Communication method and apparatus

Abstract

The present application provides a communication method and apparatus for improving the reliability of AI-based CSI prediction. The method includes: a terminal device receiving first information, the first information indicating a usage of a first channel state information (CSI) resource, the usage of the CSI resource including at least one of CSI information collection, artificial intelligence (AI) model performance monitoring, and AI model inference; and a terminal device transmitting first CSI information based on the first information and / or a terminal device monitoring the performance of an AI model based on the first information, the first CSI information corresponding to the first CSI resource.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to Chinese Patent Application No. 202211721001.6, entitled "Communication Method and Apparatus," filed with the State Intellectual Property Office of the People's Republic of China on December 30, 2022, the entire contents of which are incorporated herein by reference.

[0002] The present application relates to the field of mobile communication technologies, and in particular to communication methods and devices. [Background technology]

[0003] 5th generation (5 th In a 5G (5th generation) mobile communication system, a network device needs to obtain channel-state information (CSI) between a terminal device and the network device, and perform resource scheduling for uplink or downlink data transmission based on the CSI.

[0004] Artificial intelligence (AI)-enhanced CSI feedback mechanisms are being considered in the 3rd generation partnership project (3GPP®) Release 18 standard discussion. AI-based CSI prediction is a candidate case. In the AI-based CSI prediction process, some past CSI information and / or current CSI information may be input into an AI prediction model to output a predicted future CSI.

[0005] However, currently, a terminal device cannot clearly know the specific CSI resources used to predict future CSI and the specific CSI resources used to measure CSI information, and therefore the terminal device may misprocess the CSI resources, which results in the AI-based CSI prediction mechanism not functioning properly and reduces the reliability of CSI prediction. Summary of the Invention [Means for solving the problem]

[0006] The present application provides a communication method and apparatus for improving the reliability of AI-based CSI prediction.

[0007] According to a first aspect, a communication method is provided. The method may be performed by a terminal device or a component within the terminal device, and the terminal device may also be referred to as a communication device. The component in this application may include, for example, at least one of a chip, a chip system, a processor, a transceiver, a processing unit, or a transceiver unit. An example in which the execution entity is a terminal device is used. The method may be performed by using the following steps: a step in which the terminal device receives first information, the first information indicating a usage of a first channel state information (CSI) resource, the CSI resource usage including at least one of the following: CSI information collection, artificial intelligence (AI) model performance monitoring, and AI model inference; and a step in which the terminal device transmits first CSI information based on the first information and / or a step in which the terminal device monitors the performance of the AI ​​model based on the first information, the first CSI information corresponding to the first CSI resource.

[0008] According to the method of the first aspect, the terminal device may know the use of the CSI information based on the first information from the network device, and thus may know which CSI resources may be used to predict the CSI information in order to avoid using the CSI resources for incorrect purposes. Thus, the reliability of the CSI prediction may be improved.

[0009] In a possible implementation, the AI ​​model is used for CSI prediction.

[0010] In a possible implementation, if the application includes AI model inference, the first CSI information includes CSI information predicted based on the first CSI resource and the AI ​​model; if the application includes CSI information collection or AI model performance monitoring, the first CSI information includes CSI measurement results obtained by measuring the first CSI resource; or if the application includes AI model performance monitoring, the first CSI information includes monitoring results of the AI ​​model, and the monitoring results indicate the accuracy of the prediction results of the AI ​​model.

[0011] According to this implementation, the terminal device may determine predicted CSI information based on a first CSI resource whose use includes AI model inference, acquire CSI measurement results based on the first CSI resource whose use includes CSI information collection or AI model performance monitoring, and use the CSI measurement results as the first CSI information, or acquire monitoring results based on the first CSI resource whose use includes AI model performance monitoring, and use the monitoring results as the first CSI information. Therefore, to further improve the accuracy of the prediction, appropriate CSI information may be fed back to the network device based on the use.

[0012] In a possible implementation, the terminal device transmits capability information, which includes at least one of the following: information indicating whether the terminal device supports CSI prediction, information regarding requirements for an AI model of the terminal device for the periodicity of input CSI information, information regarding requirements for an AI model of the terminal device for the amount of input CSI information, information regarding a time point of predicted CSI information output by the AI ​​model of the terminal device, information regarding requirements for an AI model of the terminal device for frequency-domain attributes of the input CSI information, information regarding frequency-domain attributes of CSI information that can be output by the AI ​​model of the terminal device, information regarding requirements for an AI model of the terminal device for dimensions of input and / or output CSI information, information regarding requirements for an AI model of the terminal device for types of input and / or output CSI information, and information regarding requirements for an AI model of the terminal device for reference signals used for CSI information measurement.

[0013] According to this implementation, the network device may determine the usage indication of the CSI resource by referring to the capability information of the terminal device to improve the accuracy of the usage configuration.

[0014] In a possible implementation, the first information may further indicate a compression configuration of the CSI information. The terminal device may transmit the first CSI information based on the compression configuration.

[0015] According to this implementation, the first information may further indicate a compression configuration. The network device may configure different CSI compression schemes based on different requirements for performance and complexity. Thus, flexible configuration of compression schemes can be implemented.

[0016] In a possible implementation, the first information may specifically indicate the usage of CSI resources in a first resource group, and the CSI resources in the first resource group include the first CSI resource.

[0017] According to this implementation, the usage of CSI resources may be configured by groups, thus implementing flexible configuration of usage at multiple granularities.

[0018] In a possible implementation, the first information further indicates a usage of second CSI resources in the first resource group, where the usage of the second CSI resources is different from that of the first CSI resources.

[0019] According to this implementation, to improve the flexibility of resource configuration, the usage of different CSI resources within the same resource group may be different.

[0020] In a possible implementation, the CSI resources in the first resource group and the CSI resources in the second resource group are jointly used, and the usage of the CSI resources in the second resource group is the same as the usage of the CSI resources in the first resource group.

[0021] According to this implementation, joint use of multiple groups of CSI resources having the same purpose may be supported. For example, multiple groups of resources whose purpose includes AI model inference may be jointly used for CSI information prediction to improve prediction performance.

[0022] In a possible implementation, the CSI resources in the first resource group and the CSI resources in the second resource group correspond to the same CSI reporting configuration, the CSI resources in the first resource group and the CSI resources in the second resource group are associated with the same AI model, or the CSI resources in the first resource group and the CSI resources in the second resource group have a quasi-colocated QCL relationship.

[0023] According to this implementation, the CSI resources that need to be jointly used may be flexibly determined.

[0024] In a possible implementation, the terminal device receives second information indicating that the CSI resources in the first resource group and the CSI resources in the second resource group are jointly used.

[0025] According to this implementation, the CSI resources that need to be jointly used can be flexibly indicated.

[0026] In a possible implementation, the first information specifically indicates a CSI resource pattern, and the CSI resource pattern is used to determine time-domain locations of CSI resources whose uses are at least one of CSI information collection, AI model performance monitoring, and AI model inference.

[0027] According to this implementation, the usage of CSI resources can be flexibly indicated.

[0028] In a possible implementation, the first information further indicates at least one of the following: a predicted configuration of the AI ​​model and the CSI information.

[0029] According to this implementation, the same signaling may indicate the prediction configuration of the AI ​​model and / or CSI information and indicate the usage of CSI resources, thereby reducing signaling overhead.

[0030] According to a second aspect, a communication method is provided. The method may be performed by a network device or a component within the network device, and the network device may also be referred to as a communication device. The component in this application may include, for example, at least one of a chip, a chip system, a processor, a transceiver, a processing unit, or a transceiver unit. An example in which the execution entity is the network device is used. The method may be performed by the network device using the following steps: transmitting first information to a terminal device, the first information indicating first channel state information (CSI) resource usage, the CSI resource usage including at least one of the following: CSI information collection, artificial intelligence (AI) model performance monitoring, and AI model inference.

[0031] In a possible implementation, the network device may further receive first CSI information from the terminal device, the first CSI information corresponding to the first CSI resource.

[0032] In a possible implementation, the AI ​​model is used for CSI prediction.

[0033] In a possible implementation, if the application includes AI model inference, the first CSI information includes CSI information predicted based on the first CSI resource and the AI ​​model; if the application includes CSI information collection or AI model performance monitoring, the first CSI information includes CSI measurement results obtained by measuring the first CSI resource; or if the application includes AI model performance monitoring, the first CSI information includes monitoring results of the AI ​​model, and the monitoring results indicate the accuracy of the prediction results of the AI ​​model.

[0034] In a possible implementation, the network device may further receive capability information of the terminal device, which includes at least one of the following: information indicating whether the terminal device supports CSI prediction, information regarding requirements for an AI model of the terminal device for the periodicity of input CSI information, information regarding requirements for an AI model of the terminal device for the amount of input CSI information, information regarding a time point of predicted CSI information output by the AI ​​model of the terminal device, information regarding requirements for an AI model of the terminal device for frequency-domain attributes of the input CSI information, information regarding frequency-domain attributes of CSI information that can be output by the AI ​​model of the terminal device, information regarding requirements for an AI model of the terminal device for dimensions of input and / or output CSI information, information regarding requirements for an AI model of the terminal device for types of input and / or output CSI information, and information regarding requirements for an AI model of the terminal device for reference signals used for CSI information measurement.

[0035] In a possible implementation, the first information further indicates a compression configuration of the CSI information.

[0036] In a possible implementation, the first information specifically indicates the usage of CSI resources in a first resource group, and the CSI resources in the first resource group include the first CSI resource.

[0037] In a possible implementation, the first information further indicates a usage of second CSI resources in the first resource group, where the usage of the second CSI resources is different from that of the first CSI resources.

[0038] In a possible implementation, the CSI resources in the first resource group and the CSI resources in the second resource group are jointly used, and the usage of the CSI resources in the second resource group is the same as the usage of the CSI resources in the first resource group.

[0039] In a possible implementation, the CSI resources in the first resource group and the CSI resources in the second resource group correspond to the same CSI reporting configuration, the CSI resources in the first resource group and the CSI resources in the second resource group are associated with the same AI model, or the CSI resources in the first resource group and the CSI resources in the second resource group have a quasi-colocated QCL relationship.

[0040] In a possible implementation, the network device transmits second information, where the second information indicates that the CSI resources in the first resource group and the CSI resources in the second resource group are jointly used.

[0041] In a possible implementation, the first information specifically indicates a CSI resource pattern, and the CSI resource pattern is used to determine time-domain locations of CSI resources whose uses are at least one of CSI information collection, AI model performance monitoring, and AI model inference.

[0042] In a possible implementation, the first information further indicates at least one of the following: a predicted configuration of the AI ​​model and the CSI information.

[0043] According to a third aspect, there is provided a communication device. The device may perform the method according to the first or second aspect and any possible design thereof. The device has the functionality of the network device or terminal device described above. The device may be, for example, a terminal device, a functional module in a terminal device, a network device, or a functional module in a network device.

[0044] In an optional implementation, the apparatus may include modules that perform and correspond one-to-one to the methods / operations / steps / actions described in the first or second aspect. The modules may be hardware circuits, software, or hardware circuits in combination with software. In an optional implementation, the apparatus includes a processing unit (also referred to as a processing module) and a communication unit (also referred to as a transceiver module, communication module, etc.). The transceiver unit can perform transmitting and receiving functions. When the transceiver unit performs transmitting functions, the transceiver unit may be referred to as a transmitting unit (also referred to as a transmitting module). When the transceiver unit performs receiving functions, the transceiver unit may be referred to as a receiving unit (also referred to as a receiving module). The transmitting unit and the receiving unit may be the same functional module, and the functional module may be referred to as a transceiver unit, and the functional module can perform transmitting and receiving functions. Alternatively, the transmitting unit and the receiving unit may be different functional modules, and the transceiver unit is a collective term for these functional modules.

[0045] For example, when the apparatus is configured to perform the method described in the first or second aspect, the apparatus may include a communication unit and a processing unit.

[0046] According to a fourth aspect, an embodiment of the present application further provides a communications device, including a processor configured to execute a computer program (or computer-executable instructions) stored in a memory, which, when executed, enables the device to perform a method according to either the first aspect or the second aspect and possible implementations of the first aspect or the second aspect.

[0047] In a possible implementation, the processor and memory are integrated with each other.

[0048] In another possible implementation, the memory is located external to the communication device.

[0049] The communication device further includes a communication interface. The communication interface is for communication, e.g., sending or receiving data and / or signals, between the communication device and another device. For example, the communication interface may be a transceiver, a circuit, a bus, a module, or another type of communication interface.

[0050] According to a fifth aspect, there is provided a computer-readable storage medium configured to store a computer program or instructions, which, when executed, perform a method according to the first aspect or the second aspect and any possible implementation thereof.

[0051] According to a sixth aspect, there is provided a computer program product comprising instructions which, when run on a computer, perform a method according to the first aspect or the second aspect and any possible implementation of the first aspect or the second aspect.

[0052] According to a seventh aspect, an embodiment of the present application further provides a communication device, wherein the communication device is configured to perform a method according to the first aspect or the second aspect and a possible implementation of the first aspect or the second aspect.

[0053] According to an eighth aspect, a chip system is provided. The chip system includes a logic circuit (alternatively, it may be understood that the chip system includes a processor, and the processor may include a logic circuit, etc.) and may further include an input / output interface. The input / output interface may be configured to input a message or to output a message. The input / output interface may be the same interface. In other words, the same interface can realize both a sending function and a receiving function. Alternatively, the input / output interface includes an input interface and an output interface. The input interface is configured to realize a receiving function, i.e., configured to receive a message. The output interface is configured to realize a sending function, i.e., configured to send a message. The logic circuit may be configured to perform operations other than the sending and receiving functions in the method according to the first or second aspect and any possible implementation form of the first or second aspect. The logic circuit may be further configured to send a message to the input / output interface or receive a message from another communication device from the input / output interface. The chip system may be configured to perform the method according to the first or second aspect and any possible implementation form of the first or second aspect. A chip system may include a chip, or may include a chip and other discrete devices.

[0054] Optionally, the chip system may further include a memory, and the memory may be configured to store instructions. The logic circuit may call the instructions stored in the memory to implement corresponding functions.

[0055] According to a ninth aspect, there is provided a communication system. The communication system may include at least one terminal device and a network device. Any terminal device may be configured to perform the method according to the first aspect and any possible implementation form of the first aspect. The network device may be configured to perform the method according to the second aspect and any possible implementation form of the second aspect.

[0056] For the technical effects provided by the second to ninth aspects, please refer to the description of the first aspect, and the details will not be described again here. [Brief explanation of the drawings]

[0057] [Figure 1] FIG. 1 is a diagram of the architecture of a wireless communication system according to an embodiment of the present application. [Figure 2] Diagram of the structure of a neuron. [Figure 3] FIG. 1 is a diagram of the structure of a neural network. [Figure 4] This is a diagram illustrating the principle of AI-based CSI prediction. [Figure 5] 1 is a schematic flowchart of a communication method according to an embodiment of the present application; [Figure 6] FIG. 1 is a diagram of a periodic pattern of CSI resources according to an embodiment of the present application. [Figure 7] FIG. 10 is a diagram of another periodic pattern of CSI resources according to an embodiment of the present application. [Figure 8] FIG. 1 is a diagram of CSI resource group joint use according to one embodiment of the present application. [Figure 9] FIG. 1 is a diagram of independent use of CSI resource groups according to one embodiment of the present application. [Figure 10] 1 is a diagram of the structure of a communication device according to an embodiment of the present application; [Figure 11] FIG. 2 is a diagram of the structure of another communication device according to the present application. [Figure 12] FIG. 2 is a diagram of the structure of another communication device according to the present application. DETAILED DESCRIPTION OF THE INVENTION

[0058] The embodiments of the present application provide a communication method and an apparatus. The method and the apparatus are based on the same inventive concept. Because the method and the apparatus have similar problem-solving principles, the implementation forms of the apparatus and the method are referred to each other, and repeated descriptions will not be provided. In the description of the embodiments of the present application, the term "and / or" describes an association relationship between associated objects and indicates that three relationships may exist. For example, A and / or B may indicate the following three cases: when only A exists, when both A and B exist, and when only B exists. The character " / " generally indicates an "or" relationship between associated objects. In the present application, "at least one" means one or more, and "plurality" means two or more. In addition, it should be understood that in the description of the present application, terms such as "first" and "second" are used only for distinction and explanation, and should not be understood as indicating or implying relative importance or indicating or implying an order.

[0059] The communication method provided in the embodiments of the present application may be applied to a fourth-generation (4G) communication system, such as a long-term evolution (LTE) communication system, or a fifth-generation (5G) communication system, such as a 5G new radio (NR) communication system, or various future communication systems, such as a sixth-generation (6G) communication system. The method provided in the embodiments of the present application may further be applied to a Bluetooth system, a WiFi system, a LoRa system, or a vehicle internet system. The method provided in the embodiments of the present application may further be applied to a satellite communication system. The satellite communication system may be integrated with the aforementioned communication systems.

[0060] To facilitate understanding of the embodiments of the present application, the application scenario used in the present application will be described by using the architecture of a communication system shown in FIG. 1 as an example. As shown in FIG. 1, a communication system 100 includes a network device 101 and a terminal device 102. The apparatus provided in the embodiments of the present application may be used in the network device 101 or the terminal device 102. It will be understood that FIG. 1 shows only one possible architecture of a communication system to which the embodiments of the present application may be applied. In another possible scenario, the architecture of the communication system may alternatively include another device.

[0061] The network device 101 is a node in a radio access network (RAN) and may also be referred to as a base station or a RAN node (or device). Currently, some examples of access network devices are gNB / NR-NB, macro base station, micro base station, indoor base station, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved Node B, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wifi) access point (AP), satellite device, relay node, donor node, radio controller in cloud radio access network (CRAN) scenario, road side unit (RSU) in vehicle to everything (V2X) technology, or network device in 5G communication system, or open access network (open The network device 101 may be an access network device or a module of an access network device in a RAN (Radio Access Network, Optical Range Access Network, Optical Network, Optical Access Network), ORAN (O-RAN), or a network device in a possible future communication system. Alternatively, the network device 101 may be another device having a network device function. For example, the network device 101 may alternatively be a device assuming a network device function in device-to-device (D2D) communication, vehicular internet communication, or machine-to-machine communication.Alternatively, the network device 101 may be a network device in a possible future communication system. It will be appreciated that multiple access network devices in a communication system may be of the same type or different types.

[0062] In some deployments, a gNB may include a centralized unit (CU) and a DU. The gNB may further include a radio unit (RU). The CU implements some functions of the gNB, and the DU implements some functions of the gNB. For example, the CU implements functions of the radio resource control (RRC) layer and the packet data convergence protocol (PDCP) layer, and the DU implements functions of the radio link control (RLC) layer, the media access control (MAC) layer, and the physical (PHY) layer. RRC layer information ultimately becomes or is converted from PHY layer information. Therefore, in this architecture, higher layer signaling, such as RRC layer signaling or PDCP layer signaling, may also be considered to be transmitted by the DU or by the DU and RU. It may be understood that a network device may be a CU node, a DU node, or a device including a CU node and a DU node. In addition, the CU may be classified as a network device in the access network (RAN), or the CU may be classified as a network device in the core network (CN), which is not limited here. In an ORAN system, the CU may be referred to as an O-CU, the DU may be referred to as an open (O)-DU, the CU-CP may be referred to as an O-CU-CP, the CU-UP may be referred to as an O-CU-UP, and the RU may be referred to as an O-RU.

[0063] The terminal device 102 may be referred to as user equipment (UE), a mobile station (MS), a mobile terminal (MT), etc., and may be a device that provides voice or data connectivity to a user and may be an Internet of Things device. For example, the terminal device may include a handheld device or a vehicle-mounted device with wireless connectivity capabilities. Currently, the terminal device may be a mobile phone, a tablet computer, a laptop computer, a palmtop computer, a mobile internet device (MID), a wearable device (e.g., a smart watch, a smart band, or a pedometer), a vehicle-mounted device (e.g., an automobile, a bicycle, an electric vehicle, an airplane, a ship, a train, or a high-speed train), a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a smart home device (e.g., a refrigerator, a television, an air conditioner, or an instrument), an intelligent robot, a workshop equipment, a wireless terminal in autonomous driving, a wireless terminal in remote surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, a flying device (e.g., an intelligent robot, a hot air balloon, an unmanned aerial vehicle, or an airplane), etc. Alternatively, the terminal device may be another device having a terminal function. For example, the terminal device may alternatively be a device that functions as a terminal function in D2D communication. In this application, a terminal device having wireless transceiver functionality and a chip that may be disposed in the terminal device are collectively referred to as a terminal device.

[0064] With reference to the communication system shown in FIG. 1, the following describes in detail the communication method provided in the embodiment of the present application.

[0065] To better understand the solutions provided in the embodiments of the present application, the following will first explain some terms, concepts, or procedures in the embodiments of the present application.

[0066] 1. AI AI refers to intelligence exhibited by machines created by people. In general, artificial intelligence is the technology of exhibiting human intelligence through the use of conventional computer programs. AI may be defined as a machine or computer that mimics humans and possesses cognitive functions related to human thinking, such as learning and problem-solving. AI can learn from past experiences, make rational decisions, and respond quickly. The goal of AI is to understand intelligence through symbolic reasoning, or by building computer programs for reasoning.

[0067] 2. Machine Learning Machine learning is a method for achieving artificial intelligence, that is, solving problems in artificial intelligence by using machine learning as a tool. Machine learning theory is primarily concerned with designing and analyzing several algorithms that allow computers to learn automatically. Machine learning algorithms are algorithms that automatically analyze data to obtain rules and then use those rules to predict unknown data. Machine learning algorithms involve a large amount of statistical theory. Machine learning is closely related to inferential statistics and is also called statistical learning theory.

[0068] 3. AI model An AI model is an algorithm or computer program that can implement an AI function. The AI ​​model represents a mapping relationship between the model's input and output. The AI ​​model may be a neural network or another machine learning model. In this application, the AI ​​model used for CSI prediction may be referred to as an AI model, or simply as a model.

[0069] 4. Neural network (NN) Neural networks are a concrete implementation of machine learning. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, so they have the ability to learn any mapping. Therefore, neural networks can accurately model complex, high-dimensional problems.

[0070] In a neural network, each neuron performs a weighted sum operation on its input values, and the output is generated by using an activation function on the results obtained through the weighted sum. Figure 2 shows the structure of a neuron. The inputs to a neuron are x=[x0,x1,...,x n ], and the weights corresponding to the inputs are w=[w,w1,...,w n ] and the offset for weighted summation is assumed to be b. The form of the activation function can be varied. The activation function of a neuron is assumed to be y = f(z) = max(0,z). In this case, the output of the neuron is

number

number

[0071] Neural networks generally include multiple layers, each of which may contain one or more neurons. Increasing the depth and / or width of a neural network can improve the neural network's representational capabilities and provide more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network may refer to the number of layers included in the neural network, and the number of neurons included in each layer may be referred to as the layer width. Figure 3 illustrates the layer relationships of a neural network. In a possible implementation, the neural network includes an input layer and an output layer. The input layer of the neural network performs neuronal processing on the received input and then forwards the results to the output layer. The output layer obtains the output result of the neural network. In another possible implementation, the neural network includes an input layer, a hidden layer, and an output layer. The input layer of the neural network performs neuronal processing on the received input and then forwards the results to an intermediate hidden layer. The hidden layer forwards the calculation results to the output layer or an adjacent hidden layer. Finally, the output layer obtains the output result of the neural network. A neural network may include one hidden layer or multiple hidden layers connected in series. This is not limited. In the neural network training process, a loss function may be defined. The loss function describes the gap or difference between the neural network's output value and the neural network's ideal target value. The specific form of the loss function is not limited in this application. The neural network training process is a process of adjusting the neural network parameters, such as the number of neural network layers, the neural network width, the neuron weights, and / or the neuron activation function parameters, so that the value of the loss function is less than a threshold or meets the target requirement.

[0072] 5. AI-based CSI prediction In the process of AI-based CSI prediction, some past CSI information and / or current CSI information may be input into an AI prediction model, which may then output predicted future CSI information. As shown in FIG. 4, three pieces of past CSI information may be input into the AI ​​prediction model, which may then output CSI information at a specific future time point. The future CSI information may be used by network devices to perform resource scheduling at future times to improve communication performance.

[0073] In this application, the CSI information may be a CSI measurement result or a CSI report that is used to carry the measurement result in some scenarios.

[0074] 6. CSI Resource Configuration Method As shown in Table 1, a network device may configure CSI resources associated with a CSI report by using a CSI reporting configuration (CSI-ReportConfig). One CSI report may be associated with up to three CSI resource configurations. As shown in Table 1-1, one CSI resource configuration identifier (CSI-ResourceConfigId) may correspond to the configuration of multiple CSI resources. A first CSI resource may be used independently for CSI measurements, or the first CSI resource may be used together with the other two CSI resources for CSI measurements.

[0075] [Table 1]

[0076] As shown in Table 1-2, one CSI-ResourceConfig may be composed of one or more resource set lists (ResourceSetList), and each ResourceSetList includes one or more resource sets (ResourceSet).

[0077] [Table 2]

[0078] As shown in Tables 1-3, one ResourceSet may be associated with multiple CSI-RS resources (CSI-RS-Resources). A CSI-RS-Resource may be a periodic CSI resource, a semi-persistent CSI resource, or an aperiodic CSI resource. An aperiodic CSI resource is an independent CSI-RS resource, while both periodic CSI resources and semi-persistent CSI resources include multiple CSI-RS resources.

[0079] [Table 3]

[0080] Generally, an AI model has good inference performance only for data with a distribution close to that of the training data. For an AI model used for CSI prediction, if three pieces of CSI information spaced 5 milliseconds (ms) apart are used to predict CSI information for 5 ms in the future during training, i.e., CSI information at time points t-10 ms, t-5 ms, and t are input to the AI ​​model, and the label is CSI information for time point t+5 ms, when the AI ​​model is used for inference, the AI ​​model can accurately predict CSI information for 5 ms in the future only when the three pieces of CSI information spaced 5 milliseconds (ms) apart are input. However, based on the CSI reporting configuration, multiple CSI resources may be configured for a terminal device, and some CSI resources may not be used by the AI ​​model. If the terminal device and the network device do not agree on which measurement results of CSI resources can be input to the AI ​​prediction model for prediction, the output of the AI ​​prediction model may not represent CSI information for time point t+5 ms. As a result, communication performance is affected. In addition, because the AI ​​prediction model is typically trained and used by the terminal device, the network device does not know the specific configuration of CSI information required by the AI ​​prediction model to perform CSI prediction. If the CSI resources configured by the base station are not suitable for the terminal device to execute the AI ​​prediction model, the UE cannot correctly use the AI ​​prediction model to perform prediction.

[0081] Therefore, the current configuration solution of CSI resources cannot meet the requirements of the AI-based CSI prediction mechanism, resulting in a reduced reliability of the CSI prediction mechanism.

[0082] To enable a CSI resource configuration solution to meet the requirements of an AI-based CSI prediction mechanism and improve the reliability of CSI prediction, an embodiment of the present application provides a communication method. The method will be described below with reference to FIG. 5. FIG. 5 will be described using an example in which the execution entities are a terminal device and a network device. The terminal device may include the terminal device shown in FIG. 1 or may include components within the terminal device, such as a processor, a chip, a processing unit, or a communication unit. The terminal device may be replaced with components within the network device. According to the method, the terminal device may know the use of CSI resources based on received first information, and determine whether to report CSI information based on the use of the CSI resources by using an appropriate reporting configuration, or whether to not report CSI information based on the use. The use of the CSI resources includes at least one of CSI information collection, AI model performance monitoring, and CSI information prediction. As a result, the terminal device can perform CSI prediction based on the appropriate CSI resources to meet CSI prediction requirements.

[0083] As shown in FIG. 5, the communication method may include the following steps.

[0084] S101: A network device transmits first information.

[0085] In response, the terminal device receives the first information.

[0086] The first information indicates a use of the first CSI resource, and the use of the CSI resource includes at least one of the following: CSI information collection, AI model performance monitoring, and AI model inference. The AI ​​model may be used for CSI prediction.

[0087] In this application, a CSI resource may be a resource used to carry a channel state information reference signal (CSI-RS) and therefore may also be referred to as a CSI-RS resource. The terminal device may perform CSI measurements (also referred to as RS resource channel measurements, channel measurements, pilot signal measurements, etc.) based on the CSI-RS resource to obtain CSI measurement results including at least one of channel response information, a channel-quality indicator (CQI), a rank index (RI) of downlink data transmission, and a precoding matrix index (PMI). The terminal device may further report the CSI measurement results to a network device by using CSI reporting.

[0088] The following describes the use of the first CSI resource individually.

[0089] (1) CSI (Critical Signal Intelligence) or data collection applications The application means that the network device needs to collect CSI information determined based on the CSI resource, where the CSI information may be obtained by performing channel measurements on the CSI resource. The collected CSI information may be used for AI model training, AI model updating, etc. Therefore, for the CSI resource for the application, the terminal device may determine a CSI measurement result of the CSI resource and report the CSI measurement result to the network device.

[0090] Optionally, the CSI measurement results may be reported in a reporting manner corresponding to the use of the CSI information collection. For example, compared with the CSI resources using AI model inference, the CSI measurement results corresponding to the CSI resources using CSI information collection are usually used as labels for AI model training, and therefore require high accuracy.

[0091] (2) AI model inference, also known as model inference applications The application means that the terminal device needs to predict CSI information at a future time-domain position based on the CSI measurement results of the CSI resource and the AI ​​model, and then report the predicted CSI information to the network device so that the network device can perform data transmission based on the predicted CSI information.

[0092] When performing CSI prediction using an AI model, the terminal device can only input CSI information corresponding to a CSI resource whose use is model inference to the AI ​​model.

[0093] Optionally, the CSI information may be reported in a reporting manner corresponding to the application of the AI ​​model inference.

[0094] (3) AI model performance monitoring, also known as model monitoring applications The use means that the terminal device may monitor the performance of an AI model based on CSI measurement results of the CSI resource. For example, if the use of a first CSI resource is AI model performance monitoring, the terminal device may use an AI model to predict CSI information of the first CSI resource, measure the first CSI resource to obtain actual CSI measurement results, and then further compare the difference between the predicted CSI information and the actual CSI measurement results and determine the accuracy of the AI ​​model based on the difference. Optionally, if the difference between the predicted CSI information and the actual CSI measurement results is large, the terminal device may trigger a training process for the AI ​​model.

[0095] Optionally, for the CSI resource for that purpose, the terminal device may not report the CSI measurement result corresponding to the CSI resource to the network device. Alternatively, the terminal device may report a monitoring result. The monitoring result may indicate the accuracy of the prediction result of the AI ​​model, or the monitoring result may be a determination result that determines whether the AI ​​model needs to be updated based on the accuracy.

[0096] Optionally, the same CSI resource in the present application may be configured for one or more uses. For example, a first CSI resource may be configured for model inference and model monitoring. Specifically, the UE may input CSI information obtained by measuring the CSI resource to the AI ​​model, or may monitor the performance of the AI ​​model based on the CSI information obtained by measuring the CSI resource.

[0097] In a possible implementation, the CSI resource usage in this application may be configured for a single CSI resource. For example, the same group of CSI resources may have different usages. The same group of CSI resources may refer to multiple resources corresponding to the same CSI reporting configuration (or CSI reporting configuration identifier), multiple resources corresponding to the same CSI-RS resource set list, or multiple resources corresponding to the same CSI-RS resource set. For example, a network device may configure CSI resource usage for one CSI-RS resource identifier.

[0098] In another possible implementation, CSI resource usage may alternatively be configured for a CSI resource set including multiple CSI resources (or a group thereof). For example, if a network device configures CSI resource usage for a first resource group, all of the usages of multiple CSI resources in the first resource group (which may include the first CSI resource) are the same. In the case of a configuration scheme for multiple CSI resources (or a group thereof), the network device may configure CSI resource usage for one CSI reporting configuration (or CSI reporting configuration identifier (CSI-ReportConfigId)). For example, the network device may configure CSI resource usage for a CSI-ReportConfigId in Table 1-1, and multiple CSI-RS resources corresponding to the CSI reporting configuration identifier may be used as a group of CSI resources, and all of the CSI resources are configured for that usage. In another example, CSI resource usage may be configured for a CSI-ResourceConfigId in Table 1-1. In this case, multiple CSI-RS resources associated with the CSI-ResourceConfigId may be used as a group of CSI resources. Additionally, the network device may configure CSI resource usage for a CSI-RS resource set list, in which case multiple CSI-RS resources associated with the CSI-RS resource set list may be used as a group of CSI resources, and all of the CSI resources are configured for that usage. Alternatively, the network device may configure CSI resource usage for a CSI-RS resource set, in which multiple CSI-RS resources associated with the CSI-RS resource set may be used as a group of CSI resources, and all of the CSI resources are configured for that usage.

[0099] Optionally, in the present application, different types of CSI resources may be configured in different manners, which means that the CSI resources may be periodic CSI resources, semi-persistent CSI resources, and aperiodic CSI resources.

[0100] For periodic CSI-RS resources and semi-persistent CSI-RS resources, the network device may configure the use of the CSI resource by using a CSI resource pattern. In other words, the first information may be a CSI resource pattern. The CSI resource pattern may also be referred to as a periodic pattern and may be used to determine the time-domain location of a CSI resource whose use is at least one of CSI information collection, AI model performance monitoring, and AI model inference. Therefore, after determining the time-domain location of the first CSI resource, the terminal device may determine the use of the first CSI resource based on the resource pattern.

[0101] In one example, the CSI resource pattern may indicate whether a CSI resource is used for a specific purpose. Using an example in which the specific purpose is AI model inference, the CSI resource pattern may sequentially indicate the number of consecutive CSI-RS resources whose purpose is AI model inference and / or the number of consecutive CSI-RS resources whose purpose is not AI model inference. As shown in FIG. 6, the periodic pattern may perform the indication in the following manner: four consecutive CSI-RS resources used for model inference and one CSI-RS resource not used for model inference. Additionally, the indication may alternatively be a bitmap manner: 1 indicates a CSI-RS resource whose purpose is AI model inference, and 0 indicates a CSI-RS resource whose purpose is not AI model inference. For example, the periodic pattern shown in the following figure may perform the indication in the following manner: 11110. It can be understood that different CSI-RS resources in FIG. 6 have different time-domain positions.

[0102] In another example, the CSI resource pattern may indicate the number of consecutive CSI resources for each purpose. Using three possible purposes, namely, CSI information collection, AI model performance monitoring, and AI model inference, as an example, a specific indication scheme may be to indicate the number of consecutive CSI-RSs used for each purpose in order. For example, as shown in FIG. 7, the CSI resource pattern may be indicated in the following manner: two consecutive CSI-RS resources whose purpose is CSI information collection (e.g., indicated as Use 1), two consecutive CSI-RSs whose function is AI model inference (e.g., indicated as Use 2), and one CSI-RS whose purpose is AI model performance monitoring (e.g., indicated as Use 3).

[0103] It will be understood that when a CSI resource pattern indicates the usage of CSI resources, the starting time-domain position (or point in time) of the CSI resources indicated by the CSI resource pattern may be predefined or configured by a network device. For example, starting from the first CSI-RS resource after point in time t+t1 may be predefined in a manner such as a protocol, where t is the point in time at which the CSI-RS resource is configured, t1 is a predefined or configured time offset value, and t is greater than or equal to 0. Optionally, the unit used to describe time in this application may be one of an OFDM symbol, a slot, a subframe, a frame, or a superframe, or a combination of one or more units.

[0104] Additionally, in the case of aperiodic CSI resources, each CSI-RS resource set includes only one CSI-RS resource, and therefore, the network device may indicate the usage of the CSI-RS resource set to implement the usage indication of the aperiodic CSI resources.

[0105] Optionally, when CSI resources configured by a network device for multiple resource groups have the same use, the CSI resources in the multiple resource groups may be jointly used or used for the same task. For example, as shown in FIG. 8, both the use of CSI resources in CSI resource group 1 and the use of CSI resources in CSI resource group 2 are AI model inferences. In this case, the terminal device may jointly input CSI information corresponding to the CSI resources in CSI resource group 1 and CSI information corresponding to the CSI resources in CSI resource group 2 into the AI ​​model to obtain predicted CSI information. Therefore, when the terminal device finds that CSI prediction performance is degraded, for example, due to an increase in the movement speed of the terminal device, one additional group of CSI resources may be configured. Because the terminal device uses two or more groups of CSI resources to predict CSI information, the time domain density present when two groups of CSI resources are combined is increased, and CSI prediction performance can be improved.

[0106] In addition, CSI resources for the same purpose in this application may alternatively be used independently or may be used to perform different tasks. For example, as shown in FIG. 9, both the purpose of the CSI resources in CSI resource group 1 and the purpose of the CSI resources in CSI resource group 2 are AI model inferences. In this case, the terminal device may input the CSI resources in CSI resource group 1 to the AI ​​model to obtain predicted CSI information 1, and the terminal device may input the CSI resources in CSI resource group 2 to the AI ​​model to obtain predicted CSI information 2. Therefore, the terminal device may obtain CSI prediction results at different time-domain positions based on the CSI resources in different resource groups.

[0107] Furthermore, optionally, the terminal device may determine whether the CSI resources in the first resource group are jointly used with the CSI resources in the second resource group by using any one or more of the following methods 1 to 3:

[0108] Manner 1: Determining according to whether the CSI resources in the first resource group and the CSI resources in the second resource group correspond to the same CSI reporting configuration.

[0109] When the CSI resources in the first resource group and the CSI resources in the second resource group are included in the same CSI reporting configuration, the terminal device may jointly use the CSI resources in the first resource group and the CSI resources in the second resource group when the usage of the CSI resources in the first resource group is the same as the usage of the CSI resources in the second resource group.

[0110] Scheme 2: The determination is made based on whether the CSI resources in the first resource group and the CSI resources in the second resource group have a quasi-colocation (QCL) relationship. Quasi-colocation may also be referred to as quasi-colocation, quasi-co-site, or co-location. If two CSI resources have a quasi-colocation relationship, it indicates that the CSI information corresponding to the two CSI resources has some similar characteristics, for example, similar delay spreads or beams. Optionally, in Scheme 2, if the CSI resources in the first resource group and the CSI resources in the second resource group have a specific quasi-colocation relationship, the terminal device is alternatively required to jointly use the CSI resources in the two resource groups. The specific quasi-colocation relationship may be a quasi-colocation relationship such as type A to type D.

[0111] Method 3: Determine based on additional configuration information.

[0112] For example, the identifier may be carried in the CSI reporting configuration or another configuration. When CSI resources in a first resource group and CSI resources in a second resource group are jointly used, the CSI resources in the first resource group and the CSI resources in the second resource group may be configured with the same identifier. When CSI resources in different resource groups do not need to be jointly used, different identifiers may be configured for the two resource groups. In addition, the network device may alternatively include, in the form of indication information, indexes of multiple resource groups (e.g., CSI-ReportConfigId, an identifier of a CSI resource set list, or an identifier of a CSI resource set) or indexes of multiple resources that need to be jointly used (e.g., CSI-ResourceConfigId), or indexes of multiple resource groups or resources that do not need to be jointly used.

[0113] It should be understood that Scheme 1 to Scheme 3 may alternatively be implemented in combination. For example, if the CSI resources in the first resource group and the CSI resources in the second resource group correspond to the same CSI reporting configuration and have a quasi-co-location relationship, the terminal device jointly uses the CSI resources in the two resource groups.

[0114] Optionally, the first information may further indicate at least one of the following information:

[0115] 1. AI model When the network device indicates the use of the CSI resource by using the CSI reporting configuration, if the use of the CSI resource includes AI model inference and / or AI model performance monitoring, the first information may further indicate the AI ​​model. For example, the CSI reporting configuration may hold an index or identifier of the AI ​​model to indicate to the terminal device that the corresponding AI model is used to predict CSI information and / or monitor the performance of the corresponding AI model.

[0116] 2. Predictive structure of CSI reports The predicted configuration of the CSI report may indicate the specific content of the CSI information to be included by the terminal device in the CSI report, as follows:

[0117] (a) The prediction configuration of the CSI report indicates that the CSI information carried in the CSI report is a CSI measurement result, or indicates that the CSI information carried in the CSI report is predicted CSI information. If the prediction configuration of the CSI report indicates that the CSI information reported by the terminal device is a CSI measurement result, the terminal device does not need to include CSI information predicted using an AI model in the CSI report. In addition, if the prediction configuration of the CSI report indicates that the CSI information reported by the terminal device is predicted CSI information, the terminal device needs to include CSI information predicted using an AI model in the CSI report.

[0118] In another possible implementation, the prediction configuration of a CSI report may be specific to one type of CSI information and indicate that the type of CSI information is a CSI measurement result or predicted CSI information. Different types of CSI information may include a PMI, a CQI, or an RI. In other words, the PMI, the CQI, and the RI may be used separately as one type of CSI information. For example, if a CSI report includes a PMI, a CQI, and an RI, the prediction configuration of a CSI report may indicate only that the PMI is a CSI measurement result or predicted CSI information. In addition, the prediction configuration of a CSI report may alternatively be for all types of CSI information. For example, if a CSI report includes a PMI, a CQI, and an RI, the prediction configuration of a CSI report may indicate that the PMI, the CQI, and the RI are all CSI measurement results or predicted CSI information.

[0119] (b) The predicted configuration of the CSI report indicates a time range length (or the number of time points) corresponding to the CSI information carried in the CSI report. For example, the predicted configuration of the CSI report indicates that the CSI information included by the terminal device in the CSI report is CSI information at one time point, CSI information at two time points, or CSI information at three time points.

[0120] (c) The predicted configuration of the CSI report indicates a time domain position (or time point) of a time range corresponding to the CSI information carried in the CSI report. For example, the predicted configuration of the CSI report indicates a specific time point, such as t+5 ms or t+8 ms, for each piece of CSI information included by the terminal device in the CSI report, where t is a predefined or preconfigured reference time point.

[0121] In another possible implementation, the prediction configuration of the CSI report may alternatively indicate that the terminal device determines specific content of the CSI information carried in the CSI report. In this case, the terminal device needs to notify the network device of the above information. For example, the terminal device needs to notify the network device of at least one piece of information, such as whether the CSI information carried in the CSI report is a CSI measurement result or predicted CSI information, the time range length (or the number of time points) corresponding to the CSI information carried in the CSI report, and the time domain position (or time point) of the time range corresponding to the CSI information carried in the CSI report. The manner in which the terminal device notifies the network device of the above information is not specifically required. For example, the terminal device may notify the network device by using uplink control information, uplink data, etc.

[0122] 3. Compressed CSI Information Alternatively, the compression configuration may be a compression configuration for CSI reporting. The compression configuration may indicate whether compression of CSI information is based on an AI or a codebook, and / or, when compression is based on an AI, whether CSI prediction and CSI compression are jointly processed using one AI model, or whether CSI prediction is first performed using one AI model and then the prediction result is compressed by using one AI model, i.e., whether CSI prediction and CSI compression are implemented using one AI model or two different AI models.

[0123] Optionally, before S101, the terminal device may transmit UE capability information (which may also be referred to as auxiliary information, etc., hereinafter simply referred to as capability information). The capability information may be used by the network device to determine the first information, or may be used to trigger the network device to transmit the first information, or may be used to assist the network device in configuring CSI resources.

[0124] The capability information may include at least one of the following information:

[0125] (1) Information indicating whether the terminal device supports CSI prediction For example, the information may indicate whether the terminal device supports CSI prediction or whether CSI prediction is supported in the current environment. Based on the information, the network device may avoid sending a CSI resource configuration for AI model inference to a terminal device that does not support CSI prediction.

[0126] (2)CSI periodicity information The information may indicate the requirements of the AI ​​model of the terminal device for the periodicity of input CSI information. Accordingly, the information may also be referred to as information regarding the requirements of the AI ​​model of the terminal device for the periodicity of input CSI information. Optionally, the information may include one or more of the following information: information indicating whether only periodic CSI information can be input to the AI ​​model; information indicating whether aperiodic CSI information can be input to the AI ​​model; information regarding a time-domain pattern of aperiodic CSI information that can be input to the AI ​​model; the number of periods of CSI information that can be input to the AI ​​model; and specific values ​​of the periodicities of CSI information that can be input. The terminal device may have multiple AI models, and different AI models may support different CSI information periodicities. Accordingly, the number of periods of CSI information that can be input to the AI ​​model may not be one.

[0127] (3) Observation window of the AI ​​model The information may indicate the requirements of the AI ​​model for the amount of input CSI information. Thus, the information may also be referred to as information regarding the requirements of the AI ​​model of the terminal device for the amount of input CSI information. Optionally, the information may include one or more of the following information: information indicating whether only a fixed number of CSI information can be input in the prediction process, information indicating whether any number of CSI information can be input in the prediction process, or a specific value of the amount of CSI information that can be input.

[0128] (4) AI model prediction window The information may indicate a time point output by the AI ​​model through AI model inference. Accordingly, the information may also be referred to as information about a time point output by the AI ​​model of the terminal device through AI model inference. Optionally, the information may include one or more of the following information: information indicating whether only CSI information at a fixed time point in the future can be output, for example, information indicating whether only CSI information at time point t+t1 can be output, where t is the current time point or the last time point of the input CSI information, and t1 is a fixed value or a value related to the periodicity of the input CSI information; information indicating whether CSI information at any future time point can be output; and specific future time points of CSI information that can be output.

[0129] (5) Information on the requirements of AI models for frequency domain attributes of input CSI information The information may indicate the terminal device's requirements for attributes such as frequency-domain resources of CSI information input to the AI ​​model for prediction. Optionally, the information may include one or more of the following information: information indicating whether only CSI information with a fixed bandwidth can be input; information indicating whether CSI information with a variable bandwidth can be input; information indicating whether CSI information corresponding to multiple different bandwidths can be input at once; a frequency-domain range of CSI information that can be input; a specific value of the bandwidth of CSI information that can be input; and a frequency-domain granularity of CSI information that can be input. The frequency-domain granularity may be, for example, one resource element (RE), one resource block (RB), or another granularity. This is not particularly limited.

[0130] (6) Frequency domain attribute information of CSI information that can be output by the AI ​​model The information may indicate the terminal device's requirements for frequency-domain attributes of CSI information that can be predicted. Optionally, the information may include one or more of the following: information indicating whether only CSI information with a fixed bandwidth can be output, information indicating whether CSI information with a variable bandwidth can be output, information indicating whether CSI information corresponding to multiple different bandwidths can be output at once, a frequency-domain range of CSI information that can be output, a specific value of the bandwidth of CSI information that can be output, and a frequency-domain granularity of CSI information that can be output, for example, one RE, one RB, or another granularity.

[0131] (7) Information about the AI ​​model's requirements for the dimensions of input and / or output CSI information. The dimensions include at least one of a frequency domain dimension, a time domain dimension, and a spatial domain dimension.

[0132] (8) Information about the AI ​​model's requirements for the type of input and / or output CSI information. For example, the information may indicate whether the CSI information is channel information or a feature vector of channel information.

[0133] (9) Information regarding the AI ​​model's requirements for reference signals used to measure CSI information. For example, the information may indicate the beam configurations (e.g., precoding configurations) of reference signals supported by the AI ​​model and / or the configurations of the supported reference signals (e.g., identifiers of the reference signal configurations).

[0134] It will be understood that upon receiving the above-described capability information, the network device may configure CSI resources based on the capability information. For example, if the capability information carries information indicating that the terminal device supports CSI prediction, the network device may configure CSI resources for the terminal device whose purpose is AI model inference. In another example, the CSI resources whose purpose is AI model inference and that are configured by the network device for the terminal device satisfy the observation window of the AI ​​model, the requirements of the AI ​​model for frequency-domain attributes of the input CSI information, the requirements of the AI ​​model for the dimensionality of the input CSI information, and the requirements of the AI ​​model for the type of input CSI information carried in the capability information.

[0135] Optionally, before S101, the terminal device may further transmit resource request information to request CSI resources. The resource request message may be used to request CSI resources for one or more specific applications and may include, for example, an application index. The request message may also be used to request a resource group and / or CSI resources jointly used with a resource group (e.g., a first resource group) and / or a CSI resource (e.g., a first CSI resource) and may include, for example, an index of the first resource group and / or an index of the first CSI resource. Optionally, the resource request message may include capability information.

[0136] S102: The terminal device transmits first CSI information based on the first information and / or monitors the performance of the AI ​​model based on the first information.

[0137] The first CSI information corresponds to a first CSI resource. For example, the first CSI information may be CSI measurement results or predicted CSI information obtained based on the first CSI resource. For example, referring to the description of S101, if the application includes AI model inference, the first CSI information may be predicted CSI information based on the first CSI resource and an AI model. If the application of the first CSI resource includes CSI information collection, AI model training, or AI model performance monitoring, the first CSI information may include CSI measurement results obtained by measuring the first CSI resource. If the application includes AI model performance monitoring, the first CSI information may include monitoring results of the AI ​​model.

[0138] According to the method illustrated in FIG. 5, the terminal device can know the purpose of CSI information based on the first information from the network device, and as a result, can avoid using CSI resources for incorrect purposes. Therefore, the reliability of CSI prediction can be improved.

[0139] Based on the same concept, an embodiment of the present application further provides a communication device. The communication device may include corresponding hardware structures and / or software modules for performing the functions set forth in the aforementioned methods. Those skilled in the art should easily recognize that the units and method steps in the examples described with reference to the embodiments disclosed in this application can be implemented by hardware or a combination of hardware and computer software. Whether the functions are performed by hardware or by hardware driven by computer software depends on the specific application scenario and design constraints of the technical solutions.

[0140] 10 to 12 are diagrams of possible communication device structures according to embodiments of the present application. The communication device may be configured to implement the functions of the network device and / or the first terminal device in the above-mentioned method embodiments, and thus can also realize the beneficial effects of the above-mentioned method embodiments. In a possible implementation, the communication device may be the network device or the terminal device shown in FIG. 1. For related details and effects, please refer to the description of the foregoing embodiments.

[0141] 10, the communication device 1000 includes a processing unit 1010 and a communication unit 1020. The communication unit 1020 may implement corresponding communication functions, and the processing unit 1010 is configured to process data. The communication unit 1020 may alternatively be a transceiver unit, an input / output interface, etc. The communication device 1000 may be configured to implement the functions of a terminal device and / or a network device in the embodiment of the method shown in FIG.

[0142] For example, when an action performed by the terminal device is realized, the communication unit 1020 may be configured to receive first information. The communication unit 1020 may be further configured to transmit the first CSI information, and / or the processing unit 1010 may be configured to monitor performance of an AI model based on the first information.

[0143] Optionally, the communication unit 1020 may be further configured to transmit capability information.

[0144] Optionally, the communication unit 1020 may be further configured to receive second information.

[0145] As another example, when the action performed by the network device is realized, the communication unit 1020 may be configured to send first information to the terminal device. Optionally, the first information may be generated by the processing unit 1010.

[0146] Optionally, the communication unit 1020 may be further configured to receive first CSI information from the terminal device.

[0147] Optionally, the communication unit 1020 may be further configured to receive capability information of the terminal device.

[0148] Optionally, the communication unit 1020 may be further configured to transmit second information.

[0149] For the aforementioned technical terms, please refer to the description of the method embodiments, and the details will not be described again here.

[0150] In the embodiments of the present application, the division into modules is an example, and is merely a logical division of functions, and it will be understood that other divisions may be used in actual implementation. In addition, the functional modules in the embodiments of the present application may be integrated into one processor, or each module may exist physically alone, or two or more modules may be integrated into one module. The integrated modules may be realized in the form of hardware or in the form of software functional modules.

[0151] FIG. 11 illustrates a communication device 1100 according to an embodiment of the present application. The communication device 1100 is configured to execute the communication method provided herein. The communication device 1100 may be a communication device to which the communication method is applied, a component of a communication device, or a device that can be used in combination with a communication device. The communication device 1100 may be a network device and / or a terminal device. The communication device 1100 may be a chip system or a chip. In this embodiment of the present application, the chip system may include a chip, or may include a chip and other discrete devices. The communication device 1100 includes at least one processor 1120 configured to execute the communication method provided in the embodiment of the present application. The communication device 1100 further includes an input / output interface 1110, which may include an input interface and / or an output interface. In this embodiment of the present application, the input / output interface 1110 may be configured to communicate with another device via a transmission medium, and the function of the input / output interface 1110 may include transmission and / or reception. For example, if the communication device 1100 is a chip, the communication device 1100 performs transmission between other chips or devices via the input / output interface 1110. The processor 1120 may be configured to perform the methods described in the above method embodiments.

[0152] For example, the processor 1120 may be configured to perform the operations performed by the processing unit 1010, and the input / output interface 1110 may be configured to perform the operations performed by the communication unit 1020. The details will not be described again.

[0153] Optionally, the communication device 1100 may further include at least one memory 1130 configured to store program instructions and / or data. The memory 1130 is coupled to the processor 1120. A coupling in this embodiment of the present application may be an electrical, mechanical, or other form of indirect coupling or communication connection between devices, units, or modules, used for information exchange between the devices, units, or modules. The processor 1120 may operate together with the memory 1130. The processor 1120 may execute program instructions stored in the memory 1130. At least one of the at least one memory may be integrated with the processor.

[0154] In this embodiment of the present application, the memory 1130 may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), or a volatile memory, such as a random-access memory (RAM). The memory is any other medium that can hold or store expected program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to this. The memory in the embodiment of the present application may alternatively be a circuit or any other device that can implement a storage function and is configured to store program instructions and / or data.

[0155] In this embodiment of the present application, the processor 1120 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed with reference to the embodiments of the present application may be executed directly by a hardware processor, or may be executed by using a combination of hardware and software modules in the processor.

[0156] FIG. 12 illustrates a communication device 1200 according to an embodiment of the present application. The communication device 1200 is configured to execute the communication method provided herein. The communication device 1200 may be a communication device to which the communication method in the embodiment of the present application is applied, a component of a communication device, or a device that can be used in combination with a communication device. The communication device 1200 may be a network device and / or a terminal device. The communication device 1200 may be a chip system or a chip. In this embodiment of the present application, the chip system may include a chip, or may include a chip and other individual devices. Some or all of the communication method provided in the above embodiment may be implemented by hardware or software. When the communication method is implemented by hardware, the communication device 1200 may include an input interface circuit 1201, a logic circuit 1202, and an output interface circuit 1203.

[0157] Optionally, in an example where the device is configured to realize the function of the receiving end, the input interface circuit 1201 may be configured to perform the receiving action performed by the communication unit 1020, the output interface circuit 1203 may be configured to perform the transmitting action performed by the communication unit 1020, and the logic circuit 1202 may be configured to perform the action performed by the processing unit 1010. The details will not be described again.

[0158] Optionally, in certain embodiments, the communication device 1200 may be a chip or an integrated circuit.

[0159] Some or all of the operations and functions performed by the communication device described in the foregoing method embodiments of the present application may be implemented using chips or integrated circuits.

[0160] An embodiment of the present application provides a computer-readable storage medium storing a computer program, the computer program including instructions for carrying out an embodiment of the method described above.

[0161] One embodiment of the present application provides a computer program product comprising instructions that, when executed on a computer, cause the computer to perform an embodiment of the method described above.

[0162] An embodiment of the present application provides a communication system including at least one terminal device and a network device. For example, the communication system includes the architecture shown in Figure 1. The terminal device and the network device may be configured to perform the method shown in Figure 5.

[0163] It may be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be another general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0164] All or part of the above embodiments may be implemented using software, hardware, firmware, or any combination thereof. When an embodiment is implemented using software, all or part of the embodiment may be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer instructions are loaded into a computer and executed, all or part of the procedures or functions according to the embodiments of the present application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, optical fiber, or digital subscriber line (DSL)) or wireless (e.g., infrared, radio wave, or microwave) transmission. The computer-readable storage medium may be any available medium accessible by a computer or a data storage device, such as a server or data center, that integrates one or more available media. The media that can be used may be magnetic media (e.g., floppy disks, hard disk drives, or magnetic tapes), optical media (e.g., high density digital video discs (DVDs)), semiconductor media (e.g., SSDs), and the like.

[0165] Please note that some of this patent application documents contain copyrighted content, and the copyright holder reserves the copyright, except for making copies of the patent documents or recording the contents of the patent documents with the State Intellectual Property Office of China.

[0166] The network device and the terminal device in the above-mentioned apparatus embodiments correspond to the network device or the terminal device in the method embodiments. Corresponding modules or units perform corresponding steps. For example, a communication unit (transceiver) performs the receiving step or the transmitting step in the method embodiments, and steps other than the transmitting step and the receiving step may be performed by a processing unit (processor). For the functions of specific units, please refer to the corresponding method embodiments. There may be one or more processors.

[0167] As used herein, terms such as “component,” “module,” and “system” are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software being executed. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and / or a computer. As illustrated through the use of diagrams, both computing devices and applications running on computing devices may be components. One or more components may reside within a process and / or thread of execution, and components may be located on one computer and / or distributed among two or more computers. Additionally, these components may execute from various computer-readable media that store various data structures. For example, components may communicate using local and / or remote processes based on signals, for example, having one or more data packets (e.g., data from two components interacting with another component in a local system, a distributed system, and / or over a network such as the Internet that interacts with other systems using signals).

[0168] Those skilled in the art will recognize that the illustrative logical blocks and steps described in the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether a function is implemented by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may implement the described functions using various methods for each specific application, but such implementation should not be considered as going beyond the scope of this application.

[0169] For the sake of convenient and concise description, it can be clearly understood by those skilled in the art that for the detailed operation processes of the above-mentioned systems, devices and units, please refer to the corresponding processes in the above-mentioned method embodiments, and the details will not be described again here.

[0170] In some embodiments provided in the present application, it should be understood that the disclosed system, device, and method may be realized in other ways. For example, the described device embodiment is merely an example. For example, the division into units is merely a logical division of function, and may be divided differently in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not implemented. In addition, the shown or described mutual couplings or direct couplings or communication connections may be realized by using some interfaces. Indirect couplings or communication connections between devices or units may be realized in electronic, mechanical, or other forms.

[0171] The units described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., located in one location or distributed across multiple network units. Some or all of the units may be selected based on actual requirements to achieve the objectives of the solutions of the embodiments.

[0172] In addition, the functional units of the embodiments of the present application may be integrated into one processing unit, each of the units may exist physically alone, or two or more units may be integrated into one unit. When the functions are realized in the form of a software functional unit and sold or used as an independent product, the functions may be stored in a computer-readable storage medium.

[0173] The above description is merely a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. Any variations or replacements that can be easily conceived by those skilled in the art within the technical scope disclosed in the present application shall fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the scope of protection of the claims. [Explanation of symbols]

[0174] 100 Communication Systems 101 Network Devices 102 Terminal Devices 1000 Communication Equipment 1010 Processing Unit 1020 Communication Unit 1100 Communication equipment 1110 Input / Output Interface 1120 processor 1130 memory 1200 Communication Equipment 1201 Input interface circuit 1202 Logic Circuit 1203 Output Interface Circuit

Claims

1. 1. A communication method comprising: receiving first information, the first information indicating a usage of a first channel state information (CSI) resource, the usage of the CSI resource including at least one of the following: CSI information collection, artificial intelligence (AI) model performance monitoring, and AI model inference; transmitting first CSI information based on the first information; and / or monitoring the performance of the AI ​​model based on the first information; Including, The first CSI information corresponds to the first CSI resource.

2. The method of claim 1 , wherein the AI ​​model is used for CSI prediction.

3. When the application includes the AI ​​model inference, the first CSI information includes CSI information predicted based on the first CSI resource and the AI ​​model; When the application includes the CSI information collection or the AI ​​model performance monitoring, the first CSI information includes a CSI measurement result obtained by measuring the first CSI resource; or 3. The method of claim 1, wherein when the application includes monitoring the AI ​​model performance, the first CSI information includes a monitoring result of the AI ​​model, and the monitoring result indicates accuracy of a prediction result of the AI ​​model.

4. The method comprises: Transmitting capability information and wherein the capability information includes the following: Information indicating whether the terminal device supports CSI prediction; Information regarding the requirements of the AI ​​model of the terminal device for the periodicity of input CSI information; Information regarding the requirements of the AI ​​model of the terminal device for the amount of input CSI information; Information regarding the time point of predicted CSI information output by the AI ​​model of the terminal device; Information regarding the requirements of the AI ​​model of the terminal device for frequency domain attributes of the input CSI information; Frequency domain attribute information of CSI information that can be output by the AI ​​model of the terminal device; Information regarding the requirements of the AI ​​model of the terminal device for the dimensions of input and / or output CSI information; Information regarding the requirements of the AI ​​model of the terminal device for the type of input and / or output CSI information; and Information regarding the requirements of the AI ​​model of the terminal device for reference signals used for CSI information measurement; The method according to any one of claims 1 to 3, comprising at least one of:

5. The first information further indicates a compressed configuration of CSI information, and the step of transmitting the first CSI information based on the usage includes: transmitting the first CSI information based on the compression configuration.

2. The method of claim 1, comprising:

6. 6. The method of claim 1, wherein the first information specifically indicates a usage of CSI resources in a first resource group, and the CSI resources in the first resource group include the first CSI resource.

7. 7. The method of claim 1, wherein the first information further indicates a usage of second CSI resources in the first resource group, the usage of the second CSI resources being different from a usage of the first CSI resources.

8. 7. The method of claim 6, wherein the CSI resources in the first resource group and the CSI resources in the second resource group are jointly used, and the usage of the CSI resources in the second resource group is the same as the usage of the CSI resources in the first resource group.

9. the CSI resources in the first resource group and the CSI resources in the second resource group correspond to the same CSI reporting configuration; the CSI resources in the first resource group and the CSI resources in the second resource group are associated with the same AI model; or 9. The method of claim 8, wherein the CSI resources in the first resource group and the CSI resources in the second resource group have a quasi-colocated QCL relationship.

10. The method comprises: receiving second information, the second information indicating that the CSI resources in the first resource group and the CSI resources in the second resource group are jointly used; 10. The method of claim 8 or 9, further comprising:

11. 11. The method of claim 1, wherein the first information specifically indicates a CSI resource pattern, and the CSI resource pattern is used to determine time-domain locations of CSI resources whose uses are at least one of CSI information gathering, AI model performance monitoring, and AI model inference.

12. The first information is: AI models, and Prediction of the CSI information 12. The method of claim 1, further comprising at least one of:

13. 1. A communication method comprising: transmitting first information to a terminal device, the first information indicating a usage of a first channel state information (CSI) resource, the usage of the CSI resource including at least one of the following: CSI information collection, artificial intelligence (AI) model performance monitoring, and AI model inference; A method comprising:

14. The method comprises: receiving first CSI information from the terminal device, the first CSI information corresponding to the first CSI resource; 14. The method of claim 13, further comprising:

15. The method of claim 13 or 14, wherein the AI ​​model is used for CSI prediction.

16. When the application includes the AI ​​model inference, the first CSI information includes CSI information predicted based on the first CSI resource and the AI ​​model; When the application includes the CSI information collection or the AI ​​model performance monitoring, the first CSI information includes a CSI measurement result obtained by measuring the first CSI resource; or When the application includes monitoring the AI ​​model performance, the first CSI information includes a monitoring result of the AI ​​model, and the monitoring result indicates the accuracy of a prediction result of the AI ​​model. The method of claim 13.

17. The method comprises: receiving capability information of the terminal device and wherein the capability information includes the following: Information indicating whether the terminal device supports CSI prediction; Information regarding the requirements of the AI ​​model of the terminal device for the periodicity of input CSI information; Information regarding the requirements of the AI ​​model of the terminal device for the amount of input CSI information; Information regarding the time point of predicted CSI information output by the AI ​​model of the terminal device; Information regarding the requirements of the AI ​​model of the terminal device for frequency domain attributes of the input CSI information; Frequency domain attribute information of CSI information that can be output by the AI ​​model of the terminal device; Information regarding the requirements of the AI ​​model of the terminal device for the dimensions of input and / or output CSI information; Information regarding the requirements of the AI ​​model of the terminal device for the type of input and / or output CSI information; and Information regarding the requirements of the AI ​​model of the terminal device for reference signals used for CSI information measurement; 17. The method of any one of claims 13 to 16, comprising at least one of:

18. The method of claim 13 , wherein the first information further indicates a compression configuration of CSI information.

19. 19. The method of claim 13, wherein the first information specifically indicates the usage of CSI resources in a first resource group, and the CSI resources in the first resource group include the first CSI resource.

20. 20. The method of claim 13, wherein the first information further indicates a usage of second CSI resources in the first resource group, the usage of the second CSI resources being different from a usage of the first CSI resources.

21. 21. The method of claim 20, wherein the CSI resources in the first resource group and the CSI resources in the second resource group are jointly used, and the usage of the CSI resources in the second resource group is the same as the usage of the CSI resources in the first resource group.

22. the CSI resources in the first resource group and the CSI resources in the second resource group correspond to the same CSI reporting configuration; the CSI resources in the first resource group and the CSI resources in the second resource group are associated with the same AI model; or 22. The method of claim 21, wherein the CSI resources in the first resource group and the CSI resources in the second resource group have a quasi-colocated QCL relationship.

23. The method comprises: transmitting second information, the second information indicating that the CSI resources in the first resource group and the CSI resources in the second resource group are jointly used; 23. The method of claim 21 or 22, further comprising:

24. 24. The method of claim 13, wherein the first information specifically indicates a CSI resource pattern, and the CSI resource pattern is used to determine time-domain locations of CSI resources whose uses are at least one of CSI information gathering, AI model performance monitoring, and AI model inference.

25. The first information is: AI models, and Prediction of the CSI information 25. The method of claim 13, further comprising at least one of:

26. A communications device comprising a processor, the processor configured to execute computer program instructions stored in a memory to perform the method of any one of claims 1 to 12 or any one of claims 13 to 25.

27. 26. A computer readable storage medium comprising computer program instructions which, when executed by a computer, enable the computer to perform the method of any one of claims 1 to 12 or any one of claims 13 to 25.

28. A communication device comprising modules configured to carry out the method of any one of claims 1 to 25.

Images