting the first model; the fourth information is the fourth CSI and / or the fourth channel information.

32. The method according to claim 31, characterized in that If the third information is the third CSI, the fourth information is the fourth CSI; if the third information is the third channel information, the fourth information is the fourth channel information.

33. The method according to claim 22, characterized in that The configuration information includes a fourth CSI report configuration, the fourth CSI report configuration is associated with a third resource set, and the third resource set is used to perform performance evaluation on the first model; The third resource set is a periodic or semi-persistent periodic resource set, or a non-periodic resource set.

34. The method according to claim 33, characterized in that The method further comprises: receiving a fourth CSI report; The fourth CSI report includes the fifth CSI and / or the third performance evaluation result and / or the sixth CSI and / or the sixth channel information; or, the fourth CSI report includes the third performance evaluation result and / or the sixth CSI and / or the sixth channel information; The fifth CSI or the fifth channel information is obtained by the terminal device predicting the channel information and / or the CSI based on the fourth CSI report configuration and the first model; the third performance evaluation result is obtained by the terminal device performing a performance evaluation on the first model based on the fourth CSI report configuration; the sixth CSI or the sixth channel information is obtained by the terminal device without using the first model.

35. The method according to claim 34, characterized in that The third performance evaluation result is represented by the accuracy of the fifth information, and / or represented by the similarity between the fifth information and the sixth information; The fifth information is the fifth CSI and / or the fifth channel information; The fifth information is obtained by the terminal device using the first model, the sixth information is obtained by the terminal device not using the first model, and the sixth information is the sixth CSI and / or the sixth channel information.

36. The method according to claim 35, characterized in that If the fifth information is the fifth CSI, the sixth information is the sixth CSI; if the fifth information is the fifth channel information, the sixth information is the sixth channel information.

37. A communication device, characterized in that: The device comprises: a communication unit, configured to receive configuration information, wherein the configuration information is used to determine a performance evaluation result of a first model, wherein the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel status; State information CSI; A determining unit is used to determine a performance evaluation result of the first model based on the configuration information.

38. A communication device, characterized in that: The device comprises: a determining unit, configured to determine configuration information, where the configuration information is used to determine a performance evaluation result of a first model, where the first model is an artificial intelligence model or a machine learning model, and the first model is used to predict channel information and / or channel state information CSI; A communication unit is used to send the configuration information.

39. A terminal device, characterized in that: The terminal device includes a processor and a memory, and the processor and the memory are connected to each other, wherein the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 21.

40. A network device, characterized in that: The network device includes a processor and a memory, which are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 22 to 36.

41. A chip, characterized in that: The method comprises a processor and a communication interface, wherein the processor is configured to cause the chip to execute the method according to any one of claims 1 to 21, or is configured to cause the chip to execute the method according to any one of claims 22 to 36.

42. A module device, characterized in that: The module device includes a communication module, a power module, a storage module and a chip, wherein: The power module is used to provide electrical energy to the module device; The storage module is used to store data and instructions; The communication module is used for internal communication of the module device, or for communication between the module device and an external device; The chip is used to execute the method according to any one of claims 1 to 21, or to execute the method according to any one of claims 22 to 36.

43. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed on the communication device, the communication device executes the method described in any one of claims 1 to 21, or executes the method described in any one of claims 22 to 36.

Images