A method for determining beam sets and related equipment

Abstract

The present application provides a method for determining a beam set and related equipment, which relate to the field of wireless communication technology. The method includes: receiving a first measurement report sent by a terminal device, the first measurement report including a beam measurement result of a reference signal sent in a beam direction of a first beam subset, the first beam subset is a subset of a beam set, and the beam set includes all possible beam directions; taking the beam measurement result of the first beam subset as input, and determining the beam measurement result of the beam set through a target self-supervisory model; based on the beam measurement result of the beam set and the second beam subset, determining a target beam subset, the second beam subset including the optimal beam direction predicted by the AI / ML model, and the target beam subset is used to monitor the performance of the AI / ML model. By reasonably configuring the target beam subset, the effectiveness of the AI / ML model performance detection can be guaranteed while reducing resource overhead.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of wireless communication technologies, and in particular to a method for determining a beam set and related devices. Background Art

[0002] In wireless communication systems, artificial intelligence (AI) technology can be applied to beam management. For example, AI / machine learning (ML) models can be used to determine the optimal beam direction so that network devices can transmit data along the optimal beam direction.

[0003] When using AI / ML models for beam management, performance monitoring is often required to determine their effectiveness. Therefore, it is necessary to properly configure the beam set used to monitor AI / ML model performance to ensure accurate performance monitoring while minimizing resource overhead. Summary of the Invention

[0004] This application provides a method and related equipment for determining a beam set. By reasonably configuring the beam set for detecting AI / ML model performance, the effectiveness of AI / ML model performance detection can be ensured while reducing resource overhead.

[0005] In a first aspect, a method for determining beam sets is provided. This method can be performed, for example, by a network device, or by a component configured within the network device (such as a circuit, chip, or chip system), or by a logic module or software capable of implementing all or part of the network device's functions. This application is not limited to this method. The following description uses a network device as an example.

[0006] The method includes:

[0007] A first measurement report sent by a receiving terminal device is included, where the first measurement report includes a beam measurement result of a reference signal sent in a beam direction of a first beam subset, where the first beam subset is a subset of the beam set, and the beam set includes all possible beam directions; the beam measurement result of the first beam subset is used as input, and the beam measurement result of the beam set is determined through a target self-supervisory model; a target beam subset is determined based on the beam measurement result of the beam set and the second beam subset, where the second beam subset includes the optimal beam direction predicted by the AI / ML model, and the target beam subset is used to monitor the performance of the AI / ML model.

[0008] Exemplarily, the first beam subset is setB in the embodiment, the second beam subset is the Top-K beam set in the embodiment, the beam set is setA in the embodiment, and the target beam subset is setM in the embodiment.

[0009] The number of optimal beam directions included in the second beam subset may be one or more. It can be understood that the second beam subset and the target beam subset are both subsets of the beam set.

[0010] The target self-supervised model can reconstruct the beam measurement results of the beam set based on an arbitrary first beam subset.

[0011] In this way, by reconstructing the beam measurement results of each beam direction in the beam set, the network device determines the target beam subset for detecting the performance of the AI / ML model based on the beam measurement results of each beam direction in the reconstructed beam set and the beam measurement results of the first beam subset. In this way, the terminal device is prevented from measuring all possible beam directions, which can reduce resource overhead. In addition, based on the beam measurement results of each beam direction in the reconstructed beam set, the target beam subset is determined in combination with the optimal beam direction predicted by the AI / ML model. After the terminal device measures the beam directions included in the target beam subset, the measured value of the optimal beam direction predicted by the AI / ML model is compared with the measured value of the Top-K beam direction. It can be determined whether the optimal beam direction predicted by the AI / ML model is accurate, thereby detecting whether the AI / ML model prediction is effective, thereby improving the effectiveness of model performance monitoring.

[0012] As an example of the present application, based on the beam measurement results of the beam set and the second beam subset, a target beam subset is determined, including: from the beam set, sorting the beam measurement results from large to small and then selecting the first value of beam directions, the union of the first value of beam directions and the beam directions included in the second beam subset is less than or equal to the second value, and the second value is the number of beam directions that the terminal device can monitor at a single time; and determining the subset consisting of the selected first value of beam directions and the beam directions included in the second beam subset as the target beam subset.

[0013] Based on the beam measurement results of each beam direction in the reconstructed beam set and combined with the optimal beam direction predicted by the AI / ML model, the target beam subset is determined, which can accurately detect whether the AI / ML model prediction is valid.

[0014] As an example of the present application, the first measurement report further includes a beam identifier of a beam direction in the second beam subset, so that the network device can determine the second beam subset according to the beam identifier.

[0015] As an example of the present application, a network device receives a first measurement capability report, the first measurement capability report including a second value. The first measurement capability report is used to indicate the beam measurement capability of the terminal device. The second value is carried in the first measurement capability report, so that the network device can determine how many beam directions to select from the beam set as part of the target beam subset based on the second value.

[0016] As an example of the present application, the method also includes: sending first measurement configuration information to the terminal device, the first measurement configuration information includes a first reporting quantity indication parameter, and the first reporting quantity indication parameter is used to indicate the reporting of the beam measurement results of the first beam subset and the beam identifier of the second beam subset.

[0017] As an example, the first reporting quantity indication parameter is a first enumeration value, such as CRI-RSRP-TopK.

[0018] As an example, the first measurement configuration information further includes a second reporting quantity indication parameter, where the second reporting quantity indication parameter is used to indicate the number of beam directions included in the second beam subset to be reported.

[0019] Exemplarily, the second reporting quantity indication parameter is numberOfTopKBeams = K.

[0020] As an example, the method also includes: sending second measurement configuration information to the terminal device, the second measurement configuration information is used to configure the reference signal of the beam direction included in the target beam subset; sending MAC CE to the terminal device, MAC CE is used to activate the TCI state corresponding to the beam direction included in the target beam subset; sending DCI to the terminal device multiple times, the DCI carries the index of the currently selected TCI state; after each transmission, transmit the reference signal in the beam direction corresponding to the currently selected TCI state.

[0021] In this way, the terminal device can quickly switch between the beam directions included in the target beam subset.

[0022] As an example, the method also includes: receiving a second measurement report reported by multiple terminal devices, the second measurement report including the beam measurement results of the corresponding terminal devices for the reference signal of the beam set; determining training data based on the beam measurement results reported by the multiple terminal devices; and obtaining a target self-supervised model by training an incompletely trained self-supervised model based on the training data.

[0023] In this way, the network device trains the self-supervised model based on the beam measurement results reported by multiple terminal devices to obtain a target self-supervised model. The target self-supervised model can reconstruct the beam measurement results of all possible beam directions, and then facilitate the reasonable determination of the monitoring set setM based on the reconstructed beam measurement results of all possible beam directions to ensure the accuracy of model performance monitoring.

[0024] As an example, based on the beam measurement results reported by multiple terminal devices, the specific implementation of determining the training data may include: selecting at least one group of fourth-value beam measurement results from the beam measurement results reported by each terminal device to obtain multiple groups of fourth-value beam measurement results; using the multiple groups of fourth-value beam measurement results as the input of the encoder in the self-supervised model, encoding them through the encoder to obtain the encoding result; using the encoding result and the mask mark as the input of the decoder in the self-supervised model, decoding them through the decoder to obtain the decoding result, where the mask mark is obtained by masking the beam measurement results other than the fourth-value beam measurement results in the beam measurement results reported by each terminal device; training the self-supervised model based on the decoding result and the true value to obtain the target self-supervised model, where the true value is the vector obtained after converting the beam measurement results reported by multiple terminal devices.

[0025] In this way, by training the target self-supervisory model, the target self-supervisory model can reconstruct the beam measurement results of the beam set based on any first beam subset, thereby avoiding the need for the terminal device to measure the beam measurement results of each beam direction in the beam set, which can reduce resource overhead.

[0026] In a second aspect, a method for determining beam sets is provided. This method can be performed, for example, by a terminal device, or by a component configured in the terminal device (such as a circuit, chip, or chip system), or by a logic module or software that implements all or part of the terminal device's functions. This application is not limited to this method. The following description uses a terminal device as an example.

[0027] The method includes:

[0028] A first measurement report is sent to the network device. The first measurement report is used by the network device to determine the target beam subset. The first measurement report includes the beam measurement result of the reference signal sent in the beam direction of the first beam subset and the beam identifier of the second beam subset. The second beam subset includes the optimal beam direction predicted by the AI / ML model. The target beam subset is used to monitor the performance of the AI / ML model. The first beam subset, the second beam subset and the target beam subset are all subsets of the beam set, and the beam set contains all possible beam directions.

[0029] In this way, by reporting the first measurement report, the network device reconstructs the beam measurement results of each beam direction in the beam set through the target self-supervisory model based on the beam measurement results of the beam direction of the first beam subset in the first measurement report. The network device determines the target beam subset for detecting the performance of the AI / ML model based on the beam measurement results of each beam direction in the reconstructed beam set and the second beam subset. In this way, the terminal device is prevented from measuring all possible beam directions, which can reduce resource overhead. In addition, based on the beam measurement results of each beam direction in the reconstructed beam set, the target beam subset is determined in combination with the optimal beam direction predicted by the AI / ML model. After the terminal device measures the beam directions included in the target beam subset, the measurement value of the optimal beam direction predicted by the AI / ML model is compared with the measurement value of the Top-K beam direction. It can be determined whether the optimal beam direction predicted by the AI / ML model is accurate, so that it can be detected whether the AI / ML model prediction is effective, thereby improving the effectiveness of model performance monitoring.

[0030] As an example of the present application, the first measurement report further includes a beam identifier of a beam direction in the second beam subset.

[0031] In this way, the network device can determine the optimal beam direction based on the beam identifier.

[0032] As an example of the present application, the method further includes: sending a first measurement capability report to the network device, the first measurement capability report including a second value, where the second value is the number of beam directions that the terminal device can monitor at a single time. In this way, the network device can determine how many beam directions to select from the beam set as part of the target beam subset based on the second value.

[0033] As an example of the present application, the method further includes: receiving first measurement configuration information sent by a network device, the first measurement configuration information including a first reporting quantity indication parameter, the first reporting quantity indication parameter being used to indicate reporting of beam measurement results of a first beam subset and beam identifiers of a second beam subset. As an example, the first reporting quantity indication parameter is a first enumeration value. For example, the first enumeration value is CRI-RSRP-TopK.

[0034] As an example of the present application, the first measurement configuration information further includes a second reporting quantity indication parameter, where the second reporting quantity indication parameter is used to indicate the number of beam directions included in the second beam subset to be reported. Exemplarily, the second reporting quantity indication parameter is numberOfTopKBeams = K.

[0035] In a third aspect, a communication device is provided, which includes a processing module and a transceiver module, and the communication device is used to execute the program or instructions of the method described in the first aspect above, or to execute the program or instructions of the method described in the second aspect above.

[0036] In a fourth aspect, a communication device is provided, comprising a processor. The processor is coupled to a memory and can be configured to execute instructions or data in the memory to implement the method in any possible implementation of the first aspect or the method in any possible implementation of the second aspect. Optionally, the communication device further comprises a memory.

[0037] Optionally, there are one or more processors and one or more memories.

[0038] In a fifth aspect, a computer program product is provided, comprising: a computer program (also referred to as code, or instructions), which, when executed, enables a computer to execute the method in any possible implementation of the first aspect, or to execute the method in any possible implementation of the second aspect.

[0039] In a sixth aspect, a computer-readable storage medium is provided, which stores a computer program (also referred to as code, or instructions). When the computer-readable storage medium is run on a computer, the computer executes the method in any possible implementation of the first aspect or the method in any possible implementation of the second aspect.

[0040] In a seventh aspect, embodiments of the present application provide a chip system comprising one or more processors configured to retrieve and execute instructions stored in a memory, thereby executing the method of each of the above aspects or any possible implementation of each aspect. The chip system may be composed of a chip or may include a chip and other discrete devices.

[0041] Among them, the chip system may include an input circuit or interface for sending information or data, and an output circuit or interface for receiving information or data.

[0042] In an eighth aspect, a communication system is provided, comprising the aforementioned terminal device and network device. Optionally, the communication system may further comprise other devices communicating with the terminal device and / or the network device. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 1 is a schematic diagram of a framework of a monitoring set determination method based on a self-supervisory model according to an exemplary embodiment;

[0044] Figure 2is a schematic diagram of a communication system according to an exemplary embodiment;

[0045] Figure 3 is a schematic diagram of a self-supervised model training method according to an exemplary embodiment;

[0046] Figure 4 is a schematic diagram showing communication between a network device and a terminal device according to an exemplary embodiment;

[0047] Figure 5 is a schematic diagram showing a process flow of a self-supervisory model processing training data according to an exemplary embodiment;

[0048] Figure 6 is a flow chart illustrating a method for determining a target beam subset through a target self-supervisory model according to an exemplary embodiment;

[0049] Figure 7 is a flow chart illustrating a method for determining a target beam subset through a target self-supervisory model according to another exemplary embodiment;

[0050] Figure 8 It is a schematic block diagram of a communication device according to an exemplary embodiment. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0052] It should be understood that the “multiple” mentioned in this application refers to two or more. In the description of this application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in order to facilitate the clear description of the technical solution of this application, words such as “first” and “second” are used to distinguish between identical or similar items with basically the same functions and effects. Those skilled in the art can understand that words such as “first” and “second” do not limit the quantity and execution order, and words such as “first” and “second” do not necessarily limit them to be different.

[0053] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0054] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD), Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication system, future fifth generation (5G) system or new radio (NR), etc.

[0055] The terminal device in the embodiments of the present application may refer to user equipment (UE), station, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device. The terminal device may also be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a large screen, an in-vehicle device, a wearable device, a terminal device in a 5G network or a terminal device in a future-evolved public land mobile network (PLMN), etc., and the embodiments of the present application are not limited to this.

[0056] The network device in the embodiments of the present application may be a device used for terminal device communication. For example, the network device is a radio access network (RAN) node (or device) that connects the terminal device to a wireless network, which may also be referred to as a base station. Exemplarily, the network device may be an evolved NodeB (eNodeB), a transmission reception point (TRP), a next-generation NodeB (gNB) in a 5G mobile communication system, a base station in a future mobile communication system, or an access point (AP) in a WiFi system, a wireless controller in a cloud radio access network (CRAN) scenario, a relay station, an access point, a vehicle-mounted device, a wearable device, or a network device in other communication systems that evolve in the future.

[0057] In an embodiment of the present application, a terminal device or network device includes a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system layer. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory (also known as main memory). The operating system can be any one or more computer operating systems that implement business processing through processes, such as the Linux operating system, the Unix operating system, the Android operating system, the iOS operating system, or the Windows operating system. The application layer includes applications such as browsers, address books, word processing software, and instant messaging software. In addition, the embodiment of the present application does not specifically limit the specific structure of the execution subject of the method provided in the embodiment of the present application. As long as it is possible to communicate according to the method provided in the embodiment of the present application by running a program that records the code of the method provided in the embodiment of the present application, it is sufficient.

[0058] In addition, various aspects or features of the present application can be implemented as methods, apparatus, or articles of manufacture using standard programming and / or engineering techniques. The term "article of manufacture" as used herein encompasses a computer program accessible from any computer-readable device, carrier, or medium. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes), optical disks (e.g., compact discs (CDs), digital versatile discs (DVDs), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memories (EPROMs), cards, sticks, or key drives). Furthermore, the various storage media described herein may represent one or more devices and / or other machine-readable media for storing information. The term "machine-readable medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0059] In order to facilitate understanding of the embodiments of the present application, the relevant concepts involved in the embodiments of the present application are first explained.

[0060] 1. Beamforming: This technology forms a directional beam by adjusting the phase and amplitude of the antenna array, thereby enhancing the signal in a specific direction and suppressing it in other directions, thereby achieving directional transmission and reception.

[0061] Based on beamforming, dynamic management and optimization of the formed beams ensures signal transmission along the optimal path, minimizing interference and signal attenuation. During beam management, network devices (such as base stations) periodically transmit reference signals in different beam directions. Terminal devices measure the signal quality of each reference signal sent by the network device, such as the reference signal received power (RSRP) or signal-to-noise ratio (SNR). Based on the beam measurement results, the network device dynamically adjusts the beam direction based on the terminal device's feedback.

[0062] 2. Channel State Information-Reference Signal (CSI-RS): This is a reference signal used to measure channel state information (CSI). In beam management, terminal devices can use CSI-RS to measure CSI, such as RSRP, and provide feedback to network devices. This feedback allows the network devices to optimize beam direction.

[0063] 3. RSRP: It is a key parameter used to measure wireless signal quality in LTE and 5G networks. The higher the RSRP value, the closer the distance between the terminal device and the network device, the stronger the signal, and the better the communication quality.

[0064] 4. Quasi co-location (QCL): Its main function is to allow a terminal device to infer the channel characteristics of a known reference signal from another reference signal. If two reference signals have a QCL relationship, it means that they have similar propagation characteristics in space. For example, during beam management, the network equipment configures the QCL relationship for the terminal device. In this way, the terminal device can use the beam direction and QCL relationship of the known reference signal to receive the other reference signal, thereby reducing the complexity of beam search.

[0065] 5. Transmission Configuration Indication (TCI) State: A TCI state corresponds to a beam direction and contains parameters related to that beam direction, such as the reference signal configuration, beam direction, and QCL relationship. Through the TCI state, the network device can tell the terminal device how to receive signals in different beam directions. The network device can configure multiple TCI states for the terminal device and activate these states simultaneously through the media access control element (MAC CE). This allows the terminal device to obtain the configuration information for multiple beam directions, including beam directions, reference signals, and QCL relationships, in advance. This means that the terminal device already knows multiple possible beam paths and does not need to re-request this information during each handover. The network device can indicate a specific TCI state through downlink control information (DCI). Since the terminal device has already obtained the configuration information for multiple beam directions in advance, it can quickly schedule one of the multiple activated TCI states based on the TCI state indicated by the DCI, thereby achieving multi-beam parallelization or rapid handover.

[0066] 6. MAC CE: It is a set of control information that can include multiple control information, such as activation or deactivation of TCI status. It is sent by the network device to the terminal device to instruct the terminal device to perform specific operations, such as beam switching.

[0067] 7. Radio Resource Control Signaling (RRC): RRC is a key mechanism for controlling and managing radio resources in wireless communication systems. It facilitates interaction between terminal devices and network equipment, establishing, maintaining, and releasing radio resources, and configuring terminal device behavior and parameters.

[0068] 8. AI / ML model: A system built based on data and algorithms to perform specific tasks such as prediction, classification, and recognition. It can make decisions automatically by learning patterns and regularities in data.

[0069] 9. Self-supervised model: It mainly includes an encoder and a decoder. The encoder encodes the input data into a high-dimensional feature representation (usually called an embedding or feature vector). This feature representation can capture the intrinsic structure and pattern of the data; the decoder decodes the low-dimensional feature representation into a form close to the original input data for reconstructing the input data. Through the reconstruction process, the self-supervised model can learn the complete structure and pattern of the data.

[0070] In wireless communications (such as the 5G air interface), AI technology can be applied to beam management. AI / ML models can be deployed on either the network or the terminal device side to determine the optimal beam direction for data transmission. For example, using the AI / ML model deployed on the terminal device side, during beam management, the network device (such as a base station) configures a beam subset for the terminal device and sends reference signals for different beam directions within the subset. The beam subset includes a small number of different beam directions. The terminal device then measures the reference signals, such as their RSRP, to obtain beam measurement results. The terminal device then uses the beam measurement results as input and uses the AI / ML model to predict the optimal beam direction among all possible beam directions supported by the network device. The optimal beam direction, which may be one or multiple, is then fed back to the network device. Based on the feedback from the terminal device, the network device selects the optimal beam direction for data transmission. In this way, the network device only needs to send a small number of reference signals to predict the optimal beam direction, avoiding the need for the network device to send reference signals in each beam direction of all possible beam directions. This can greatly reduce the number of beams that the terminal device needs to test, does not rely entirely on the measurement and feedback of the terminal device, takes less time, and can reduce resource consumption.

[0071] In order to adapt to the complex and changing dynamic antenna environment, the performance of the AI / ML model can be tested regularly. In the performance test process of beam management, the network device is required to transmit reference signals of some beam directions (which can be defined as the monitoring set setM) to the terminal device. The terminal device measures the reference signals of these beam directions and determines the optimal beam direction based on the beam measurement results. For example, one or more beam directions with the highest ranking are selected from the monitoring set setM in descending order of RSRP as the optimal beam direction. Afterwards, the terminal device can determine whether the AI / ML model is effective based on the RSRP value of the optimal beam direction selected from the monitoring set setM and the RSRP value of the optimal beam direction predicted by the AI / ML model. As an example, the terminal device can compare the maximum RSRP value of the optimal beam direction predicted by the AI / ML model with the maximum RSRP value of the optimal beam direction determined based on the beam measurement results. If the maximum RSRP value of the optimal beam direction predicted by the AI / ML model is equal to the maximum RSRP value of the optimal beam direction determined based on the beam measurement results, or if the maximum RSRP value of the optimal beam direction predicted by the AI / ML model is less than the maximum RSRP value of the optimal beam direction determined based on the beam measurement results but the difference between the two does not exceed a certain threshold, then it can be determined that the AI / ML model prediction is valid; otherwise, it is determined that the AI / ML model prediction is inaccurate, that is, the AI / ML model prediction is invalid. In this way, after multiple tests, it can be determined whether the AI / ML model is valid. If the AI / ML model is invalid, it can be returned to the traditional non-AI beam management mode or switched to another AI model.

[0072] In some embodiments, the network device sets all possible beam directions supported by the network device as a monitoring set setM. Although this can accurately detect the performance of the AI / ML model, the terminal device is required to measure the reference signals of all beam directions, resulting in excessive reference signal resource overhead. In other embodiments, the network device randomly selects some beam directions from all possible beam directions supported as the monitoring set setM. Although this can reduce the reference signal resource overhead to a certain extent, the beam directions in the randomly selected monitoring set setM may not fully cover the actual optimal beam direction among all possible beam directions, which will affect the accuracy of performance detection.

[0073] To this end, an embodiment of the present application provides a method for determining a monitoring set setM. The method trains a self-supervisory model in a network device and deploys the trained self-supervisory model in the network device, so that the network device reconstructs the RSRP of all supported beam directions through the self-supervisory model, and configures the detection set setM accordingly, thereby ensuring the accuracy of AI / ML model performance detection while reducing resource overhead.

[0074] For example, see Figure 1 , Figure 1 This diagram provides an overview of a method for determining a monitoring set set M according to an exemplary embodiment. The method primarily includes two parts: a self-supervised model training method and a self-supervised model deployment method. As an example, the self-supervised model training method is implemented on a network device. The network device can obtain beam measurement results for all possible beam directions from each of multiple terminal devices within the network, and use masking techniques to generate training data for a self-supervised model. The self-supervised model is then trained based on this training data. The trained self-supervised model (referred to as a target self-supervised model) is then deployed on the network device. Therefore, when model performance testing is required, the network device can use the AI / ML model input as the input for the target self-supervised model. The target self-supervised model reconstructs the RSRP for each of all possible beam directions and configures the monitoring set set M accordingly. This avoids the need for terminal devices to measure reference signals for each of all possible beam directions during model performance testing. Furthermore, since the RSRP for each of all possible beam directions is reconstructed, resource overhead is reduced while ensuring the accuracy of AI / ML model performance testing.

[0075] Next, the self-supervised model training method and the self-supervised model deployment method will be explained respectively with reference to the accompanying drawings.

[0076] Before this, a brief introduction to the communication system involved in the embodiment of the present application is given. Figure 2 The self-supervisory model training method and the self-supervisory model deployment method involved in the embodiments of the present application can be applied to Figure 2 In the communication system shown in FIG. Figure 2 As shown, the communication system may include at least one wireless access network device 110 and at least one terminal device (such as Figure 2 ). The terminal device is wirelessly connected to a radio access network device 110. Radio access network device 110 may be the aforementioned network device, such as a gNB. At least one terminal device may send uplink data or information to radio access network device 110, and radio access network device 110 may also send downlink data or information to at least one terminal device.

[0077] It should be understood that Figure 2 This is just a schematic diagram. The communication system may also include other network equipment (such as core network, base station, etc.) and / or terminal equipment ( Figure 2 (not shown), the embodiments of the present application do not limit the number and type of network devices and terminal devices included in the communication system.

[0078] Based on the above embodiments, see Figure 3 , Figure 3 This is a process of a self-supervised model training method according to an exemplary embodiment. As an example, the method is applied to Figure 2 In the communication system shown, the method is implemented by interaction between the terminal device and the network device, and may include some or all of the following contents:

[0079] S301: The terminal device sends a second measurement capability report to the network device.

[0080] The second measurement capability report is used to indicate the data collection capability of the terminal device.

[0081] Exemplarily, the second measurement capability report may include parameters such as a beam measurement frequency and a beam measurement time slot. The beam measurement frequency indicates the frequency at which the terminal device measures the reference signal. The beam measurement time slot indicates the time slot in which the terminal device measures the reference signal.

[0082] Optionally, the second measurement capability report may also include a beam set, where the beam set includes beam identifiers of all possible beam directions. For example, the beam set is recorded as setA, where setA includes CRI1, CRI2, CR3, ..., CRIN, that is, it includes N beam directions, where N is a positive integer. Carrying the beam set in the second measurement capability report is used to indicate that the terminal device is capable of measuring reference signals in all possible beam directions. The beam identifier can be used to identify a beam direction. For example, the beam identifier can be represented by a channel-rate indicator (CRI).

[0083] As an example, all terminal devices in the network covered by the network device send a second measurement capability report to the network device when initially accessing the network to report their respective data collection capabilities. Figure 4 The network covered by the network device includes seven terminal devices: UE1, UE2, UE3, UE4, UE5, UE6, and UE7. Upon initial access, these seven terminal devices report their data collection capabilities to the network device. The following explanations mostly use the interaction between the network device and one of the terminal devices as an example.

[0084] S302: The network device sends third measurement configuration information to the terminal device.

[0085] The third measurement configuration information is used to configure the reference signal of the beam direction included in the beam set set A. Exemplarily, the third measurement configuration information includes a beam identifier, as well as time domain information, frequency domain information, QCL relationship, beam scanning mode, measurement frequency, etc. of the reference signal.

[0086] The time domain information and the frequency domain information are used to indicate the time / frequency domain position of the reference signal.

[0087] The beam scanning mode is used to indicate a beam scanning method, including, for example, an omnidirectional scanning mode or a directional scanning mode.

[0088] The measurement frequency indicates the frequency of the measurement reference signal.

[0089] After receiving the second measurement capability report reported by each terminal device, the network device provides the corresponding terminal device with data collection configuration according to the second measurement capability report. As an example, the network device can send third measurement configuration information to the terminal device via RRC signaling, thereby providing the terminal device with data collection configuration.

[0090] S303: The network device transmits a reference signal to the terminal device in the beam direction included in the beam set setA.

[0091] After the network device provides the terminal device with the data collection configuration, it transmits a reference signal in each beam direction included in the beam set setA, so that the terminal device can measure the signal quality of the reference signal in each beam direction included in the beam set setA (the following uses RSRP measurement as an example to illustrate).

[0092] S304: The terminal device measures the reference signal in the beam direction included in the beam set setA.

[0093] The terminal device can measure the reference signal in each beam direction included in the beam set setA according to the third measurement configuration information configured by the network device, such as measuring the RSRP of the reference signal in each beam direction included in the beam set setA, thereby determining the beam measurement result.

[0094] As an example, the beam measurement result includes a measurement value of a reference signal in each beam direction in the beam set setA and a beam identifier. Exemplarily, the measurement value is RSRP.

[0095] S305: The terminal device sends a second measurement report (including beam measurement results) to the network device.

[0096] Specifically, the second measurement report includes the beam measurement result of the corresponding terminal device on the reference signal in the beam direction included in the beam set setA.

[0097] For different terminal devices in the network covered by the network device, due to the different positions of the terminal devices, the RSRP measured by different terminal devices for the reference signal in the same beam direction may be different, that is, the beam measurement results of the beam set setA reported by different terminal devices are different. In order to facilitate distinction, the beam measurement results reported by different terminal devices can be recorded as , contains N elements, for example, see Figure 5 in , There are 35 elements in it. The numbers in the circles indicate the elements in this An element corresponds to the beam measurement result of a beam direction, which can be recorded as , Including RSRP and beam identification, such as ,in For RSRP, is the beam identifier, and i is an integer.

[0098] For example, L terminal devices report the second measurement report to the network device respectively. In the second measurement reports reported by these L terminal devices, the beam measurement results of the beam set setA are respectively , , ,..., .

[0099] Wherein L is an integer greater than 1. For example, L is the number of all terminal devices in the network covered by the network device, or L can also be a preset value. j is an integer greater than or equal to 1 and less than L.

[0100] S306: The network device obtains a target self-supervised model by training the untrained self-supervised model based on the beam measurement results reported by the multiple terminal devices.

[0101] As an example, the network device may train an untrained self-supervised model based on the beam measurement results reported by multiple terminal devices to obtain a target self-supervised model. The specific implementation may include the following steps (1)-(3):

[0102] (1) The network device receives the data reported by each of the L terminal devices. Selecting a subset of beams .

[0103] Network devices can be reported from terminal devices The beam measurement results of the randomly selected beam direction are used to form setB, where setB includes multiple For example, Randomly select B elements from , according to different random selection methods, it can be based on Get multiple ;from Randomly select B elements from , according to different random selection methods, it can be based on Get multiple ;from Randomly select B elements from , similarly, according to the different random selection methods, Get multiple ; And so on, in this way, from each According to different random selection methods, each time B elements are selected, multiple . In addition, in each random selection, The remaining unselected elements in are masked, as .

[0104] For example, see Figure 5 ② in a random selection, It includes 7 elements, that is, B is 7, and the corresponding serial numbers are 1, 7, 12, 19, 25, 26, and 34. Contains 28 elements.

[0105] and It can be expressed by the following formula (1) and formula (2) respectively:

[0106] (1)

[0107] (2)

[0108] It is from The beam measurement results of B randomly selected beam directions are composed of . Indicates from Randomly select a subset from express Except The subset of beam measurement results for beam directions other than There are NB elements in it.

[0109] As an example, a network device may The beam measurement results of each beam direction in the mask processing are performed. For example, the beam measurement results of each beam direction can be initialized to a specified character, and the specified character represents an invalid value, such as the specified character is "F" or "0", so as to obtain The coding mark, The corresponding mask mark can be written as .

[0110] According to the previous records, The beam measurement result of the i-th beam direction includes the beam identifier and RSRP value. , for example, can be expressed as shown in formula (3):

[0111] (3)

[0112] in, , , represents the set of real numbers, Represents a set of integers.

[0113] (2) Network equipment is based on multiple , build training data.

[0114] As an example, a network device may The beam measurement results for each beam direction are included to construct a B*2 matrix, which can be called a sample vector, as shown in formula (4). In this way, multiple sample vectors can be obtained, and the network device uses the constructed multiple sample vectors as training data.

[0115] (4)

[0116] in, is the sample vector, .

[0117] (3) The network device inputs the training data into the untrained self-supervised model for training.

[0118] As mentioned above, the self-supervised model mainly includes an encoder and a decoder. The network device uses the above training data as the input of the encoder, and the encoder extracts each sample vector based on the Transformer model. and output the corresponding feature representation For example, the feature representation output by the encoder is As shown in formula (5):

[0119] (5)

[0120] Among them, H is the dimension of feature representation, which represents the features of the unmasked beam set; Indicates encoding.

[0121] The network device represents the feature output of the encoder and the corresponding The mask mark of is used to perform feature splicing to obtain multiple spliced ​​data. For example, the network device can use formula (6) to represent the feature output of the encoder and the corresponding The mask mark of is used for feature splicing:

[0122] (6)

[0123] in, is the spliced ​​data obtained after feature splicing, N is The number of beam measurements included.

[0124] The network device uses the multiple spliced ​​data obtained after splicing as the input of the decoder of the self-supervised model, for example, see Figure 5 In ③, the black circle represents the mask mark, and the white circle represents the feature representation. The network device concatenates the feature representation with the corresponding mask mark and inputs it into the decoder. The decoder decodes each concatenated data input and outputs multiple sets of prediction values. Each set of prediction values ​​is as follows: Figure 5 As shown in ④, each set of prediction values ​​can be understood as an estimated value of the beam measurement results of the beam directions included in the beam set setA. For example, the prediction value output by the decoder is shown in formula (7):

[0125] (7)

[0126] in, is the predicted value, Indicates decoding.

[0127] As an example, the network device uses the data reported by the terminal device as The beam measurement results are used as the true values ​​for model training. For example, the true values ​​are shown in formula (8):

[0128] (8)

[0129] During the training process, the mean square error (MSE) can be selected as the loss function. As shown in formula (9), the loss value is calculated based on the true value and the predicted value through the loss function.

[0130] (9)

[0131] in, is the loss value.

[0132] In this way, after multiple training sessions, when the training end conditions are determined to be met based on multiple loss values, such as when the average of multiple loss values ​​is less than a preset threshold, or when the number of training sessions reaches a preset number, the network device ends the training, thereby obtaining a self-supervised model that has completed training, namely, the target self-supervised model.

[0133] It should be noted that the embodiments of this application are described using an example in which a network device determines training data. In another example, the network device may determine training data through other devices after collecting beam measurement results reported by multiple terminal devices. For example, the network device may send the results to a server, which may determine the training data. This embodiment of the application is not limited to this.

[0134] In an embodiment of the present application, the terminal device reports the beam measurement results of all possible beam directions to the network device. The network device trains the self-supervisory model based on the beam measurement results reported by multiple terminal devices to obtain a target self-supervisory model. The target self-supervisory model can reconstruct the beam measurement results of all possible beam directions, thereby facilitating the reasonable determination of the monitoring set setM based on the reconstructed beam measurement results of all possible beam directions to ensure the accuracy of model performance monitoring. In addition, since the terminal device only needs to report the beam measurement results of all possible beam directions once, the network device can obtain the target self-supervisory model through training and subsequently use the target self-supervisory model to predict the beam measurement results of all possible beam directions. That is, the terminal device does not need to measure the reference signals of all possible beam directions each time the model is monitored, so resource overhead can be reduced.

[0135] Based on the above embodiment, the self-supervisory model deployment method provided by the embodiment of the present application is introduced below. This method can also be applied to Figure 2 or Figure 4 In the communication system shown in FIG, the terminal device and the network device interact to realize the communication. This application embodiment takes the AI / ML model deployed in the terminal device and the target self-supervisory model deployed on the network device side as an example for explanation. Figure 6 , the method may include some or all of the following:

[0136] S601: The terminal device sends a first measurement capability report to the network device.

[0137] The first measurement capability report is used to indicate the data collection capability of the terminal device for the beam subset.

[0138] As an example, the first measurement capability report includes a second value, which is the number of beam directions that the terminal device can monitor at a single time. The terminal device reports the second value, which enables the network device to determine how many beam directions the monitoring set setM can include based on the second value, for example, it can include a maximum of the second value of beam directions.

[0139] Optionally, the first measurement capability report may further include a fourth value, monitoring function indication information, a reporting frequency, etc.

[0140] The fourth value is used to indicate the number of beam directions included in the first beam subset, where the first beam subset can be determined by the network device and used to determine the optimal beam direction.

[0141] The monitoring function indication information is used to indicate the indicators that the terminal device can monitor, for example, the monitoring function indication information is RSRP. The reporting frequency is used to indicate the frequency of reporting CSI reports to the network device. The CSI report is used to report the beam measurement results of the first beam subset and the optimal beam direction predicted by the AI / ML model.

[0142] As an example, the terminal device may periodically send the first measurement capability report to the network device; as another example, the terminal device may also send the first measurement capability report to the network device according to actual data reception requirements.

[0143] S602: The network device sends first measurement configuration information to the terminal device through RRC signaling.

[0144] During implementation, the network device may send the first measurement configuration information to the terminal device according to the first measurement capability report.

[0145] The first measurement configuration information is used to configure a reference signal for a beam direction included in the first beam subset, and includes configuration information related to the first beam subset. Exemplarily, the first measurement configuration information includes a beam identifier for the beam direction included in the first beam subset, as well as time domain information, frequency domain information, QCL relationship, beam scanning mode, measurement frequency, and other information of the reference signal.

[0146] As an example, the first measurement configuration information also includes a first reporting quantity indication parameter, where the first reporting quantity indication parameter is used to indicate reporting of beam measurement results of a first beam subset and beam identifiers of a second beam subset, where the second beam subset includes an optimal beam direction determined by an AI / ML model. Exemplarily, the first reporting quantity indication parameter is a first enumeration value.

[0147] Since the terminal device is required to report the beam measurement results of the first beam subset and the optimal beam direction predicted by the AI / ML model (i.e., the second beam subset) in the future, the network device can add a first reporting quantity indication parameter in the RRC signaling to instruct the terminal device to report the beam measurement results of the first beam subset and the optimal beam direction predicted by the AI / ML model through the added first reporting quantity indication parameter.

[0148] Optionally, the first measurement configuration information also includes a second reporting quantity indication parameter, which is used to indicate the number of beam directions included in the second beam subset. That is, the network device can also add a second reporting quantity indication parameter in the RRC signaling to instruct the terminal device to report the number of optimal beam directions predicted by the AI / ML model.

[0149] For example, the relevant content in the RRC signaling is as follows:

[0150] CSI-ReportConfig ::= {

[0151] reportConfigId = 1,

[0152] …

[0153] reportQuantity = CRI-RSRP-TopK, / / Report the CRI-RSRP of the first beam subset and the predicted Top-K beam direction (multi-beam scenario)

[0154] groupBasedBeamReporting = TRUE, / / Enable multi-beam reporting

[0155] numberOfBeams = B, / / Assume that the first beam subset contains B beam directions

[0156] …

[0157] numberOfTopKBeams = K, / / Report the Top-K optimal beam direction

[0158] …}

[0159] Among them, reportQuantity is a new variable in RRC signaling, that is, the first report quantity indication parameter, and its enumeration type value is CRI-RSRP-TopK, which indicates that the terminal device reports the RSRP and beam identifier of the first beam subset, and reports the beam identifier of the optimal beam direction (i.e., Top-K) predicted by the AI / ML model.

[0160] numberOfTopKBeams is another newly added variable, namely the second reporting quantity indication parameter, which is used to indicate the number of optimal beam directions predicted by the AI / ML model reported by the terminal device.

[0161] S603: The network device sends a reference signal to the terminal device in the beam direction included in the first beam subset.

[0162] After the network device configures the reference signal for the terminal device, it can send the reference signal in each beam direction included in the first beam subset according to the first measurement configuration information, so that the terminal device measures the reference signal in each beam direction included in the first beam subset.

[0163] S604: The terminal device measures a reference signal transmitted by the network device in a beam direction included in the first beam subset.

[0164] As an example, the terminal device measures the reference signal in each beam direction included in the first beam subset according to the first measurement configuration information, and obtains the RSRP of the reference signal in each beam direction included in the first beam subset. The terminal device uses the measured RSRP and beam identifier of each beam direction as the beam measurement result of the first beam subset.

[0165] S605: The terminal device predicts the optimal beam direction through the AI / ML model based on the beam measurement results of the first beam subset.

[0166] The terminal device can use the beam measurement results of the first beam subset as input and predict the optimal beam direction through the AI / ML model. For example, the optimal beam directions predicted by the AI / ML model include K, which can be denoted as the Top-K beam set, where K is an integer greater than or equal to 1.

[0167] S606: The terminal device sends a first measurement report to the network device.

[0168] The first measurement report includes beam measurement results of reference signals sent in beam directions of the first beam subset, and also includes a beam identifier of the optimal beam direction predicted by the AI / ML model, i.e., the beam identifier of the beam direction in the second beam subset. Exemplarily, the first measurement report is a CSI report.

[0169] Optionally, the first measurement report also includes a third value, where the third value is used to indicate the number of beam directions included in the second beam subset.

[0170] Optionally, the first measurement report further includes a fourth value. As described above, the fourth value is used to indicate the number of beam directions included in the first beam subset.

[0171] As an example, the terminal device may transmit the first measurement report to the network device via the UCI. For example, the field design of the UCI may be as shown in Table 1:

[0172] Table 1

[0173]

[0174] As shown in Table 1, compared with the traditional UCI, two fields related to the second beam subset are added here, which are used to report the number of beams contained in the second beam subset and the beam identifier contained in the second beam subset. The total length of the beam identifier reporting field for the optimal beam direction predicted by the AI / ML model is , where N is the number of beam directions included in the beam set setA, K is the number of optimal beam directions predicted by the AI / ML model (i.e., the beam directions included in the second beam subset), and K is the third value.

[0175] It should be noted that Table 1 uses 7-bit quantization of the RSRP of the beam directions included in the first beam subset as an example. In another example, other values ​​can also be used to quantize RSRP, which is not limited in this embodiment of the present application.

[0176] S607: The terminal device sends target indication information to the network device.

[0177] The target indication information is used to request the network device to transmit the target beam subset for performance monitoring of the AI / ML model, namely the monitoring set setM.

[0178] As an example, when the terminal device determines that performance monitoring of the AI / ML model is required, the terminal device sends target indication information to the network device to request the network device to determine and return the monitoring set set M. For example, when the terminal device detects that the prediction performance of the AI / ML model has degraded, such as when the signal-to-noise ratio decreases when receiving a signal in the optimal beam direction predicted by the AI / ML model, the terminal device may send target indication information to the network device.

[0179] Of course, it should be noted that S607 is optional. In another example, after the terminal device reports the beam measurement results of the first beam subset and the beam identifier of the second beam subset, the network device directly performs the following S608 operation.

[0180] S608: The network device uses the beam measurement result of the first beam subset as input to the target self-supervisory model, and determines the beam measurement result of the beam set setA through the target self-supervisory model.

[0181] According to the previous records, the target self-supervised model can reconstruct the beam measurement results of the beam set setA based on an arbitrary beam subset, where the beam subset includes B beam directions.

[0182] As an example, the network device converts the beam measurement results of the first beam subset into a vector, and then inputs it into the target self-supervisory model. The beam measurement results of the first beam subset are processed by the target self-supervisory model to determine the beam measurement results of the beam set setA, that is, the beam measurement results of the reconstructed beam set setA.

[0183] Exemplarily, the network device converts the beam measurement result of the first beam subset into a vector using the following formula (10):

[0184] (10)

[0185] in, is the transformed vector, .

[0186] Afterwards, the vector is input into the target self-supervisory model, and the beam measurement results of the beam set set A are reconstructed by the target self-supervisory model. That is, in the embodiment of the present application, when monitoring the model performance, the terminal device is not required to measure the beam measurement results of the reference signal for each beam direction in the beam set set A. Instead, the network device reconstructs the beam measurement results of the reference signal for each beam direction in the beam set set A by using the target self-supervisory model based on the beam measurement results of the first beam subset. This can reduce the resource overhead of the reference signal measurement.

[0187] S609: The network device determines a target beam subset based on the reconstructed beam measurement result and the second beam subset.

[0188] As an example, a specific implementation of the network device determining the target beam subset based on the reconstructed beam measurement results and the second beam subset may include: the network device, based on the reconstructed beam measurement results, sorting the beam measurement results from the beam set in descending order, and selecting a first value of beam directions, where the union of the first value of beam directions and the beam directions included in the second beam subset is a second value. Subsequently, a subset consisting of the selected first value of beam directions and the beam directions included in the second beam subset is determined as the target beam subset.

[0189] According to the previous record, the second value is the number of beam directions that the terminal device can monitor at a single time.

[0190] For example, based on the RSRP values ​​of each beam direction in the reconstructed beam measurement results, the top X beam directions are selected from the beam set setA after sorting by RSRP from highest to lowest. The network device determines a subset consisting of the selected X beam directions and the K beam directions predicted by the AI / ML model as the target monitoring set, i.e., monitoring set setM, where |Top-K∪Top-X| = the second value.

[0191] It is worth noting that in an embodiment of the present application, the optimal beam direction predicted by the AI / ML model is selected as part of the target beam subset, and the terminal device subsequently measures the reference signal on the beam direction included in the target beam subset, that is, the terminal device will measure the actual measurement value of the reference signal of the optimal beam direction predicted by the AI / ML model, as well as the actual measurement value of the reference signal on the Top-K beam direction determined by the target self-supervisory model. In this way, by comparing the measurement value of the optimal beam direction predicted by the AI / ML model with the measurement value of the Top-K beam direction, it is possible to determine whether the optimal beam direction predicted by the AI / ML model is accurate, thereby detecting whether the AI / ML model prediction is valid, thereby improving the effectiveness of model performance monitoring.

[0192] It should be noted that the embodiment of the present application is described by taking the first X beam directions from the beam set setA as an example and sorting them from large to small according to RSRP. In another example, other X beam directions may be selected from the beam set setA. For example, the middle X beam directions may be selected from the beam set setA after sorting them from large to small according to RSRP, such as selecting the 2nd to X+1th beam directions after sorting, etc. The embodiment of the present application is not limited to this.

[0193] It should also be noted that the embodiments of the present application are described using an example in which a network device determines a target beam subset based on reconstructed beam measurement results and a second beam subset. In another example, the network device may determine the target beam subset based solely on the reconstructed beam measurement results. For example, the network device may select the first second value of beam directions from the beam set, sorting them from largest to smallest according to beam measurement results, and use the subset consisting of the second value of beam directions selected as the target beam subset.

[0194] S610: The network device sends second configuration information of the target beam subset to the terminal device.

[0195] Exemplarily, the second configuration information of the target beam subset includes configuration information related to the target beam subset, such as the beam identifier of the beam direction included in the target beam subset, as well as the time domain information, frequency domain information, QCL relationship, beam scanning mode, measurement frequency, etc. of the reference signal.

[0196] Correspondingly, the terminal device receives and stores the second configuration information of the target beam subset for subsequent beam selection and signal reception based on the second configuration information.

[0197] S611: The network device sends a MAC CE to the terminal device.

[0198] As an example, the MAC CE carries the TCI-State corresponding to each beam direction included in the target beam subset.

[0199] TCI-State is the index of the TCI state. One TCI-State corresponds to one beam direction, and each TCI-State is used to define the transmission configuration of the beam. For example, the TCI-State includes QCL information for downlink reception.

[0200] The network device activates the TCI state corresponding to each beam direction contained in the target beam subset through MAC CE so that the terminal device can quickly switch beams.

[0201] S612: The terminal device receives the MAC CE and activates multiple TCI states according to the instructions.

[0202] Afterwards, the terminal device is ready to receive reference signals from the beam directions corresponding to these activated TCI states.

[0203] S613: The network device sends DCI to the terminal device multiple times, and each time it sends DCI, it selects a beam direction corresponding to an activated TCI state to transmit a reference signal.

[0204] As an example, the network device may send a DCI to the terminal device to indicate which TCI state of the multiple activated TCI states the terminal device uses to receive the reference signal. For example, the DCI includes the index of the currently selected TCI state, that is, it includes TCI-State. In addition, each time a DCI is sent to the terminal device, the network device transmits a reference signal in the beam direction corresponding to the currently selected TCI state, that is, it transmits a reference signal in the beam direction corresponding to the TCI-State carried by the currently sent DCI.

[0205] S614: The terminal device receives the DCI and selects the corresponding TCI state according to the TCI-State in the DCI.

[0206] S615: The terminal device receives the reference signal using the beam direction corresponding to the selected TCI state.

[0207] In this way, the terminal device can measure the RSRP of the reference signal in the beam direction included in the target beam subset according to the DCI sent by the network device, thereby obtaining the beam measurement result of the target beam subset.

[0208] S616: The terminal device performs performance testing on the AI / ML model based on the beam measurement results of the target beam subset.

[0209] As an example, the terminal device determines the optimal beam direction from the target beam subset based on the beam measurement results of the target beam subset, such as selecting one or more beam directions with a high RSRP ranking, and then compares the beam measurement value of the selected optimal beam direction with the beam measurement value of the optimal beam direction predicted by the AI / ML model to determine whether the AI / ML model is effective.

[0210] As an example, the terminal device can compare the maximum RSRP value of the optimal beam direction predicted by the AI / ML model with the maximum RSRP value of the selected optimal beam direction. If the maximum RSRP value of the optimal beam direction predicted by the AI / ML model is equal to the maximum RSRP value of the selected optimal beam direction, or the maximum RSRP value of the optimal beam direction predicted by the AI / ML model is less than the maximum RSRP value of the selected optimal beam direction but the difference between the two does not exceed a certain threshold, it can be determined that the AI / ML model prediction is valid; otherwise, it is determined that the AI / ML model prediction is inaccurate, that is, the AI / ML model prediction is invalid.

[0211] It should be noted that the above method of determining whether the AI / ML model is effective is merely exemplary. In another example, other methods can be used for determination. For example, if the optimal beam direction determined from the target beam subset is the same as the optimal beam direction predicted by the AI / ML model, then the AI / ML model prediction is determined to be accurate, i.e., the AI / ML model prediction is effective; if the optimal beam direction determined from the target beam subset is different from the optimal beam direction predicted by the AI / ML model, then the AI / ML model prediction is determined to be inaccurate, i.e., the AI / ML model prediction is invalid.

[0212] Alternatively, if the intersection ratio of the optimal beam direction determined from the target beam subset and the optimal beam direction predicted by the AI / ML model is greater than or equal to a preset ratio threshold, the AI / ML model prediction is determined to be accurate, i.e., the AI / ML model prediction is valid; if the intersection ratio of the optimal beam direction determined from the target beam subset and the optimal beam direction predicted by the AI / ML model is less than the preset ratio threshold, the AI / ML model prediction is determined to be inaccurate, i.e., the AI / ML model prediction is invalid. The preset ratio threshold can be set as needed.

[0213] Alternatively, multiple tests can be performed in the same manner as above. If the proportion of valid tests to all tests is greater than or equal to a preset threshold, the AI / ML model prediction is determined to be accurate, i.e., the AI / ML model prediction is valid. If the proportion of valid tests to all tests is less than the preset threshold, the AI / ML model prediction is determined to be inaccurate, i.e., the AI / ML model prediction is invalid. The valid number refers to the number of times the AI / ML model is determined to be valid during multiple tests.

[0214] In an embodiment of the present application, the terminal device reports the beam measurement results of the first beam subset to the network device, so that the network device reconstructs the beam measurement results of each beam direction in the beam set based on the beam measurement results of the first beam subset through the trained target self-supervised model. The network device determines the target beam subset for detecting the performance of the AI / ML model based on the beam measurement results of each beam direction in the reconstructed beam set and the beam measurement results of the first beam subset. In this way, the terminal device avoids the need to measure all possible beam directions, which can reduce resource overhead. In addition, based on the beam measurement results of each beam direction in the reconstructed beam set, the target beam subset is determined in combination with the optimal beam direction predicted by the AI / ML model. After the terminal device measures the beam directions included in the target beam subset, the measured value of the optimal beam direction predicted by the AI / ML model is compared with the measured value of the Top-K beam direction. It can be determined whether the optimal beam direction predicted by the AI / ML model is accurate, so that it can be detected whether the AI / ML model prediction is valid, thereby improving the effectiveness of model performance monitoring.

[0215] See Figure 7 , Figure 7 This is a method flow for determining a monitoring set according to another exemplary embodiment. The method can be applied to Figure 2 or Figure 4 The communication system is implemented by the interaction between the terminal device and the network device. The embodiment of the present application is described by taking the AI / ML model deployed in the network device and the self-supervisory model deployed on the network device side as an example. The method may include some or all of the following contents:

[0216] S701: The terminal device sends a first measurement capability report to the network device.

[0217] The first measurement capability report is used to indicate the data collection capability of the terminal device for the beam subset.

[0218] As an example, the first measurement report includes a second value, where the second value is the number of beam directions that the terminal device can monitor at a single time.

[0219] Optionally, the first measurement capability report may further include a fourth value, monitoring function indication information, reporting frequency, etc. For details, see Figure 6 S601 in the illustrated embodiment.

[0220] S702: The network device sends first measurement configuration information to the terminal device through RRC signaling according to the first measurement capability report.

[0221] The first measurement configuration information is used to configure the reference signal of the beam direction included in the first beam subset. Exemplarily, the first measurement configuration information includes a beam identifier, as well as time domain information, frequency domain information, QCL relationship, beam scanning mode, measurement frequency, etc. of the reference signal.

[0222] Optionally, the first measurement configuration information further includes a first report quantity indication parameter and a second report indication parameter. The first report quantity indication parameter is used to indicate the beam measurement result of the first beam subset and the beam identifier of the second beam subset to be reported, and the second report quantity indication parameter is used to indicate the number of beam directions included in the second beam subset to be reported. In implementation, the network device can modify the RRC to carry the first report quantity indication parameter and the second report indication parameter in the first measurement configuration information. For specific implementation, please refer to Figure 6 S602 in the embodiment.

[0223] S703: The network device sends a reference signal to the terminal device in a beam direction included in the first beam subset based on the first measurement configuration information.

[0224] S704: The terminal device measures a reference signal transmitted by the network device in a beam direction included in the first beam subset.

[0225] The specific implementation of the above S703 to S704 can be found in Figure 6 S603 to S604 in the embodiment.

[0226] S705: The terminal device reports the beam measurement result of the first beam subset to the network device.

[0227] As an example of the present application, since the AI / ML model is deployed on the network device side, the terminal device can report the beam measurement results of the first beam subset to the network device, that is, report the beam measurement results of each beam direction in the first beam subset, so that the network device can predict the optimal beam direction based on the beam measurement results of the first beam subset.

[0228] As an example, the terminal device may report the beam measurement results of the first beam subset to the network device through the UCI.

[0229] S706: The network device predicts the optimal beam direction through the AI / ML model based on the beam measurement results of the first beam subset.

[0230] The network device may use the beam measurement results of the first beam subset as input and predict the optimal beam direction through the AI / ML model. For example, the AI / ML model may predict K optimal beam directions, denoted as the Top-K beam set, where K is an integer greater than or equal to 1.

[0231] S707: The network device uses the beam measurement result of the first beam subset as input to the target self-supervisory model, and determines the beam measurement result of the beam set setA through the target self-supervisory model.

[0232] As an example, when the network device determines that the performance of the AI / ML model needs to be monitored, it can perform the operation of S707 to determine the target beam subset for detecting the performance of the AI / ML model. As another example, when the network device receives an instruction from the terminal device, it can also perform the operation of S707 to determine the target beam subset for detecting the performance of the AI / ML model.

[0233] The network device uses the beam measurement results of the first beam subset as the input of the target self-supervisory model. The specific implementation of determining the beam measurement results of the beam set setA through the target self-supervisory model can be found in Figure 6 S608 in the embodiment.

[0234] S708: The network device determines a target beam subset based on the reconstructed beam measurement result and the second beam subset.

[0235] S709: The network device sends third configuration information of the target beam subset to the terminal device.

[0236] As an example, the third configuration information includes configuration information related to the target beam subset, such as the beam identifier of the beam direction included in the target beam subset, time domain information of the reference signal, frequency domain information, QCL relationship, beam scanning mode, measurement frequency, etc. In addition, the third configuration information also includes instruction information for instructing the terminal device to report the beam measurement result of the target beam subset, so that the terminal device can report the beam measurement result of the target beam subset to the network device after measuring the beam measurement result of the target beam subset.

[0237] S710: The network device sends a MAC CE to the terminal device.

[0238] S711: The terminal device receives the MAC CE and activates multiple TCI states according to the instructions.

[0239] Afterwards, the terminal device is ready to receive reference signals from the beam directions corresponding to these activated TCI states.

[0240] S712: The network device sends DCI to the terminal device multiple times, and each time it sends DCI, it selects a beam direction corresponding to an activated TCI state to transmit a reference signal.

[0241] S713: The terminal device receives the DCI and selects the corresponding TCI state according to the TCI-State in the DCI.

[0242] S714: The terminal device receives the reference signal using the beam direction corresponding to the selected TCI state.

[0243] The specific implementation of the above S708 to S714 can be found in Figure 6 S609 to S615 in the embodiment.

[0244] In this way, the terminal device can measure the RSRP of the reference signal in the beam direction included in the target beam subset according to the DCI sent by the network device, thereby obtaining the beam measurement result of the target beam subset.

[0245] S715: The terminal device reports the beam measurement results of the target beam subset to the network device.

[0246] As an example of the present application, since the AI / ML model is deployed on the network device side, the terminal device reports the beam measurement results of the target beam subset to the network device, that is, reports the beam measurement results of each beam direction in the target beam subset, so that the network device can perform performance testing on the AI / ML model based on the beam measurement results of the target beam subset.

[0247] As an example, the terminal device can report the beam measurement results of the target beam subset to the network device through UCI.

[0248] S716: The network device performs performance testing on the AI / ML model based on the beam measurement results of the target beam subset.

[0249] The specific implementation can be found in Figure 6 S616 in the illustrated embodiment.

[0250] In an embodiment of the present application, the terminal device reports the beam measurement results of the first beam subset to the network device, so that the network device reconstructs the beam measurement results of each beam direction in the beam set based on the beam measurement results of the first beam subset through the trained target self-supervised model. The network device determines the target beam subset for detecting the performance of the AI / ML model based on the beam measurement results of each beam direction in the reconstructed beam set and the beam measurement results of the first beam subset. In this way, the terminal device avoids the need to measure all possible beam directions, which can reduce resource overhead. In addition, based on the beam measurement results of each beam direction in the reconstructed beam set, the target beam subset is determined in combination with the optimal beam direction predicted by the AI / ML model. After the terminal device measures the beam directions included in the target beam subset, the measured value of the optimal beam direction predicted by the AI / ML model is compared with the measured value of the Top-K beam direction. It can be determined whether the optimal beam direction predicted by the AI / ML model is accurate, so that it can be detected whether the AI / ML model prediction is valid, thereby improving the effectiveness of model performance monitoring.

[0251] It should be noted that the above embodiments are described using the example of deploying the target self-supervisory model on the network device side. In another example, the target self-supervisory model can also be deployed on the terminal device side. In this case, the operations performed by the target self-supervisory model are implemented on the terminal device side, which is not limited in the embodiments of the present application.

[0252] Figure 8 A schematic block diagram of a communication device provided in an embodiment of the present application is shown. The communication device 8 can be a terminal device / network device, or a chip, chip system, or processor in the terminal device / network device that implements the above-mentioned method. The device can be used to implement the method described in the above-mentioned method embodiment. For details, please refer to the description of the above-mentioned method embodiment.

[0253] The communication device 1800 may include one or more processors 1810, also referred to as processing units, which may implement certain control functions. The processor 1810 may be a general-purpose processor or a dedicated processor. For example, it may be a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, while the central processing unit may be used to control the communication device, execute software programs, and process software program data.

[0254] In an optional design, the processor 1810 may also store instructions and / or data, which can be executed by the processor 1810 to enable the communication device 1800 to perform the method described in the above method embodiment.

[0255] In another alternative design, the communication device 1800 may include a communication interface 1820 for implementing receiving and transmitting functions. For example, the communication interface 1820 may be a transceiver circuit, an interface, an interface circuit, or a transceiver. The transceiver circuit, interface, interface circuit, or transceiver for implementing the receiving and transmitting functions may be separate or integrated. The transceiver circuit, interface, interface circuit, or transceiver may be used for reading and writing code / data, or the transceiver circuit, interface, interface circuit, or transceiver may be used for transmitting or delivering signals.

[0256] Optionally, the communication device 1800 may include one or more memories 1830, which may store instructions that can be executed on the processor 1810, causing the communication device 1800 to perform the methods described in the above method embodiments. Optionally, the memories 1830 may also store data. Optionally, the processor 1810 may also store instructions and / or data. The processor 1810 and the memories 1830 may be provided separately or integrated together.

[0257] It should be understood that in one possible design, each step in the method embodiment provided in the embodiment of the present application can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0258] It should be noted that the processor in the embodiments of the present application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above-described method embodiments can be completed by hardware integrated logic circuits in the processor or by software instructions. The above-described processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software modules can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above-described method.

[0259] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0260] An embodiment of the present application also provides a computer program product, which includes: computer program code, which, when executed on a computer, enables the computer to execute the various steps or processes executed by the terminal device / network device in any of the above method embodiments.

[0261] An embodiment of the present application also provides a computer-readable storage medium, which stores program code. When the program code runs on a computer, the computer executes the various steps or processes executed by the terminal device / network device in any of the above method embodiments.

[0262] An embodiment of the present application also provides a communication device, including a processor and an interface, wherein the interface is used to send and / or receive signals, so that the processor executes the various steps or processes performed by the terminal device / network device in any of the above method embodiments.

[0263] The above-mentioned device embodiments and method embodiments are completely corresponding, and the corresponding steps are performed by the corresponding modules or units. For example, the communication unit or communication interface performs the receiving or sending steps in the method embodiment. Other steps except sending and receiving can be performed by the processing unit or processor.

[0264] In the embodiments of this application, each term and English abbreviation is provided for convenience of description and shall not constitute any limitation to this application. The embodiments of this application do not exclude the possibility of defining other terms that can achieve the same or similar functions in existing or future protocols.

[0265] As used in this specification, the terms "component," "module," "system," and the like are used to refer to computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. By way of illustration, both an application running on a computing device and the computing device can be a component. One or more components can reside in a process and / or an execution thread, and a component can be located on a single computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable storage media having various data structures stored thereon. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component on a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0266] Those skilled in the art will appreciate that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented using hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0267] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can be based on the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0268] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0269] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0270] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0271] In the above embodiments, the functions of each functional unit can be implemented in whole or in part through software, hardware, firmware, or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, the processes or functions described in the embodiments of this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0272] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0273] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for determining a beam set, characterized in that: Applied to a network device, the method includes: receiving a first measurement report sent by a terminal device, where the first measurement report includes a beam measurement result of a reference signal sent in a beam direction of a first beam subset, where the first beam subset is a subset of a beam set, and the beam set includes all possible beam directions; Taking the beam measurement results of the first beam subset as input, and determining the beam measurement results of the beam set through a target self-supervisory model; A target beam subset is determined based on the beam measurement results of the beam set and a second beam subset, where the second beam subset includes an optimal beam direction predicted by an artificial intelligence AI / machine learning ML model, and the target beam subset is used to monitor the performance of the AI / ML model.

2. The method according to claim 1, wherein The determining a target beam subset based on the beam measurement result of the beam set and the second beam subset includes: From the beam set, select a first value of beam directions after sorting the beam measurement results from largest to smallest, where the union of the first value of beam directions and the beam directions included in the second beam subset is less than or equal to a second value, where the second value is the number of beam directions that the terminal device can monitor at a single time; A subset consisting of the selected first numerical number of beam directions and the beam directions included in the second beam subset is determined as the target beam subset.

3. The method according to claim 2, wherein The first measurement report further includes beam identifiers of beam directions in the second beam subset.

4. The method according to claim 2 or 3, wherein: The method further includes receiving a first measurement capability report, the first measurement capability report including the second value.

5. The method according to claim 4, wherein The method further comprises: Send first measurement configuration information to the terminal device, where the first measurement configuration information includes a first reporting quantity indication parameter, and the first reporting quantity indication parameter is used to indicate the reporting of the beam measurement results of the first beam subset and the beam identifier of the second beam subset.

6. The method according to claim 5, wherein The first reporting quantity indication parameter is a first enumeration value.

7. The method according to claim 5, wherein The first measurement configuration information also includes a second reporting quantity indication parameter, and the second reporting quantity indication parameter is used to indicate the number of beam directions included in the second beam subset to be reported.

8. The method according to claim 1, wherein The method further comprises: Sending second measurement configuration information to the terminal device, where the second measurement configuration information is used to configure a reference signal of a beam direction included in the target beam subset; Sending a media access control element MAC CE to the terminal device, where the MAC CE is used to activate a transmission configuration indication TCI state corresponding to the beam direction included in the target beam subset; Sending downlink control information DCI to the terminal device multiple times, where the DCI carries the index of the currently selected TCI state; After each transmission, a reference signal is transmitted in the beam direction corresponding to the currently selected TCI state.

9. The method according to claim 1, wherein The method further comprises: Receiving second measurement reports reported by multiple terminal devices, where the second measurement reports include beam measurement results of corresponding terminal devices on the reference signal of the beam set; Determining training data according to the beam measurement results reported by the multiple terminal devices; Based on the training data, the target self-supervised model is obtained by training the self-supervised model that has not completed training.

10. The method according to claim 9, wherein The determining the training data according to the beam measurement results reported by the multiple terminal devices includes: Selecting at least one set of beam measurement results with a fourth value from the beam measurement results reported by each terminal device to obtain multiple sets of beam measurement results with a fourth value; Using the beam measurement results of the multiple groups of fourth values ​​as inputs of an encoder in the self-supervisory model, and performing encoding processing by the encoder to obtain an encoding result; Using the encoding result and the mask mark as inputs of a decoder in the self-supervised model, and performing decoding processing by the decoder to obtain a decoding result, wherein the mask mark is obtained by masking the beam measurement results reported by each terminal device except the fourth value of beam measurement results; The self-supervisory model is trained based on the decoding result and the true value to obtain the target self-supervisory model, wherein the true value is a vector obtained by converting the beam measurement results reported by the multiple terminal devices.

11. A method for determining a beam set, characterized in that: Applied to a terminal device, the method includes: Sending a first measurement report to a network device, where the first measurement report is used by the network device to determine a target beam subset, the first measurement report including a beam measurement result of a reference signal sent in a beam direction of the first beam subset and a beam identifier of a second beam subset, the second beam subset including an optimal beam direction predicted by an artificial intelligence (AI) / machine learning (ML) model, and the target beam subset is used to monitor performance of the AI / ML model; The first beam subset, the second beam subset, and the target beam subset are all subsets of a beam set, and the beam set includes all possible beam directions.

12. The method according to claim 11, wherein The first measurement report further includes beam identifiers of beam directions in the second beam subset.

13. The method according to claim 11 or 12, wherein: The method further comprises: A first measurement capability report is sent to the network device, where the first measurement capability report includes a second value, where the second value is the number of beam directions that the terminal device can monitor at a single time.

14. The method according to claim 11 or 12, wherein: The method further comprises: Receive first measurement configuration information sent by the network device, where the first measurement configuration information includes a first reporting quantity indication parameter, and the first reporting quantity indication parameter is used to indicate reporting of the beam measurement results of the first beam subset and the beam identifier of the second beam subset.

15. The method according to claim 14, wherein The first measurement configuration information also includes a second reporting quantity indication parameter, and the second reporting quantity indication parameter is used to indicate the number of beam directions included in the second beam subset to be reported.

16. A communication device, characterized in that: The communication device comprises a processing unit and a transceiver unit, and is used to execute the program or instruction of the method according to any one of claims 1 to 10, or the program or instruction of the method according to any one of claims 11 to 15.

17. A communication device, characterized in that: The method comprises a processor coupled to a memory, wherein the memory stores a program or instruction for executing the method according to any one of claims 1 to 10, or the memory stores instructions for executing the method according to any one of claims 11 to 15.

18. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instructions are executed, the computer is caused to perform the method according to any one of claims 1 to 10 or any one of claims 11 to 15.

19. A communication system, characterized in that: Comprising the communication device as claimed in claim 16.

20. A computer program product, characterized in that The invention comprises a computer program which, when being executed, causes the method according to any one of claims 1 to 10 or 11 to 15 to be performed.

Images