Communication method and device

Abstract

The embodiment of the invention provides a communication method and device, relates to the field of communication, can perform performance monitoring on an AI / ML model (a first model), and can save signaling overhead. Exemplary, the communication method provided by the embodiment of the invention can be applied to a beam prediction scene. The method comprises the following steps: the terminal equipment can predict a first beam set based on a first model (AI / ML model) deployed on the terminal equipment; then, the terminal device may send a first message to the network device, the first message including first indication information indicating a performance state of the first model, and beam-related information. Wherein the performance state of the first model can be a normal state, an abnormal state or an unknown state, for example. The wave beam related information comprises related information of wave beams in the first wave beam set obtained through prediction of the first model, or the wave beam related information comprises related information of wave beams in a subset of the first wave beam set.

Description

[0001] This application claims priority to Chinese Patent Application No. 202411369236.2, filed with the State Intellectual Property Office of China on September 27, 2024, entitled "A Method for Monitoring Beam Status", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to a communication method and apparatus. Background Technology

[0003] High-frequency deployment is a development trend in mobile communications; however, it also brings problems such as high signal attenuation and high signal loss. To ensure communication link quality, massive MIMO and beam management have become indispensable technologies. However, with further increases in frequency bands and antenna size, beam management under traditional beam management frameworks generates huge signaling overhead. One important means to reduce the signaling overhead of traditional beam management frameworks is artificial intelligence (AI) / machine learning (ML) models. In AI / ML model-assisted beam management, the AI / ML model can predict the optimal beam for a larger beam set based on measurements of a smaller beam set. This eliminates the need for the base station to transmit the entire candidate beam set, thus significantly saving signaling overhead.

[0004] However, changes in scenarios due to the mobility of terminal devices or alterations in the distribution of moving scatterers can render current AI / ML models inapplicable. When AI / ML models fail, communication quality is severely compromised; therefore, performance monitoring of AI / ML models is essential. However, there is currently no consensus on how to conduct performance monitoring of AI / ML models. Summary of the Invention

[0005] This application provides a communication method and apparatus that can monitor the performance of an AI / ML model (first model) and save signaling overhead.

[0006] To achieve the above objectives, the embodiments of this application adopt the following technical solutions:

[0007] Firstly, a communication method is provided. This method can be executed by a terminal device, or by a component (such as a circuit, chip, or chip system) configured in the terminal device, or by a logic module or software capable of implementing all or part of the functions of the terminal device. This application does not limit this approach. The following description uses a terminal device as an example.

[0008] The method includes: obtaining a first beam set based on a first model; sending a first message, the first message including first indication information and beam-related information, the first indication information being used to indicate the performance status of the first model, and the beam-related information including information related to beams in the first beam set, or the beam-related information including information related to beams in a subset of the first beam set.

[0009] Based on the communication method provided in the embodiments of this application, the terminal device can perform performance monitoring on the first model (e.g., AI / ML model) to obtain the first indication information, and can send the first indication information and related information of the beam set in the same message (first message) to the network device without defining a new report configuration (report field) for the first indication information, and without generating additional control signaling overhead.

[0010] Furthermore, the terminal device sends the first instruction information to the network device, enabling the network device to understand the performance status of the AI / ML model based on the first instruction information, thereby performing adaptive processing and improving communication quality.

[0011] In one possible implementation, beam-related information includes the beam index of each of the first K beams in the first beam set. The first K beams consist of the K beams ranked highest to lowest based on their predicted signal quality, or the K beams ranked highest to lowest based on their best beam prediction probabilities; K is an integer greater than or equal to 1. Thus, by reporting the first K beams with high prediction confidence (high prediction probability / high predicted signal quality) for network devices to select (downlink) for transmission, it is unnecessary to report the beam indices of all beams in the entire first beam set, thereby saving signaling overhead.

[0012] In one possible implementation, the beam-related information also includes predicted signal quality values ​​for each of the first K beams in the first beam set. This allows network devices to select beams more accurately; for example, the network device can select the downlink transmission beam that meets the requirements (e.g., the beam with better channel quality) based on the predicted signal quality values ​​to ensure communication quality.

[0013] In one possible implementation, beam-related information includes signal quality measurements of each beam in a second beam set, which is a subset of the first beam set. Obtaining the first beam set based on the first model includes obtaining the first beam set based on both the first model and the second beam set. In this way, the network device can select downlink transmission beams that meet the requirements (e.g., beams with better channel quality) based on the signal quality measurements of each beam in the second beam set to ensure communication quality.

[0014] In one possible implementation, the beam-related information also includes the beam index of each beam in the second beam set. Each beam index corresponds to a signal quality measurement. The network device can determine the beam index of the downlink transmission beam based on the beam index of each beam in the second beam set.

[0015] In one possible implementation, beam-related information includes the beam index of each of the first K beams in the third beam set, where the first K beams are ranked by signal quality measurement values ​​from highest to lowest. The third beam set is a subset of the first beam set and is used to validate the first beam set, where K is an integer greater than or equal to 1. Specifically, the third beam set is used to validate the first beam set. If the validation of the first beam set fails, the first K beams in the third beam set with high prediction confidence (high prediction probability / high signal quality prediction value) can be reported for network devices to select (downlink) transmission beams. This eliminates the need to report the beam indices of the first beam set, preventing network devices from selecting unsuitable downlink transmission beams, and also eliminates the need to report the beam indices of all beams in the third beam set, saving signaling overhead.

[0016] In one possible implementation, the beam-related information also includes measurements of the signal quality of each of the first K beams in the third beam set. This allows the network device to select the downlink transmit beam that meets the requirements (e.g., the beam with better channel quality) based on the predicted signal quality values ​​of the first K beams in the third beam set, thus ensuring communication quality.

[0017] In the above possible implementations, when the beam-related information includes a beam index, the network device can select the corresponding downlink transmission beam based on the beam index. Since the beam index included in the beam-related information is usually the beam index of a high-quality beam, the network device can select the downlink transmission beam from these high-quality beam indices, which can ensure communication quality while saving signaling overhead.

[0018] Furthermore, beam-related information can also include measured or predicted values ​​of the beam's signal quality, allowing network devices to select the downlink transmission beam with better quality based on the measured or predicted signal quality values. This enables network devices to select beams more accurately, for example, by choosing one or more optimal beams based on the measured or predicted signal quality values, thereby ensuring communication quality.

[0019] In one possible implementation, the first message is a channel state information (CSI) report. A CSI report can refer to a report related to channel state information. For example, a CSI report may carry one or more parameters such as channel quality indicator (CQI), precoding matrix indicator (PMI), CRI, rank indication (RI), and L1-RSRP.

[0020] In one possible implementation, the first indication information is a first value, a second value, or a third value; wherein the first value is used to indicate that the performance state of the first model is normal, the second value is used to indicate that the performance state of the first model is abnormal, and the third value is used to indicate that the performance state of the first model is unknown.

[0021] In one possible implementation, the first indication information includes two bits. For example, when the first indication information is "11" (the first indication information is the first value, and the first value is "11"), it can indicate that the AI / ML model is in a normal state, that is, the performance is good. When the first indication information is "00" (the first indication information is the second value, and the first value is "00"), it can indicate that the AI / ML model is in an abnormal state, that is, the performance is poor. When the first indication information is "10" or "01" (the first indication information is the third value, and the third value is "10" or "01"), it can indicate that the AI / ML model is in an unknown state, that is, a "no monitoring" state.

[0022] In one possible implementation, sending the first message includes: periodically sending the first message, wherein the value of the first indication information in the first message sent in each period is the same, or the value of the first indication information in the first messages sent in at least two periods is different. Based on the periodic sending of the first message by the terminal device, on the one hand, the network device can determine the performance status of the first model in multiple periods based on the first indication information corresponding to multiple periods, so as to perform corresponding processing (e.g., switching beam management modes) according to the performance status of the first model, thereby improving communication quality. On the other hand, the network device can obtain changes in beam-related information in a timely manner based on the beam-related information in the first message, so that the network device can select a beam with better quality for communication, thereby improving communication quality.

[0023] In one possible implementation, the method further includes: when M1 consecutive first indication information values ​​are second values, the terminal device switches from a first beam management mode to a second beam management mode, where M1 is an integer greater than or equal to 1; or when the proportion of first indication information values ​​being second values ​​within a preset window is greater than or equal to a first preset threshold, the terminal device switches from the first beam management mode to the second beam management mode; wherein, when the terminal device is in the first beam management mode, the first model (AI / ML model) works normally (performing beam prediction normally), and the terminal device can report relevant information of beams in the first beam set to the network device. When the terminal device is in the second beam management mode, the AI / ML model can perform beam prediction, but it does not need to report the prediction results of the AI / ML model (e.g., first beam-related information) to the network device (e.g., base station), but can report relevant information of beams in a subset of the first beam set (e.g., the second beam set or the third beam set) to the network device. It is known that when the value of the first indication information is the second value for M1 consecutive times (indicating that the performance status of the first model is abnormal), or when the proportion of the first indication information with the second value in the preset window is greater than or equal to the first preset threshold, the performance of the AI / ML model is poor, and its prediction results are unreliable / inaccurate (i.e., the AI / ML model fails). Therefore, the terminal device can switch from the first beam management mode to the second beam management mode without reporting the prediction results of the AI / ML model (such as the first beam related information) to the network device, thus avoiding affecting the communication quality.

[0024] In one possible implementation, the method further includes: receiving second indication information, the second indication information being used to indicate a switch from a first beam management mode to a second beam management mode; switching from the first beam management mode to the second beam management mode based on the second indication information; wherein, in the first beam management mode, beam-related information includes information about beams in a first beam set; in the second beam management mode, beam-related information includes information about beams in a subset of the first beam set. That is, the network device can instruct the terminal device to switch from the first beam management mode to the second beam management mode, so that the terminal device will no longer report the prediction results of the AI / ML model (e.g., first beam-related information) to the network device when the performance of the AI / ML model is poor, thus avoiding impacting communication quality. Furthermore, the network device directly instructs the terminal device to switch beam management modes, reducing the complexity of terminal processing and saving power consumption of the terminal device.

[0025] In one possible implementation, before the terminal device determines the first indication information, the method further includes: the terminal device receiving a second beam set configured by the network device; or the terminal device receiving a second beam set and a third beam set configured by the network device; wherein the second beam set and the third beam set are subsets of the first beam set, and the transmission period of the second beam set is shorter than the transmission period of the third beam set. The third beam set is used to verify the first beam set obtained by the first model. The network device can transmit the third beam set periodically so that the terminal device can verify the first beam set based on the third beam set. Therefore, the network device (e.g., a base station) can transmit the second beam set at a shorter period and the third beam set at a longer period. That is, after the network device transmits the second beam set multiple times, it can transmit the third beam set only once, avoiding frequent transmission of the third beam set and thus saving signaling overhead.

[0026] Secondly, a method is provided, which can be executed by a network device, or by a component (such as a circuit, chip, or chip system) configured in the network device, or by a logic module or software capable of implementing all or part of the functions of the network device. This application does not limit this. The following description uses a network device as an example.

[0027] The method includes: receiving a first message, the first message including first indication information and related information of a beam set, the first indication information being used to indicate the performance status of a first model, the first model being used to acquire a first beam set, the beam-related information including related information of beams in the first beam set, or the beam-related information including related information of beams in a subset of the first beam set.

[0028] Based on the communication method provided in this application embodiment, the network device can receive a first message from the terminal device. The first message can simultaneously carry first indication information and beam-related information. This eliminates the need to define a new report configuration (report field) for the first indication information, thus avoiding additional control signaling overhead.

[0029] Furthermore, after receiving the first instruction information, the network device can learn about the performance status of the AI / ML model based on the first instruction information, and thus perform adaptive processing to improve communication quality.

[0030] In one possible implementation, the beam-related information includes the beam index of each of the first K beams in the first beam set, the first K beams being the K beams whose predicted signal quality values ​​are sorted from highest to lowest, or the first K beams being the K beams whose best beam prediction probabilities are sorted from highest to lowest; K is an integer greater than or equal to 1.

[0031] In one possible implementation, the beam-related information also includes a predicted value for the signal quality of each of the first K beams in the first beam set.

[0032] In one possible implementation, the beam-related information includes signal quality measurements for each beam in a second beam set, which is a subset of the first beam set; the first model for obtaining the first beam set includes: the first model is used to obtain the first beam set based on the second beam set.

[0033] In one possible implementation, the beam-related information also includes the beam index of each beam in the second beam set.

[0034] In one possible implementation, the beam-related information includes the beam index of each of the first K beams in the third beam set, which includes the K beams whose signal quality measurements are sorted from highest to lowest; the third beam set is a subset of the first beam set and is used to verify the first beam set, where K is an integer greater than or equal to 1.

[0035] In one possible implementation, the beam-related information also includes measurements of the signal quality of each of the first K beams in the third beam set.

[0036] In one possible implementation, the first message is a Channel State Information (CSI) report.

[0037] In one possible implementation, the first indication information is a first value, a second value, or a third value; wherein the first value is used to indicate that the performance state of the first model is normal, the second value is used to indicate that the performance state of the first model is abnormal, and the third value is used to indicate that the performance state of the first model is unknown.

[0038] In one possible implementation, the first indication information comprises two bits.

[0039] In one possible implementation, receiving the first message includes: periodically receiving the first message, wherein the value of the first indication information in the first message received in each period is the same, or the value of the first indication information in the first message received in at least two periods is different.

[0040] In one possible implementation, the method further includes: sending second indication information when M1 consecutive first indication information values ​​are the second value, the second indication information indicating a switch from a first beam management mode to a second beam management mode; or sending the second indication information when the proportion of first indication information values ​​being the second value within a preset window is greater than or equal to a first preset threshold; wherein, in the first beam management mode, the beam-related information includes the beam-related information of beams in the first beam set; and in the second beam management mode, the beam-related information includes the beam-related information of beams in a subset of the first beam set.

[0041] In one possible implementation, before receiving the first message, the method further includes: configuring (sending) a second beam set; or configuring a second beam set and a third beam set; wherein the second beam set and the third beam set are subsets of the first beam set, and the transmission period of the second beam set is shorter than the transmission period of the third beam set.

[0042] Thirdly, a communication device is provided, comprising a processing module and a transceiver module. The processing module is used to determine first indication information, which indicates the performance status of a first model. The first model is used to acquire a first beam set. The transceiver module is used to send a first message to a network device. The first message includes the first indication information and related information of the beam set, wherein the beam set is the first beam set or a subset of the first beam set.

[0043] Fourthly, a communication device is provided, the communication device including a transceiver module, the transceiver module being used to receive a first message from a terminal device, the first message including first indication information and related information of a beam set, the first indication information being used to indicate the performance status of a first model, the first model being used to acquire a first beam set, the beam set being a first beam set or a subset of the first beam set.

[0044] Fifthly, a communication device is provided, including a processor. The processor is coupled to a memory and can be used to execute instructions or data in the memory to implement the method in any possible implementation of the first aspect described above. Optionally, the communication device further includes a memory. Optionally, the communication device further includes a communication interface, and the processor is coupled to the communication interface.

[0045] In one implementation, the communication interface may be a transceiver, or an input / output interface.

[0046] In another implementation, the communication device is a chip configured in a terminal device. When the communication device is a chip configured in a terminal device, the communication interface can be an input / output interface.

[0047] In a sixth aspect, a communication device is provided, including a processor. The processor is coupled to a memory and can be used to execute instructions or data in the memory to implement the method in any possible implementation of the second aspect described above. Optionally, the communication device further includes a memory. Optionally, the communication device further includes a communication interface, and the processor is coupled to the communication interface.

[0048] In one implementation, the communication interface may be a transceiver, or an input / output interface.

[0049] In another implementation, the communication device is a chip configured in a satellite. When the communication device is a chip configured in a satellite, the communication interface can be an input / output interface.

[0050] In a seventh aspect, a processor is provided, comprising: an input circuit, an output circuit, and a processing circuit. The processing circuit is configured to receive signals through the input circuit and transmit signals through the output circuit, causing the processor to execute a method in any possible implementation of any of the preceding aspects.

[0051] In specific implementation, the processor can be one or more chips, the input circuit can be input pins, the output circuit can be output pins, and the processing circuit can be transistors, gate circuits, flip-flops, and various logic circuits. The input signal received by the input circuit can be received and input by, for example, but not limited to, a receiver, and the signal output by the output circuit can be, for example, but not limited to, output to and transmitted by a transmitter. Furthermore, the input circuit and the output circuit can be the same circuit, which is used as both the input circuit and the output circuit at different times. This application does not limit the specific implementation of the processor and various circuits.

[0052] Eighthly, a communication device is provided, including a processor and a memory. The processor is used to read instructions stored in the memory, receive signals via a receiver, and transmit signals via a transmitter to execute the method in any possible implementation of any of the preceding aspects.

[0053] Optionally, the processor may be one or more, and the memory may be one or more.

[0054] Ninthly, a computer program product is provided, the computer program product comprising: a computer program (also referred to as code or instructions), which, when the computer program is run, causes a computer to perform a method in any possible implementation of any of the above aspects.

[0055] In a tenth aspect, a computer-readable storage medium is provided that stores a computer program (also referred to as code or instructions) that, when run on a computer, causes the computer to perform the method in any possible implementation of any of the above aspects.

[0056] Eleventhly, embodiments of this application provide a chip system including one or more processors for calling and executing instructions stored in memory, causing the methods in any possible implementation of any of the above aspects to be executed. The chip system may be composed of chips or may include chips and other discrete devices.

[0057] The chip system may include input circuits or interfaces for transmitting information or data, and output circuits or interfaces for receiving information or data.

[0058] In a twelfth aspect, a communication system is provided, including the aforementioned terminal device and network device. Optionally, the communication system may further include other devices that communicate with the terminal device and / or network device. Attached Figure Description

[0059] Figure 1 A schematic diagram of spatial beam prediction provided for an embodiment of this application;

[0060] Figure 2 A schematic diagram of a communication system provided in an embodiment of this application;

[0061] Figure 3 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application;

[0062] Figure 4 This application provides a schematic diagram of the structure of a network device according to an embodiment of the present application.

[0063] Figure 5 A flowchart illustrating a communication method provided in an embodiment of this application;

[0064] Figure 6 A schematic diagram of a measurement beam and a prediction beam provided for an embodiment of this application;

[0065] Figure 7 This application provides an embodiment of an interaction diagram between a network device and a terminal device.

[0066] Figure 8 This application provides another schematic diagram illustrating the interaction between a network device and a terminal device.

[0067] Figure 9 A schematic diagram of a preset window provided in an embodiment of this application;

[0068] Figure 10 A flowchart illustrating a communication method provided in an embodiment of this application;

[0069] Figure 11A This is a schematic diagram of the structure of another terminal device provided in an embodiment of this application;

[0070] Figure 11B This is a schematic diagram of the structure of another network device provided in an embodiment of this application;

[0071] Figure 12 This is a schematic diagram of a chip system provided in an embodiment of this application. Detailed Implementation

[0072] To ensure clarity and conciseness in the description of the following embodiments, a brief introduction to the relevant concepts or technologies is given first:

[0073] Beam: A beam is a communication resource. A beam can be wide, narrow, or other types of beam. Beamforming technology can be beamforming technology or other techniques. Beamforming technology can specifically be digital beamforming technology, analog beamforming technology, or hybrid digital / analog beamforming technology. Different beams can be considered different resources. The same or different information can be transmitted through different beams. Optionally, multiple beams with the same or similar communication characteristics can be considered as a single beam. A beam can include one or more antenna ports for transmitting data channels, control channels, and detection signals, etc. For example, a transmit beam can refer to the distribution of signal strength in different directions in space after a signal is transmitted through an antenna, and a receive beam can refer to the distribution of signal strength in different directions in space of the wireless signal received from the antenna. It is understood that one or more antenna ports forming a beam can also be considered as a set of antenna ports. When using low-frequency or mid-frequency bands, signals can be transmitted omnidirectionally or through a wide angle. When using high-frequency bands, thanks to the smaller carrier wavelength of high-frequency communication systems, antenna arrays consisting of many antenna elements can be arranged at both the transmitting and receiving ends. The transmitting end transmits signals with a certain beamforming weight, forming a spatially directional beam. At the same time, using an antenna array with a certain beamforming weight at the receiving end can improve the signal reception power and counteract path loss.

[0074] Beam Management encompasses a series of operations including beam scanning, beam measurement, beam reporting, and beam selection. Beam scanning refers to covering a spatial area with a set of transmit and receive beams according to pre-specified time intervals and directions. Beam measurement refers to the evaluation of the received signal quality at the BS or UE. Signal quality metrics may include, for example, reference signal receiving power (RSRP), reference signal receiving quality (RSRQ), signal-to-interference plus noise ratio (SINR), or signal-to-noise ratio (SNR). Beam reporting is the process by which the UE transmits beam quality and beam decision information to the Radio Access Network (RAN). Beam selection refers to selecting one or more suitable beams at the BS or UE based on the measurement results obtained through the beam measurement process.

[0075] AI / ML Model: An AI / ML model is a function trained on statistical data (e.g., beam measurement results) collected in a specific scenario (e.g., beam management scenario), and is applicable to that specific scenario. In the embodiments of this application, the AI / ML model can assist in beam management. The AI / ML model can also be simply referred to as an AI model, and this application does not limit it.

[0076] Use cases of terminal device-side models in beam management: Terminal device-side models can be used for spatial beam prediction in beam management. Here, a terminal device-side model refers to an AI / ML model deployed on the terminal device side, meaning the inference operation is performed on the terminal device side. For example, the terminal device can perform spatial beam prediction for beam set Set 2 based on measurements of beam set Set 1. Specifically, the terminal device can use measurements of the signal quality of beams in Set 1 as input or part of the input to the AI / ML model to predict the signal quality of beams in Set 2.

[0077] Set 1 and Set 2 typically have the following two relationships: 1) such as Figure 1Figure (a) shows a schematic diagram of spatial beam prediction. The reference signal types corresponding to Set 1 and Set 2 can be different. For example, Set 1 is the beam set corresponding to a wider synchronization signal / PBCH block (SSB) (i.e., the beam set scanned based on the SSB), and Set 2 is the beam set corresponding to a narrower channel state information-reference signal (CSI-RS) (i.e., the beam set scanned based on the CSI-RS). The number of beams in Set 1 can be less than that in Set 2.

[0078] In one possible implementation, the SSB and CSI-RS have a quasi-colocation (QCL) relationship (e.g., QCL-D), in which case the terminal device can assume that the SSB and CSI-RS use the same spatial filter.

[0079] After the terminal device predicts the beam set corresponding to CSI-RS based on the beam set corresponding to SSB, it can send the relevant information of the beam set corresponding to CSI-RS (e.g., the beam index of CSI-RS beam and the predicted value of signal quality) to the network device. The network device can then communicate with the terminal device based on the relevant information of the beam set corresponding to CSI-RS.

[0080] 2) such as Figure 1 Figure (b) shows another schematic diagram of spatial beam prediction. Set 1 is a subset of Set 2. For example, Set 2 contains S1 beams, and Set 1 contains S2 beams from Set 2. S1 is an integer greater than 1, and S2 is an integer less than S1. Set 1 and Set 2 can be beam sets corresponding to SSB signals or CSI-RS signals.

[0081] To ensure the quality of communication links, performance monitoring and lifecycle management of AI / ML models are essential. The selection of performance metrics, the establishment of reporting content, and the design of reporting methods are key aspects of constructing a suitable performance monitoring framework and are also problems that urgently need to be addressed.

[0082] One sub-topic in Release 19AI / ML in Beam Management is performance monitoring. Current discussion suggests that performance monitoring should be initiated by the network side, with two main options: Option 1: The UE reports measurement results to the network side (NW side), and the network side calculates performance metrics and makes decisions based on the measurement results; Option 2: The UE calculates performance metrics based on the measurement results and reports them to the network side for decision-making. However, currently, there is no consensus on how the UE should report performance metrics in Option 2.

[0083] This application provides a communication method that includes a performance indicator reporting method and a network decision-making method, enabling network devices and / or terminal devices to perform timely lifecycle management (e.g., switching / rollback) of AI / ML models based on performance monitoring, thereby ensuring communication quality.

[0084] For example, the communication method provided in the embodiments of this application can be applied to beam prediction scenarios.

[0085] The technical solutions of this application can be applied to various communication systems. For example, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, worldwide interoperability for microwave access (WiMAX) communication systems, 5G mobile communication systems, or new radio (NR), etc. The 5G mobile communication system described in this application includes non-standalone (NSA) 5G mobile communication systems and / or standalone (SA) 5G mobile communication systems. The technical solutions provided in this application can also be applied to future communication systems, such as sixth-generation mobile communication systems. Communication systems can also be future evolved public land mobile network (PLMN) networks, device-to-device (D2D) networks, machine-to-machine (M2M) networks, Internet of Things (IoT) networks, or other networks.

[0086] Figure 2A schematic diagram of a communication system to which the technical solutions provided in the embodiments of this application are applicable is given. The communication system may include a network device 200 and one or more terminal devices 100 connected to the network device 200. Figure 2 (Only one is shown). Data transmission can occur between network devices (also known as network-side devices) and terminal devices (also known as terminal device-side devices). In this embodiment, an AI / ML model is deployed on the terminal device 100, and the terminal device can report MPI to the network device. The MPI is used to indicate the status of the AI / ML model.

[0087] In this application, network device 200 can be a device capable of communicating with terminal device 100. For example, network device 200 can be a base station, which can be an evolved Node B (eNB or eNodeB) in LTE, a base station in NR, a relay station or access point, or a base station in a future network, etc., without limitation in this embodiment. In NR, a base station can also be called a transmission reception point (TRP) or gNB. In this embodiment, network device can be a separately sold network device, such as a base station, or a chip within a network device that implements the corresponding functions. In this embodiment, the chip system can be composed of chips or include chips and other discrete components. In the technical solutions provided in this embodiment, the network device itself is used as an example to describe the technical solutions provided in this embodiment.

[0088] In this application embodiment, the terminal device 100 can also be referred to as a terminal device, which can be a device with wireless transceiver capabilities. The terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on water (such as on ships); and it can also be deployed in the air (e.g., on airplanes, balloons, and satellites). The terminal device can be user equipment (UE). The UE includes handheld devices, vehicle-mounted devices, wearable devices, or computing devices with wireless communication capabilities. For example, the UE can be a mobile phone, tablet computer, or computer with wireless transceiver capabilities. The terminal device can also be a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in autonomous driving, a wireless terminal device in telemedicine, a wireless terminal device in a smart grid, a wireless terminal device in a smart city, a wireless terminal device in a smart home, etc. In this application embodiment, the terminal device can be a separately sold terminal device or a chip within a terminal device. In the technical solutions provided in the embodiments of this application, the terminal device is used as an example to describe the technical solutions provided in the embodiments of this application.

[0089] Examples of this application Figure 2 The network device 200 or terminal device 100 can be implemented by a single device or as a functional module within a single device; this application embodiment does not specifically limit this. It is understood that the aforementioned functions can be network elements in hardware devices, software functions running on dedicated hardware, virtualization functions instantiated on a platform (e.g., a cloud platform), or chip systems. In this application embodiment, the chip system can be composed of chips or can include chips and other discrete devices.

[0090] Figure 3This is a schematic diagram of the structure of a terminal device (e.g., terminal device 100) provided in an embodiment of this application. Terminal device 100 may be a mobile phone, tablet computer, desktop computer, laptop computer, handheld computer, notebook computer, ultra-mobile personal computer (UMPC), netbook, as well as cellular phone, personal digital assistant (PDA), augmented reality (AR) device, virtual reality (VR) device, artificial intelligence (AI) device, wearable device, in-vehicle device, smart home device and / or smart city device. This embodiment of the application does not impose any special restrictions on the specific type of terminal device.

[0091] See Figure 3 The terminal device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an accelerometer sensor 180E, a distance sensor 180F, a proximity sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0092] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the terminal device 100. In other embodiments of this application, the terminal device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0093] Processor 110 may include one or more processing units. AI / ML models may be deployed in the processor (such as an NPU).

[0094] The processor 110 may also include a memory for storing instructions and data.

[0095] In some embodiments, processor 110 may include one or more interfaces.

[0096] The wireless communication function of the terminal device 100 can be implemented through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0097] The terminal device 100 can perform shooting functions through an ISP, camera 193, video codec, GPU, display 194, and application processor. The camera 193 can also be referred to as a camera module.

[0098] The external storage interface 120 can be used to connect an external storage card, such as a Micro SD card, to expand the storage capacity of the terminal device 100. The external storage card communicates with the processor 110 through the external storage interface 120 to perform data storage functions.

[0099] Internal memory 121 can be used to store computer-executable program code, which includes instructions. Processor 110 executes various functional applications and data processing of terminal device 100 by running the instructions stored in internal memory 121.

[0100] The methods described in the following embodiments can all be implemented in the terminal device 100 having the above-described hardware structure.

[0101] It is understood that the structure illustrated in this embodiment does not constitute a specific limitation on the terminal device 100. In other embodiments, the terminal device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware. For example, the terminal device 100 may also include auxiliary devices such as a mouse, keyboard, and drawing board for the processes of creating, transmitting, receiving, and customizing target expressions.

[0102] The aforementioned terminal device 100 can be a general-purpose device or a dedicated device. In specific implementations, the terminal device 100 can be a desktop computer, laptop, network server, PDA (personal digital assistant), mobile phone, tablet computer, wireless terminal device, embedded device, or other similar device. Figure 3 Devices with similar structures. This application does not limit the type of terminal device 100 to any particular embodiment.

[0103] For example, means for implementing the functions of the network device provided in the embodiments of this application can be used... Figure 4 This is achieved through device 400. Figure 4 The diagram shows a hardware structure of the device 400 provided in an embodiment of this application. The device 400 includes at least one processor 401 for implementing the functions of the network device provided in this embodiment. The device 400 may also include a bus 402 and at least one communication interface 404. The device 400 may also include a memory 403.

[0104] Bus 402 can be used to transfer information between the aforementioned components.

[0105] Communication interface 404 is used for communication with other devices or communication networks, such as Ethernet, RAN, WLAN, etc. Communication interface 404 can be an interface, circuit, transceiver, or other device capable of communication; this application does not impose any limitations. Communication interface 404 can be coupled to processor 401.

[0106] The memory 403 stores program instructions and can be executed by the processor 401 to implement the methods provided in the following embodiments of this application. For example, the processor 401 calls and executes the instructions stored in the memory 403 to implement the methods provided in the following embodiments of this application.

[0107] Optionally, memory 403 may be included in processor 401.

[0108] In a specific implementation, as one example, processor 401 may include one or more CPUs, for example... Figure 4 CPU0 and CPU1 in the CPU.

[0109] In a specific implementation, as one embodiment, device 400 may include multiple processors, for example... Figure 4 Processors 401 and 405 are specified in the text. Each of these processors may be a single-core processor or a multi-core processor. A processor here may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0110] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings. In the description of this application, unless otherwise stated, "at least one" refers to one or more, and "more than one" refers to two or more. Furthermore, to facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first," "second," etc., are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or execution order, and that "first," "second," etc., do not necessarily imply differences.

[0111] For ease of understanding, the communication method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0112] Figure 5 A flowchart illustrating the communication method provided in this application embodiment includes:

[0113] S01. The terminal device obtains the first beam set based on the first model.

[0114] The first model can be an AI / ML model. The terminal device can obtain the first beam set based on the AI / ML model.

[0115] In some embodiments, the following steps may be included before step S01:

[0116] Network devices can configure Set 1 and Set 3 to terminal devices through CSI Resource Configuration (CSI-ResourceConfig).

[0117] The measurement results of Set 1 can be used to predict Set 2. Set 1 can be a subset of Set 2.

[0118] Set 3 can be considered as a beam set used for verification / monitoring. The measurement results of Set 3 can be used to verify / monitor the prediction results of Set 2. Set 3 can be Set 2, or a subset of Set 2.

[0119] Optionally, the transmission period of Set 1 can be shorter than the transmission period of Set 3. For example, the network device can transmit Set 1 with a shorter period and Set 3 with a longer period. For example, the transmission period of Set 3 can be an integer multiple of the transmission period of Set 1.

[0120] After receiving Set 1 and Set 3 configured by the network device, the terminal device can perform measurements on Set 1 and Set 3 respectively. That is, the signal quality of each beam in Set 1 and Set 3 is measured separately, and the corresponding measurement results are obtained.

[0121] The signal quality of a beam can be measured by the layer-1 reference signal received power (L1-RSRP). For example, the measurement results for Set 1 include the L1-RSRP measurements for each beam in Set 1. The measurement results for Set 3 include the L1-RSRP measurements for each beam in Set 3.

[0122] The terminal device predicts Set 2 based on the measurement results of Set 1. An AI / ML model (first model) can be deployed on the terminal device. The AI / ML model is used to obtain Set 2. The AI / ML model can obtain Set 2 based on Set 1. Specifically, the terminal device can input the measurement results of Set 1 into the AI / ML model so that the AI / ML model can predict Set 2. Optionally, the input to the AI / ML model may also include other auxiliary information, which is not limited in this application.

[0123] The output of the AI / ML model may include beam index information for each beam in the beam set (e.g., Set 2). The beam index information may include a channel state information reference signal resource indicator (CRI) or a synchronization signal / PBCH block resource indicator (SSB-RI), which is not limited in this application.

[0124] In some embodiments, the AI / ML model can be a regression model. In this case, the prediction output of the AI / ML model may also include the predicted signal quality value for each beam in Set 2. Alternatively, the AI / ML model can be a classification model (i.e., a probabilistic model). In this case, the prediction output of the AI / ML model may also include the predicted probability that each beam in Set 2 is the optimal beam. The optimal beam may refer to the beam with the largest signal quality measurement. Taking the optimal beam as the beam with the largest L1-RSRP as an example, the probability that a beam in Set 2 has a predicted probability of 0.8 as the optimal beam means that among all the beams included in Set 2, the probability that this beam has the largest L1-RSRP is 0.8. Alternatively, the AI / ML model may include both a classification model and a regression model. In this case, the AI / ML model can simultaneously output the predicted signal quality value for each beam in Set 2 and its predicted probability of being the optimal beam.

[0125] S02. The terminal device sends a first message to the network device, and correspondingly, the network device receives the first message sent by the terminal device. The first message includes first indication information and beam-related information. The first indication information indicates the performance status of the first model, and the beam-related information includes information about beams in the first beam set, or, alternatively, information about beams in a subset of the first beam set.

[0126] For example, the first indication information can be a model performance indicator (MPI). MPI is used to indicate the performance status of an AI / ML model.

[0127] In one possible implementation, the AI / ML model can include three performance states: normal, abnormal, and unknown. The normal state indicates that the AI / ML model meets the performance requirements, i.e., good (or excellent) performance; the abnormal state indicates that the AI / ML model does not meet the performance requirements, i.e., poor (or inferior) performance; and the unknown state indicates that the AI / ML model is in a no-monitoring state. The no-monitoring state can include two scenarios: Scenario 1: The monitoring beam group is unavailable (e.g., monitoring beam group Set 3 was not sent); Scenario 2: The AI / ML model did not perform any monitoring action.

[0128] MPI can be a first value, a second value, or a third value; where the first value indicates that the performance state of the AI / ML model is normal, the second value indicates that the performance state of the first model is abnormal, and the third value indicates that the performance state of the first model is unknown.

[0129] For example, MPI may include two bits. When MPI is "11" (MPI is the first value, the first value is "11"), it can indicate that the AI / ML model is in a normal state, that is, the performance is good. When MPI is "00" (MPI is the second value, the first value is "00"), it can indicate that the AI / ML model is in an abnormal state, that is, the performance is poor. When MPI is "10" or "01" (MPI is the third value, the third value is "10" or "01"), it can indicate that the AI / ML model is in an unknown state, that is, an unmonitored state. It should be noted that the above MPI values ​​are exemplary, and this application does not limit the actual value of MPI.

[0130] Compared to using floating-point numbers to indicate the accuracy (percentage) or beam prediction accuracy (percentage) of AI / ML models, using two-bit integer values ​​to indicate the performance status of AI / ML models can avoid performance metrics occupying a large number of bits in the transmitted message, effectively saving placeholders for performance metrics (such as MPI) and reducing overhead.

[0131] In some embodiments, when the terminal device receives Set 1 and Set 3, it can measure Set 1 and Set 3 respectively to obtain measurement results for Set 1 and Set 3. Further, the terminal device can input the measurement results of Set 1 into an AI / ML model, which can output the prediction results for Set 2. Since Set 3 is a subset of Set 2, the prediction results of Set 2 include the prediction results of Set 3. The terminal device can then compare the prediction results of Set 3 with the measurement results of Set 3 to determine the MPI.

[0132] For example, if the prediction results of Set 3 and the measurement results of Set 3 satisfy at least one of the following, the MPI is determined to be "11", that is, the AI / ML model is performing well; otherwise, the MPI is determined to be "00", that is, the AI / ML model is performing poorly.

[0133] 1. The Top-1 prediction beam of Set 3 is one of the Top-K measurement beams of Set 3.

[0134] 2. The absolute value of the difference between the predicted signal quality (e.g., L1-RSRP) value corresponding to the Top-1 predicted beam of Set 3 and the measured signal quality value corresponding to the Top-1 measured beam of Set 3 is less than the preset threshold 1.

[0135] 3. The sum of the absolute values ​​of the differences between the predicted signal quality value corresponding to the Top-K predicted beam of Set 3 and the measured signal quality value corresponding to the Top-K predicted beam of Set 3 is less than the preset threshold 2.

[0136] 4. The sum of the absolute values ​​of the differences between the signal quality measurement values ​​corresponding to the Top-K prediction beam of Set 3 and the signal quality measurement values ​​corresponding to the Top-K measurement beam of Set 3 is less than the preset threshold 3.

[0137] It should be noted that when calculating the difference between the signal quality measurements corresponding to the Top-K predicted beams of Set 3 and the signal quality measurements corresponding to the Top-K measured beams of Set 3, the difference between the signal quality measurements of predicted beams and measured beams with the same order can be calculated. Taking K=3 as an example, the sum of the absolute values ​​of the differences between the signal quality measurements corresponding to the Top-K predicted beams of Set 3 and the signal quality measurements corresponding to the Top-K measured beams of Set 3 refers to the sum of absolute value 1, absolute value 2, and absolute value 3. Here, absolute value 1 can be the absolute value of the difference between the signal quality measurements corresponding to the Top-1 predicted beams of Set 3 and the signal quality measurements corresponding to the Top-1 measured beams of Set 3. Absolute value 2 can be the absolute value of the difference between the signal quality measurement value corresponding to the Top-2 predicted beams of Set 3 and the signal quality measurement value corresponding to the Top-2 measured beams of Set 3. Absolute value 3 can be the absolute value of the difference between the signal quality measurement value corresponding to the Top-3 predicted beams of Set 3 and the signal quality measurement value corresponding to the Top-3 measured beams of Set 3.

[0138] Among them, the Top-K measurement beams of the beam set are the K largest beams in the beam set in terms of signal quality measurement value; the Top-K prediction beams of the beam set are the K largest beams in the beam set in terms of signal quality prediction value, or the K beams with the highest optimal beam prediction probability.

[0139] For example, such as Figure 6 As shown, assuming Set 3 includes beam 1, beam 2, beam 3, and beam 4, the predicted signal quality and measured signal quality values ​​corresponding to beams 1 through 4 are shown in Table 1:

[0140] Table 1

[0141] Set 3 Beam 1 Beam 2 Beam 3 Beam 4 Signal quality prediction -75dB -80dB -90dB -100dB Signal quality measurement value -78dB -82dB -90dB -102dB

[0142] In this context, the Top-1 predicted beam of Set 3 refers to the beam with the highest predicted signal quality value in Set 3, i.e., beam 1; the Top-1 measured beam of Set 3 refers to the beam with the highest measured signal quality value in Set 3, i.e., beam 1. Taking K=3 as an example, the Top-K predicted beams of Set 3 refer to the top 3 beams with the highest predicted signal quality values ​​in Set 3, i.e., beam 1, beam 2, and beam 3; the Top-K measured beams of Set 3 refer to the top 3 beams with the highest measured signal quality values ​​in Set 3, i.e., beam 1, beam 2, and beam 3.

[0143] As can be seen, the Top-1 prediction beam of Set 3 (such as beam 1) is one of the Top-K measurement beams of Set 3 (such as beam 1, beam 2 and beam 3), indicating that the AI / ML model performs well.

[0144] Taking a preset threshold of 5dB as an example, the absolute value (3dB) of the difference between the predicted signal quality value (e.g., -75dB) corresponding to the Top-1 predicted beam (e.g., beam 1) of Set 3 and the measured signal quality value (e.g., -78dB) corresponding to the Top-1 measured beam (e.g., beam 1) of Set 3 is less than the preset threshold of 1 (e.g., 5dB), indicating that the AI / ML model performs well.

[0145] Taking a preset threshold of 10dB as an example, the sum of the absolute values ​​of the differences between the predicted signal quality values ​​(i.e., -75dB, -80dB, and -90dB) corresponding to the Top-K predicted beams of Set 3 (such as beam 1, beam 2, and beam 3) and the measured signal quality values ​​(i.e., -78dB, -82dB, and -90dB) corresponding to the Top-K predicted beams of Set 3 (such as beam 1, beam 2, and beam 3), i.e., (|75-78|+|80-82|+|90-90|=5), is less than the preset threshold of 2 (e.g., 10dB), indicating that the AI / ML model performs well.

[0146] Taking a preset threshold of 8dB as an example, the sum of the absolute values ​​of the differences between the signal quality measurement values ​​(i.e., -78dB, -82dB, and -90dB) corresponding to the Top-K predicted beams of Set 3 (such as beam 1, beam 2, and beam 3) and the signal quality measurement values ​​(i.e., -78dB, -82dB, and -90dB) corresponding to the Top-K measured beams of Set 3 (such as beam 1, beam 2, and beam 3) is (|78-78|+|82-82|+|90-90|=0), which is less than the preset threshold of 3 (e.g., 8dB), indicating that the AI / ML model performs well.

[0147] In the example above, the Top-K prediction beam of Set 3 is exactly the same as the Top-K measurement beam of Set 3. In practical applications, the Top-K prediction beam of Set 3 and the Top-K measurement beam of Set 3 may be different. For example, the Top-K prediction beam of Set 3 includes beam 1, beam 2 and beam 3, while the Top-K measurement beam of Set 3 includes beam 1, beam 2 and beam 4. The method for calculating the difference can be referred to the above embodiment, and will not be repeated here.

[0148] In some embodiments, if the terminal device receives Set 1 but does not receive Set 3, the terminal device obtains the prediction result of Set 2 based on Set 1. The terminal device reports the relevant information and MPI of the Top-K prediction beam of Set 2 to the network device in a report, where the MPI can be "10" or "01", indicating that the AI / ML model is in an unmonitored / unknown state.

[0149] After the terminal device determines the MPI, it can send a first message to the network device (the first message includes the MPI and beam-related information).

[0150] The first message may include MPI and beam-related information (beam-related information in Set 2, Set 1, or Set 3).

[0151] The first message can be a CSI report. A CSI report is a report related to channel state information. For example, a CSI report may carry one or more parameters from CQI, PMI, CRI, RI, and L1-RSRP.

[0152] In some embodiments, when the terminal device is in AI mode (an example of a first beam management mode), the terminal device can send a first CSI report (an example of a first message) to a network device (e.g., a base station). The first CSI report includes the prediction results of MPI and a first beam set (e.g., Set 2) (i.e., relevant information of Set 2). That is, the terminal device can configure the prediction results and MPI of Set 2 using the same CSI report configuration (which can be referred to as the first CSI report configuration).

[0153] In this context, "terminal device in AI mode" refers to the mode in which the terminal device's AI / ML model performs beam prediction normally. When the terminal device is in AI mode, it can report the beam prediction results (e.g., the prediction results of Set 2) to network devices (e.g., base stations).

[0154] The prediction results for Set 2 may include information about the top K (predicted beams) of Set 2. This information includes at least one of the following: the beam index (e.g., CRI) of the top K predicted beams of Set 2, the predicted or measured signal quality of the top K predicted beams of Set 2, or the prediction probability of the top K predicted beams of Set 2. Specifically, the top K predicted beams of Set 2 refer to the top K beams of Set 2, which include the top K beams ranked by predicted signal quality from highest to lowest, or the top K beams include the top K beams ranked by best prediction probability from highest to lowest; K is an integer greater than or equal to 1.

[0155] For example, taking Set 2 as an example, which includes three beams (e.g., beam 1, beam 2, and beam 3), the prediction results output by the AI / ML model can include the prediction probability that each beam in Set 2 is the best beam. For instance, the best beam prediction probability of beam 1 (i.e., the prediction probability that beam 1 is the best beam) could be 0.8, the best beam prediction probability of beam 1 (i.e., the prediction probability that beam 2 is the best beam) could be 0.9, and the best beam prediction probability of beam 3 (i.e., the prediction probability that beam 3 is the best beam) could be 0.7. The beams in Set 2, sorted from highest to lowest based on their best beam prediction probabilities, could be: beam 2, beam 1, beam 3. Assuming K = 2, the first two beams of Set 2 would include beam 2 and beam 1.

[0156] like Figure 7 As shown in (a), when the terminal device is in AI mode, if the terminal device receives Set 1 but does not receive Set 3, the terminal device can encapsulate the prediction result of Set 2 and an MPI indicating that the AI ​​mode status is "no monitoring" into the first CSI report and send the first CSI report to the network device.

[0157] For example, such as Figure 7 As shown in (b), when the terminal device is in AI mode, if the terminal device receives Set 1 and Set 3, it can compare the prediction results of the AI / ML model with the measurement results of Set 3 to obtain the MPI (an MPI indicating whether the AI ​​mode is "good performance" or "poor performance"). The terminal device can encapsulate the prediction results of Set 2 and an MPI indicating whether the AI ​​mode is "good performance" or "poor performance" into a second CSI report and send the first CSI report to the network device.

[0158] In other embodiments, when the terminal device is in conventional mode (also known as non-AI mode, i.e., second beam management mode), the terminal device may send a second CSI report (another example of the first message) to the network device (e.g., a base station).

[0159] In the case of the terminal device in the traditional mode, the AI / ML model of the terminal device can perform beam prediction, but it does not need to report the prediction results of the AI / ML model (e.g., the prediction results of Set 2) to the network device (e.g., the base station). Instead, it can report the relevant information of Set 1 or Set 3 to the network device (e.g., the base station).

[0160] The relevant information for Set 1 may include the signal quality measurement value of each beam in Set 1. Optionally, the relevant information for Set 1 may also include the beam index of each beam in Set 1. The relevant information for Set 3 may include the beam index of each beam in the first K beams of Set 3. Optionally, the relevant information for Set 3 may also include the signal quality measurement value of each beam in the first K beams of Set 3. The first K beams of Set 3 include the K beams with the highest to lowest signal quality measurement values.

[0161] In the above possible implementations, when the beam-related information includes a beam index, the network device can select the corresponding downlink transmission beam based on the beam index. Since the beam index included in the beam-related information is usually the beam index of a high-quality beam, the network device can select the downlink transmission beam from these high-quality beam indices, which can ensure communication quality while saving signaling overhead.

[0162] Furthermore, beam-related information can also include measured or predicted values ​​of the beam's signal quality, allowing network devices to select the downlink transmission beam with better quality based on the measured or predicted signal quality values. This enables network devices to select beams more accurately, for example, by choosing one or more optimal beams based on the measured or predicted signal quality values, thereby ensuring communication quality.

[0163] For example, such as Figure 8As shown in (b), when the terminal device is in traditional mode, if the terminal device receives Set 1 but not Set 3, it can encapsulate the measurement results of Set 1 (e.g., the measurement results of the Top-K beam of Set 1) and an MPI indicating the AI ​​mode status as "no monitoring" into the second CSI report. That is, the second CSI report includes (carries) the MPI and the measurement results of Set 1. In other words, the terminal device can use the same CSI report configuration (which can be called the second CSI report configuration) to configure the measurement results of Set 1 and the MPI.

[0164] For example, such as Figure 8 As shown in (a), when the terminal device is in conventional mode, if it receives Set 1 and Set 3, it can compare the prediction results of the AI / ML model with the measurement results of Set 3 to obtain the MPI (an MPI indicating whether the AI ​​mode is "good" or "poor"). The terminal device can encapsulate the measurement results of Set 3 (e.g., the measurement results of the Top-K beam of Set 3) and an MPI indicating whether the AI ​​mode is "good" or "poor" into a second CSI report. That is, the second CSI report includes (carries) the MPI and the measurement results of Set 3.

[0165] Terminal devices can periodically send CSI reports (first CSI report or second CSI report) to network devices. The MPI value in each CSI report sent in each period can be the same or different.

[0166] Furthermore, the method provided in this application embodiment also includes:

[0167] When the terminal device is in AI mode, determine whether to switch from AI mode to (revert to) traditional mode.

[0168] In one implementation, if the AI / ML model continues to perform poorly for a period of time, the terminal device can switch from AI mode to traditional mode, i.e., fallback to traditional mode.

[0169] Terminal devices can determine whether to switch from AI mode to traditional mode based on the following methods.

[0170] Method 1: The terminal device autonomously decides whether to switch from AI mode to traditional mode, including the following options:

[0171] Option 1-1 states that if the M1 consecutive MPI values ​​are the second value, the terminal device can revert from AI mode to traditional mode.

[0172] Optionally, the terminal device can record MPIs other than those in the "No Monitoring" state, i.e., it can record MPIs in the "Good Performance" and "Poor Performance" states. If the terminal device records M1 consecutive MPIs in the "Poor Performance" state, it indicates that the AI / ML model's performance is poor, and its prediction results are unreliable / inaccurate (i.e., the AI / ML model is invalid). Therefore, the terminal device can revert from AI mode to traditional mode without reporting the AI / ML model's prediction results (e.g., the prediction results of Set2) to the network device. Here, M1 is an integer greater than or equal to 1.

[0173] Option 1-2: If the proportion of MPIs with the second value in the preset window is greater than or equal to the first preset threshold, the system reverts from AI mode to traditional mode. That is, the terminal device can determine the proportion of "poor performance" MPIs included in the preset window. If the proportion of "poor performance" MPIs in the preset window exceeds the first preset threshold P1, it indicates that the AI / ML model's performance is poor, and its prediction results are unreliable / inaccurate. Therefore, the terminal device can revert from AI mode to traditional mode. The preset window can be a window of size N1, used to continuously record N1 MPIs whose state is not "unmonitored". For example, upon receiving Set 1 and Set 3, the terminal device can record an MPI whose state is not "unmonitored" (e.g., an MPI with a "good performance" state) in the preset window, and upon receiving Set 1 and Set 3 again, continue to record an MPI whose state is not "unmonitored" (e.g., an MPI with a "poor performance" state) in the preset window. If N1 MPIs have been recorded in the preset window, the preset window can be slid to discard one or more of the earliest recorded MPIs in order to record the latest MPI.

[0174] For example, such as Figure 9 As shown, taking N1=6 and the first preset threshold P1 as 50% as an example, the preset window can include 6 MPIs, namely MPI 1, MPI 2, MPI 3, MPI 4, MPI 5, and MPI 6. The values ​​of MPI 1, MPI 2, MPI 3, MPI 4, MPI 5, and MPI 6 can be 00, 11, 00, 00, 00, and 11, respectively. The number of MPIs with a value of 00 is 4, accounting for 4 / 6 ≈ 66.6%. Since 66.6% > 50%, in this case, the terminal device can switch from AI mode to (revert to) traditional mode.

[0175] Options 1-3: If the difference between the number of MPIs with the second value and the number of MPIs with other values ​​(e.g., the first value or the third value) satisfies the third preset threshold P3, the terminal device can revert from AI mode to traditional mode.

[0176] Options 1-4: If the number of MPIs with the second value is greater than or equal to the number of MPIs with other values, the terminal device can revert from AI mode to traditional mode.

[0177] It should be noted that the above options are some examples of how terminal devices determine whether to switch from AI mode to traditional mode based on MPI. Other ways in which terminal devices determine whether to switch from AI mode to traditional mode based on MPI (e.g., more determinations based on the number of MPI values ​​of the second value) are all within the scope of protection of this application.

[0178] In some implementations, the terminal device can revert from AI mode to traditional mode when sending the next N CSI reports (the first CSI report). Here, N is an integer greater than or equal to 1.

[0179] Method 2: The terminal device determines whether to switch (rollback) from AI mode to traditional mode based on the instructions from the network device, including the following options:

[0180] Option 2-1: The network device can record MPIs reported by the terminal device that are not in the "No Monitoring" state, i.e., it can record MPIs in the "Good Performance" and "Poor Performance" states. If the network device records M1 consecutive MPIs in the "Poor Performance" state, the network device can send a first instruction (carrying second indication information) to the terminal device. The first instruction (with the second indication information) is used to instruct the terminal device to return from AI mode to traditional mode.

[0181] It should be understood that recording MPIs by the network device is an optional step in this application. For example, if the network device receives M1 MPIs with a status of "poor performance", the network device can send a first instruction (carrying second indication information) to the terminal device. The first instruction (with the second indication information) is used to instruct the terminal device to return from AI mode to traditional mode.

[0182] It should also be understood that the phrase "M1 consecutive MPIs in the 'poor performance' state" in this application is merely an example. For instance, if M1 MPIs in a certain number of MPIs are in the "poor performance" state, the network device can send a first instruction (carrying second indication information) to the terminal device. The first instruction (and the second indication information) is used to instruct the terminal device to revert from AI mode to traditional mode. Other similar instances in this document, such as "N1 consecutive" mentioned below, can be referenced here. To avoid redundancy, they will not be specifically explained further below.

[0183] Option 2-2: The network device determines the proportion of "poor performance" MPIs included in the preset window. If the proportion of "poor performance" MPIs in the preset window exceeds a first preset threshold P1, the network device can send a first instruction to the terminal device. The first instruction instructs the terminal device to revert from AI mode to traditional mode. The preset window can be a window of size N1, used to continuously record N1 MPIs whose state is not "unmonitored". For example, upon receiving an MPI whose state is not "unmonitored" (e.g., an MPI with a "good performance" state), the network device can record that MPI in the preset window (e.g., an MPI with a "poor performance" state) upon receiving the next MPI whose state is not "unmonitored". If N1 MPIs have been recorded in the preset window, the preset window can slide, discarding one or more of the earliest recorded MPIs to record the latest MPI.

[0184] Optionally, the first instruction can be carried in RRC or MAC CE.

[0185] In some implementations, after receiving the first instruction, the terminal device can revert from AI mode to traditional mode when sending the next N CSI reports (the first CSI report).

[0186] The corresponding parameters (e.g., one or more of M, N, N1, P1 and P3) involved in each option in Method 1 and Method 2 above can be configured by the network device (e.g., base station) and notified to the terminal device, or configured by the terminal device and reported to the network device (e.g., base station). This application does not limit this.

[0187] Option 2-3: If the difference between the number of MPIs with the second value and the number of MPIs with other values ​​(e.g., the first value or the third value) satisfies a third preset threshold P3, the network device instructs the terminal device to revert from AI mode to traditional mode.

[0188] Options 2-4: If the number of MPIs with the second value is greater than or equal to the number of MPIs with other values, the network device instructs the terminal device to revert from AI mode to traditional mode.

[0189] It should be noted that the above options are some examples of network devices determining whether to instruct terminal devices to switch from AI mode to traditional mode based on MPI. Other ways in which network devices determine whether to instruct terminal devices to switch from AI mode to traditional mode based on MPI (e.g., network devices instructing terminal devices to switch from AI mode to traditional mode based on the number of MPI values ​​of the second value) are all within the scope of protection of this application.

[0190] Furthermore, the method provided in this application embodiment also includes:

[0191] When a terminal device switches from AI mode to traditional mode, the terminal device determines whether to switch back to AI mode.

[0192] In one implementation, if the AI / ML model continues to perform well for a period of time after the terminal device switches from AI mode to traditional mode, the terminal device can switch from traditional mode to AI mode.

[0193] Terminal devices can determine whether to switch from traditional mode to AI mode based on the following methods.

[0194] Method 3: The terminal device autonomously decides whether to switch from traditional mode to AI mode, including the following options:

[0195] Option 3-1 allows the terminal device to record MPIs other than those in the "No Monitoring" state, specifically those in the "Good Performance" and "Poor Performance" states. If the terminal device records M2 consecutive MPIs in the "Good Performance" state, it indicates that the AI / ML model is performing well, and its prediction results are reliable / accurate (i.e., the AI / ML model is effective). Therefore, the terminal device can switch from traditional mode to AI mode and subsequently report the AI / ML model's prediction results (e.g., the prediction results of Set2) to the network device. Here, M2 is an integer greater than or equal to 1.

[0196] Option 3-2: The terminal device can determine the proportion of "good-performing" MPIs included in the preset window. If the proportion of "good-performing" MPIs in the preset window exceeds a second preset threshold P2, it indicates that the AI / ML model is performing well and its prediction results are reliable / accurate. Therefore, the terminal device can switch from the traditional mode to the AI ​​mode. The preset window can be a window of size N1, used to continuously record N1 MPIs whose state is not "unmonitored".

[0197] Option 3-3: If the difference between the number of MPIs with the first value and the number of MPIs with other values ​​(e.g., the second or third value) satisfies the fourth preset threshold P4, the terminal device can switch from the traditional mode to the AI ​​mode.

[0198] Option 3-4: If the number of MPIs with the first value is greater than or equal to the number of MPIs with other values, the terminal device can switch from traditional mode to AI mode.

[0199] It should be noted that the above options are some examples of how terminal devices determine whether to switch from traditional mode to AI mode based on MPI. Other methods of determining whether to switch from traditional mode to AI mode based on MPI (e.g., determining the switch from traditional mode to AI mode based on the number of MPI values ​​of the first value) are all within the scope of protection of this application.

[0200] In some implementations, the terminal device can switch from conventional mode to AI mode when sending the next N CSI reports (the first CSI report). Here, N is an integer greater than or equal to 1.

[0201] Method 4: The terminal device determines whether to switch from traditional mode to AI mode based on the instructions from the network device, including the following options:

[0202] Option 4-1: If the network device records M2 consecutive MPIs with the status "good performance", the network device can send a second instruction (carrying third indication information) to the terminal device. The second instruction (and the third indication information) is used to instruct the terminal device to switch from traditional mode to AI mode.

[0203] Option 4-2: The network device determines the proportion of "good performance" MPIs included in the preset window. If the proportion of "good performance" MPIs in the preset window exceeds the second preset threshold P2, the network device can send a second instruction to the terminal device. The second instruction is used to instruct the terminal device to switch from traditional mode to AI mode.

[0204] Optionally, the second instruction can be carried in RRC, MAC CE, or physical layer signaling (such as L1 signaling).

[0205] In some implementations, after receiving the second instruction, the terminal device can switch from the traditional mode to the AI ​​mode when sending the next N CSI reports (the first CSI report).

[0206] The parameters involved in each option in Methods 3 and 4 above (such as one or more of M, N, N1, P2 and P4) can be configured by the network device for the base station and notified to the terminal device, or configured by the terminal device itself and reported to the network device. This application does not limit this.

[0207] Option 4-3: If the difference between the number of MPIs with the first value and the number of MPIs with other values ​​(e.g., the second or third value) satisfies the fourth preset threshold P4, the network device instructs the terminal device to switch from the traditional mode to the AI ​​mode.

[0208] Option 4-4: When the number of MPIs with the first value is greater than or equal to the number of MPIs with other values, the network device instructs the terminal device to switch from traditional mode to AI mode.

[0209] It should be noted that the above options are some examples of network devices determining whether to instruct terminal devices to switch from traditional mode to AI mode based on MPI. Other methods of determining whether to instruct terminal devices to switch from traditional mode to AI mode based on MPI (e.g., instructing terminal devices to switch from traditional mode to AI mode based on the number of MPI values ​​of the first value) are all within the scope of protection of this application.

[0210] After receiving the first message from the terminal device, the network device can select a downlink transmission beam that meets the requirements (such as a beam with better channel quality) based on the beam-related information carried in the first message, and communicate with the terminal device based on the downlink transmission beam.

[0211] Furthermore, network devices and / or terminal devices can perform timely switching and rollback operations on AI / ML models based on MPI, thereby ensuring communication quality.

[0212] Based on the communication method provided in this application embodiment, the terminal device can perform performance monitoring on a first model (e.g., an AI / ML model) to obtain first indication information. It can then send the first indication information and related information about the beam set in the same message (first message) to the network device. This eliminates the need to define a new report configuration (report field) for the first indication information and avoids additional control signaling overhead. Furthermore, by sending the first indication information to the network device, the terminal device can obtain the performance status of the AI / ML model based on the first indication information, thereby enabling adaptive processing and improving communication quality.

[0213] like Figure 10 As shown, with Figure 5 The first beam set is Set 2, the second beam set is Set 1, and the third beam set is Set 3. Taking MPI as an example, the flow of the communication method provided in this application embodiment is illustrated by way of example, including:

[0214] 1010. The network device configures Set 1 and Set 3 to the terminal device. Correspondingly, the terminal device receives Set 1 and Set 3 configured by the network device. The measurement results of Set 1 can be used to predict Set 2. Set 1 can be a subset of Set 2. Set 3 can be considered a beam set used for verification / monitoring. The measurement results of Set 3 can be used to verify / monitor the prediction results of Set 2. Set 3 can be Set 2 or a subset of Set 2.

[0215] Specifically, step 1010 can be referred to the explanation in step S01, and will not be repeated here.

[0216] 1020. The terminal device makes a prediction for Set 2 based on the measurement results of Set 1.

[0217] In one possible implementation, the terminal device can input the measurement results of Set 1 into the AI / ML model, so that the AI / ML model can perform predictions to obtain Set 2. Specifically, step 1020 can be referred to the description in step S01.

[0218] 1030. Terminal equipment determines MPI.

[0219] For example, the terminal device determines the MPI based on the prediction results of Set 3 and the measurement results of Set 3, such as determining the value of the MPI. For details on how the MPI is determined, please refer to the explanation in step S01.

[0220] 1040. The terminal device sends a first message to the network device (the first message includes MPI and beam-related information), and the network device receives the first message accordingly.

[0221] The first message can be a CSI report. The content carried in this first message, such as beam-related information, depends on the mode of the terminal device. For example, if the terminal device is in AI mode, the beam-related information included in the first message could be Set 2 information. For details, please refer to step S02 regarding the explanation of the first CSI report, second CSI report, etc.

[0222] Optionally, the process may also include the following steps:

[0223] 1050. When the terminal device is in AI mode, determine whether to switch from AI mode to (revert to) traditional mode.

[0224] Terminal devices can decide independently whether to switch from AI mode to traditional mode, or they can determine whether to switch from AI mode to traditional mode based on instructions from network devices. For specific switching methods, please refer to the explanations in Method 1 and Method 2 of step S02.

[0225] 1060. When a terminal device switches from AI mode to traditional mode, the terminal device determines whether to switch back to AI mode.

[0226] Terminal devices can decide independently whether to switch from traditional mode to AI mode, or they can determine whether to switch from traditional mode to AI mode based on instructions from network devices. For specific switching methods, please refer to the explanations in methods 3 and 4 of step S02.

[0227] 1070. The network device determines the downlink transmission beam based on the first message.

[0228] 1080. Network devices communicate with terminal devices based on downlink transmission beams.

[0229] There is no necessary execution order between steps 1010 and 1080. This embodiment does not specify the execution order between the steps.

[0230] Figure 10 For explanations of the corresponding steps or related concepts, please refer to [link / reference]. Figure 5 The embodiments shown are not described in detail here.

[0231] The communication method provided in this application offers selection of terminal device reported data (e.g., MPI), reporting method (reporting via CSI report), and network configuration. The terminal device can perform performance monitoring on the AI / ML model to obtain the MPI (MPI is used to indicate the performance status of the AI / ML model), and can send the MPI and beam-related information to the network device in the same message (first message), without needing to define a new report configuration (report field) for the MPI, thus avoiding additional control signaling overhead. Furthermore, the network device and / or the terminal device can perform timely switching and rollback operations on the AI / ML model based on the MPI, thereby ensuring communication quality.

[0232] In some embodiments, when the functional modules are divided in an integrated manner, Figure 11A A schematic diagram of a terminal device 1000 is shown. The terminal device 1000 includes a processing module 1001 and a transceiver module 1002.

[0233] The processing module 1001 is used to obtain the first beam set based on the first model.

[0234] The transceiver module 1002 is used to send a first message to the network device. The first message includes first indication information and beam-related information. The first indication information is used to indicate the performance status of the first model. The beam-related information includes information about the beams in the first beam set, or the beam-related information includes information about the beams in a subset of the first beam set.

[0235] In some embodiments, when the functional modules are divided in an integrated manner, Figure 11B A schematic diagram of a network device 1100 is shown. The network device 1100 includes a transceiver module 1101 and a processing module 1102.

[0236] The transceiver module 1101 is used to receive a first message, which includes first indication information and beam-related information. The first indication information is used to indicate the performance status of the first model, the first model is used to obtain a first beam set, and the beam-related information includes information about the beams in the first beam set, or the beam-related information includes information about the beams in a subset of the first beam set.

[0237] The processing module 1102 is used to send second indication information to the terminal device through the transceiver module 1101 when the value of the first indication information is the second value for M1 consecutive times. The second indication information is used to instruct the terminal device to switch from the first beam management mode to the second beam management mode. Alternatively, the processing module 1102 is used to send second indication information to the terminal device through the transceiver module 1101 when the proportion of the first indication information with the value of the second value in the preset window is greater than or equal to the first preset threshold. The preset window is used to continuously record N1 first indication information with the value of the first value and the value of the second value, where N1 is an integer greater than or equal to 1.

[0238] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0239] This application also provides a chip system, such as... Figure 12 As shown, the chip system includes at least one processor 1201 and at least one interface circuit 1202. The processor 1201 and the interface circuit 1202 are interconnected via lines. For example, the interface circuit 1202 can be used to receive signals from other devices (e.g., the memory of a terminal device). As another example, the interface circuit 1202 can be used to send signals to other devices (e.g., the processor 1201).

[0240] For example, interface circuit 1202 can read instructions stored in the memory of the terminal device and send those instructions to processor 1201. When the instructions are executed by processor 1201, the terminal device (e.g., Figure 3 The terminal device 100 shown or the network device (such as...) Figure 4 The apparatus 400 shown performs the steps in the above embodiments.

[0241] Of course, the chip system may also include other discrete components, and this application embodiment does not specifically limit this.

[0242] This application embodiment also provides a computer-readable storage medium, which includes computer instructions, and when the computer instructions are used in a terminal device (such as...) Figure 3 The terminal device 100 shown or the network device (such as...) Figure 4When the device 400 shown is operated, it causes the terminal device or network device to perform the various functions or steps performed by the terminal device in the above method embodiment, and causes the network device to perform the various functions or steps performed by the network device in the above method embodiment.

[0243] This application also provides a computer program product that, when run on a computer, causes the computer to perform various functions or steps performed by the terminal device in the above method embodiments.

[0244] This application also provides a processing device, which can be divided into different logical units or modules according to function. Each unit or module performs different functions, so that the processing device performs the various functions or steps performed by the terminal device or network device in the above method embodiments.

[0245] Through the above description of the embodiments, those skilled in the art can clearly understand that the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0246] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0247] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0248] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0249] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially or in other words, the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0250] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, include: The first beam set is obtained based on the first model; Send a first message, the first message including first indication information and beam-related information, the first indication information being used to indicate the performance status of the first model, the beam-related information including information about beams in the first beam set, or the beam-related information including information about beams in a subset of the first beam set.

2. The method according to claim 1, characterized in that, The beam-related information includes the beam index of each beam in the first K beams of the first beam set. The first K beams include the K beams whose predicted signal quality values ​​are sorted from highest to lowest, or the first K beams include the K beams whose best beam prediction probabilities are sorted from highest to lowest. K is an integer greater than or equal to 1.

3. The method according to claim 2, characterized in that, The beam-related information also includes the predicted signal quality of each of the first K beams in the first beam set.

4. The method according to claim 1, characterized in that, The beam-related information includes the signal quality measurement value of each beam in the second beam set, which is a subset of the first beam set; The process of obtaining the first beam set based on the first model includes: The first beam set is obtained based on the first model and the second beam set.

5. The method according to claim 4, characterized in that, The beam-related information also includes the beam index of each beam in the second beam set.

6. The method according to claim 1, characterized in that, The beam-related information includes the beam index of each beam in the first K beams of the third beam set, and the first K beams include the K beams whose signal quality measurement values ​​are sorted from high to low; the third beam set is a subset of the first beam set, and the third beam set is used to verify the first beam set, where K is an integer greater than or equal to 1.

7. The method according to claim 6, characterized in that, The beam-related information also includes measurements of the signal quality of each of the first K beams in the third beam set.

8. The method according to any one of claims 1-7, characterized in that, The first message is a Channel State Information (CSI) report.

9. The method according to any one of claims 1-8, characterized in that, The value of the first indication information is a first value, a second value, or a third value; Wherein, the first value is used to indicate that the performance state of the first model is normal, the second value is used to indicate that the performance state of the first model is abnormal, and the third value is used to indicate that the performance state of the first model is unknown.

10. The method according to claim 9, characterized in that, Sending the first message includes: The first message is sent periodically, and the value of the first indication information in the first message sent in each period is the same, or the value of the first indication information in the first message sent in at least two periods is different.

11. The method according to claim 10, characterized in that, The method further includes: If the first indication information is valued as the second value for M1 consecutive times, the system switches from the first beam management mode to the second beam management mode, where M1 is an integer greater than or equal to 1; or When the proportion of the first indication information that takes the second value in the preset window is greater than or equal to the first preset threshold, the system switches from the first beam management mode to the second beam management mode. In the first beam management mode, the beam-related information includes information about the beams in the first beam set; in the second beam management mode, the beam-related information includes information about the beams in a subset of the first beam set.

12. The method according to any one of claims 1-10, characterized in that, The method further includes: Receive second indication information, the second indication information being used to indicate switching from the first beam management mode to the second beam management mode; Based on the second indication information, switch from the first beam management mode to the second beam management mode; In the first beam management mode, the beam-related information includes information about the beams in the first beam set; in the second beam management mode, the beam-related information includes information about the beams in a subset of the first beam set.

13. The method according to any one of claims 1-12, characterized in that, The method further includes: Receive the second beam set; or Receives the second and third beam sets; Wherein, the second beam set and the third beam set are subsets of the first beam set, and the transmission period of the second beam set is shorter than the transmission period of the third beam set.

14. A communication method, characterized in that, include: A first message is received, the first message including first indication information and beam-related information, the first indication information being used to indicate the performance status of a first model, the first model being used to acquire a first beam set, and the beam-related information including information about beams in the first beam set, or the beam-related information including information about beams in a subset of the first beam set.

15. The method according to claim 14, characterized in that, The beam-related information includes the beam index of each beam in the first K beams of the first beam set. The first K beams include the K beams whose predicted signal quality values ​​are sorted from highest to lowest, or the first K beams include the K beams whose best beam prediction probabilities are sorted from highest to lowest. K is an integer greater than or equal to 1.

16. The method according to claim 15, characterized in that, The beam-related information also includes the predicted signal quality of each of the first K beams in the first beam set.

17. The method according to claim 14, characterized in that, The beam-related information includes the signal quality measurement value of each beam in the second beam set, which is a subset of the first beam set; The first model used to obtain the first beam set includes: The first model is used to obtain the first beam set based on the second beam set.

18. The method according to claim 17, characterized in that, The beam-related information also includes the beam index of each beam in the second beam set.

19. The method according to claim 14, characterized in that, The beam-related information includes the beam index of each beam in the first K beams of the third beam set, and the first K beams include the K beams whose signal quality measurement values ​​are sorted from high to low; the third beam set is a subset of the first beam set, and the third beam set is used to verify the first beam set, where K is an integer greater than or equal to 1.

20. The method according to claim 19, characterized in that, The beam-related information also includes measurements of the signal quality of each of the first K beams in the third beam set.

21. The method according to any one of claims 14-20, characterized in that, The first message is a Channel State Information (CSI) report.

22. The method according to any one of claims 14-21, characterized in that, The value of the first indication information is a first value, a second value, or a third value; Wherein, the first value is used to indicate that the performance state of the first model is normal, the second value is used to indicate that the performance state of the first model is abnormal, and the third value is used to indicate that the performance state of the first model is unknown.

23. The method according to claim 22, characterized in that, The receipt of the first message includes: The first message is received periodically, and the value of the first indication information in the first message received in each period is the same, or the value of the first indication information in the first message received in at least two periods is different.

24. The method according to claim 23, characterized in that, The method further includes: If the first indication information is equal to the second value for M1 consecutive times, a second indication information is sent, which indicates a switch from the first beam management mode to the second beam management mode; or If the proportion of the first indication information that takes the second value in the preset window is greater than or equal to the first preset threshold, the second indication information is sent. In the first beam management mode, the beam-related information includes information about the beams in the first beam set; in the second beam management mode, the beam-related information includes information about the beams in a subset of the first beam set.

25. The method according to any one of claims 14-24, characterized in that, Before receiving the first message, the method further includes: Configure a second beam set; or Configure a second beam set and a third beam set; the second beam set and the third beam set are subsets of the first beam set, and the transmission period of the second beam set is shorter than the transmission period of the third beam set.

26. A communication system, characterized in that, It includes a terminal device and a network device, wherein the terminal device performs the method as described in any one of claims 1-13, and the network device performs the method as described in any one of claims 14-25.

27. A communication device, characterized in that, The communication device is a terminal device or a network device, and the communication device includes: a wireless communication module, a memory, and one or more processors; the wireless communication module, the memory, and the processor are coupled together. The memory is used to store computer program code, which includes computer instructions; when the computer instructions are executed by the processor, the communication device performs the method as described in any one of claims 1-13, or performs the method as described in any one of claims 14-25.

28. A computer-readable storage medium, characterized in that, Includes computer instructions; When the computer instructions are executed on a terminal device, the terminal device causes the terminal device to perform the method as described in any one of claims 1-13; Alternatively, when the computer instructions are executed on the network device, the network device causes the network device to perform the method as described in any one of claims 14-25.

Images