Model performance reporting method, communication device, storage medium and program product

Abstract

The embodiment of the invention discloses a model performance reporting method, a communication device, a storage medium and a program product, relates to the technical field of communication, and enables a network device to obtain the model performance of a deactivated model. The method comprises the following steps: acquiring first information, wherein the first information is used for indicating a performance index of a deactivated first model in a terminal; and sending the first information to a network device.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a model performance reporting method, communication device, storage medium, and program product. Background Technology

[0002] In related technologies, after deactivating the terminal model, the network device still needs to monitor the performance of the terminal model to determine when to activate the model. However, currently, after deactivating the terminal model, the network device cannot obtain the performance of the deactivated model. Therefore, how the network device can obtain the performance of the deactivated model is a pressing technical problem that needs to be solved. Summary of the Invention

[0003] This application provides a model performance reporting method, communication device, storage medium, and program product, which enables network devices to obtain the model performance of deactivated models.

[0004] To achieve the above objectives, this application provides the following technical solution:

[0005] Firstly, a model performance reporting method is provided. This method can be executed by a terminal, or by components of the terminal, such as the terminal's processor, chip, or chip system, or by a logic module or software capable of implementing all or part of the terminal. The following explanation uses the method executed by a terminal as an example. The model performance reporting method includes: acquiring first information, which indicates the performance metrics of a deactivated first model in the terminal; and sending the first information to a network device.

[0006] In this embodiment, the terminal obtains the performance metrics of the deactivated model and reports these metrics to the network device. This allows the network device to obtain the model's performance metrics even for the deactivated model. This solves the technical problem in related technologies where the network device cannot obtain the terminal's model performance after model deactivation.

[0007] In one possible implementation, the method further includes: receiving second information from a network device; the second information is used to instruct the terminal to report the performance metrics of the deactivated model when the model state is in a deactivated state.

[0008] Based on this, the network device can instruct the terminal to still report the model's performance metrics even when the model is in a deactivated state by displaying an instruction. This allows the network device to obtain the performance metrics of the deactivated model.

[0009] In one possible implementation, sending the first information to the network device includes: sending the first information to the network device at a first cycle.

[0010] Based on this, the network device configures the first cycle to the terminal, and the terminal can report the performance indicators of the first model based on the first cycle configured by the network device.

[0011] In one possible implementation, before sending the first information to the network device, the method further includes: receiving first configuration information from the network device; wherein the first configuration information is used to configure the period of the performance indicators of the reporting model, and the period of the performance indicators of the reporting model includes a first period.

[0012] Based on this, the network device configures the period for reporting the performance indicators of the model to the terminal through configuration information, and the terminal can report the performance indicators of the first model based on the period configured by the network device.

[0013] In one possible implementation, the first configuration information includes the specific value of the first period; or, the first configuration information includes the index of the first period in the first period mapping table; wherein, the first period mapping table includes the mapping relationship between model performance and the period of reporting model performance indicators.

[0014] Based on this, the network device configures the first cycle to the terminal in different ways, and the terminal determines the first cycle in different ways, and then reports the performance indicators of the first model based on the first cycle.

[0015] In one possible implementation, sending the first information to the network device includes: sending the first information to the network device when the performance index of the first model meets a first preset threshold.

[0016] Based on this, when the performance indicators of the first model meet the first preset threshold, the terminal can send the first information to the network device, thereby ensuring that the network device can obtain the performance indicators that meet the conditions while reducing the signaling interaction process between the terminal and the network device.

[0017] In one possible implementation, the method further includes: receiving fourth information from a network device; wherein the fourth information is used to indicate a first preset threshold.

[0018] Based on this, the network device configures a first preset threshold for the terminal, and the terminal can report the performance indicators of the first model based on the first preset threshold configured by the network device.

[0019] In one possible implementation, sending first information to a network device includes: receiving a first request message from the network device; and in response to the first request message, sending first information to the network device; wherein the first request message is used to request the reporting of performance metrics of a first model.

[0020] Based on this, the terminal can report the performance indicators of the first model to the network device based on the network device's request.

[0021] In one possible implementation, the method further includes: sending fifth information to the network device when the performance index of the first model meets the first preset threshold; wherein the fifth information is used to indicate that the performance index of the first model meets the first preset threshold.

[0022] Based on this, the terminal indicates to the network device that the performance indicators of the first model meet the first preset threshold, so that the network device can determine whether to request the terminal to report the performance indicators of the first model based on its own conditions.

[0023] In one possible implementation, the method further includes: receiving sixth information from a network device; the sixth information is used to indicate management operations on the first model; the management operations include at least one of the following: activating the first model, maintaining the first model in a deactivated state, and issuing inference configuration information.

[0024] Based on this, the network device can manage the first model based on the performance indicators of the first model reported by the terminal.

[0025] In one possible implementation, the method further includes: in response to the monitoring period corresponding to the current performance index of the first model meeting a preset condition, determining that the monitoring period of the first model needs to be adjusted; wherein, the monitoring period is the period during which the network device and / or terminal periodically monitor the model performance of the first model; the preset condition includes: the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model; or, the monitoring period corresponding to the current performance index of the first model meets a period threshold condition; sending seventh information to the network device; the seventh information is used by the network device to determine the new monitoring period.

[0026] Based on this, if the current performance indicators of the first model are not compatible with the current monitoring cycle of the first model, the terminal can instruct the network device to determine a new monitoring cycle, thereby enabling the network device to monitor the first model based on a monitoring cycle that is compatible with the current performance indicators of the first model.

[0027] In one possible implementation, the seventh information is used to indicate a new monitoring cycle, and the method further includes: sending an eighth information to the network device; the eighth information is used to indicate that the current monitoring cycle needs to be adjusted; receiving a second request message from the network device; wherein the second request message is used to request the terminal to report the adjusted monitoring cycle of the first model's performance; sending the seventh information to the network device includes: responding to the second request message by sending the seventh information to the network device.

[0028] Based on this, the terminal indicates to the network device that there is a period that needs to be adjusted. If the network device instructs the terminal to report a new period, the terminal reports a new period to the network device.

[0029] In one possible implementation, when the preset conditions include that the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model, the method further includes: receiving second configuration information from the network device; the second configuration information is used to configure a second period mapping table; the second period mapping table includes the mapping relationship between model performance and monitoring period; and determining the monitoring period corresponding to the current performance index of the first model in the second period mapping table as the new monitoring period.

[0030] Based on this, the terminal can determine a new monitoring cycle based on the cycle mapping table configured for the terminal by the network device and the current performance indicators of the first model.

[0031] In one possible implementation, the seventh information includes the specific value of the new monitoring period; or, the seventh information includes the index of the new monitoring period in the second period mapping table.

[0032] Based on this, the terminal can indicate the monitoring period to the network device by specifying the value of the monitoring period or by using the index of the monitoring period in the second period mapping table.

[0033] In one possible implementation, if the preset conditions include the monitoring period corresponding to the current performance index of the first model meeting the period threshold condition, the method further includes: receiving third configuration information from the network device; the third configuration information is used to configure the period threshold condition.

[0034] Based on this, the terminal can determine a new monitoring cycle based on the periodic threshold conditions configured for the terminal by the network device and the current performance indicators of the first model.

[0035] In one possible implementation, the network device is a centralized unit (CU), or the network device is a distributed unit (DU).

[0036] Based on this, the CU or DU can manage the reporting performance indicators and reporting monitoring cycles of the terminal, and / or manage the first model.

[0037] Secondly, a model performance reporting method is provided. This method can be executed by a network device, or by a component of the network device, such as the network device's processor, chip, or chip system, or by a logic module or software capable of implementing all or part of the network device. The following description uses the example of this method being executed by a network device. The model performance reporting method includes: receiving first information from a terminal, the first information indicating the performance metrics of a first model that has been deactivated in the terminal.

[0038] In one possible implementation, the method further includes: sending a second message to the terminal; the second message is used to instruct the terminal to report the performance metrics of the deactivated model when the model state is in a deactivated state.

[0039] In one possible implementation, the first information is sent by the terminal in a first cycle.

[0040] In one possible implementation, the method further includes: sending first configuration information to the terminal; wherein the first configuration information is used to configure the period of the performance indicators of the reporting model, and the period of the performance indicators of the reporting model includes the first period.

[0041] In one possible implementation, the first configuration information includes the specific value of the first period; or, the first configuration information includes the index of the first period in the first period mapping table; wherein, the first period mapping table includes the mapping relationship between model performance and the period of reporting model performance indicators.

[0042] In one possible implementation, the first information is sent by the terminal to the network device when the performance index of the first model meets a first preset threshold.

[0043] In one possible implementation, the method further includes: sending fourth information to the terminal; wherein the fourth information is used to indicate a first preset threshold.

[0044] In one possible implementation, receiving first information from the terminal includes: sending a first request message to the terminal; receiving first information sent by the terminal in response to the first request message; wherein the first request message is used to request the reporting of performance metrics of the first model.

[0045] In one possible implementation, the method further includes: receiving fifth information from the terminal; wherein the fifth information is used to indicate that the performance index of the first model meets a first preset threshold.

[0046] In one possible implementation, the method further includes: sending a sixth message to the terminal; the sixth message is used to indicate a management operation on the first model; the management operation includes at least one of the following: activating the first model, keeping the first model in an inactive state, and issuing inference configuration information.

[0047] In one possible implementation, the method further includes: receiving seventh information from the terminal; the seventh information is used by the network device to determine a new monitoring period; wherein the seventh information is sent by the terminal when the monitoring period corresponding to the current performance index of the first model meets preset conditions; the monitoring period is the period during which the network device and / or the terminal periodically monitors the model performance of the first model; the preset conditions include: the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model; or, the monitoring period corresponding to the current performance index of the first model meets a period threshold condition.

[0048] In one possible implementation, the seventh information is used to indicate a new monitoring cycle, and the method further includes: receiving an eighth information from the terminal; the eighth information is used to indicate that the current monitoring cycle needs to be adjusted; sending a second request message to the terminal; wherein the second request message is used to request the terminal to report the adjusted monitoring cycle of the first model's performance; receiving the seventh information from the terminal includes: receiving the seventh information sent by the terminal in response to the second request message.

[0049] In one possible implementation, if the preset conditions include that the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model, the method further includes: sending second configuration information to the terminal; the second configuration information is used to configure a second period mapping table; the second period mapping table includes the mapping relationship between model performance and monitoring period.

[0050] In one possible implementation, the seventh information includes the specific value of the new monitoring period; or, the seventh information includes the index of the new monitoring period in the second period mapping table.

[0051] In one possible implementation, if the preset conditions include the monitoring period corresponding to the current performance index of the first model meeting the period threshold condition, the method further includes: sending third configuration information to the terminal; the third configuration information is used to configure the period threshold condition.

[0052] In one possible implementation, the network device is a centralized unit (CU), or the network device is a distributed unit (DU).

[0053] Thirdly, a communication device is provided for implementing the various methods described above. This communication device can be a terminal as described in the first aspect, or a device including the terminal, or a device included in the terminal, such as a chip. Alternatively, the communication device can be a network device as described in the second aspect, or a device including the network device, or a device included in the network device, such as a chip. The communication device includes modules, units, or means corresponding to the methods described above, which can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the functions described above.

[0054] In some possible designs, the communication device may include a processing module and a transceiver module. The transceiver module, also referred to as a transceiver unit, is used to implement the transmission and / or reception functions in any of the above aspects and their possible implementations. The transceiver module may consist of transceiver circuits, transceivers, transceivers, or communication interfaces. The processing module can be used to implement the processing functions in any of the above aspects and their possible implementations.

[0055] In some possible designs, the transceiver module includes a sending module and a receiving module, which are used to implement the sending and receiving functions in any of the above aspects and any possible implementation methods.

[0056] Fourthly, a communication device is provided, comprising: at least one processor; the processor being configured to execute a computer program or instructions stored in a memory to cause the communication device to perform the methods of any of the preceding aspects. The memory may be coupled to the processor, or may be independent of the processor. The communication device may be a terminal as described in the first aspect, or a device comprising the terminal, or a device included in the terminal, such as a chip. Alternatively, the communication device may be a network device as described in the second aspect, or a device comprising the network device, or a device included in the network device, such as a chip. In some possible designs, the communication device includes a memory for storing necessary program instructions and data.

[0057] In one possible implementation, the processor includes logic circuitry and input and / or output interfaces. The output interfaces are used to perform the sending action in the corresponding method, and the input interfaces are used to perform the receiving action in the corresponding method.

[0058] In one possible implementation, the communication device further includes a communication interface and a communication bus, with the processor, memory, and communication interface connected via the communication bus. The communication interface is used to perform the sending and receiving actions in the corresponding method. The communication interface can also be called a transceiver. Optionally, the communication interface includes a transmitter and a receiver; in this case, the transmitter is used to perform the sending action in the corresponding method, and the receiver is used to perform the receiving action in the corresponding method.

[0059] In some possible designs, the communication device can be a chip or a chip system. When the communication device is a chip system, it can be composed of chips or may include chips and other discrete components. When the communication device is a chip, the aforementioned transmitting action / function can be understood as an output, and the aforementioned receiving action / function can be understood as an input.

[0060] Fifthly, a chip is provided, which includes a processor for implementing the functions involved in any of the above aspects or any implementation thereof.

[0061] In some possible designs, the chip includes a memory for storing necessary program instructions and data.

[0062] In a sixth aspect, a computer-readable storage medium is provided, which stores a computer program or instructions that, when executed on a communication device, enable the communication device to perform the methods of any of the above aspects or any implementation thereof.

[0063] In a seventh aspect, a computer program product containing instructions is provided, which, when run on a communication device, enables the communication device to execute any of the above aspects or any implementation thereof.

[0064] Eighthly, a communication system is provided, which includes the terminal described in the first aspect and the network device described in the second aspect.

[0065] For the technical effects of any of the implementation methods in aspects two through eight, please refer to the technical effects of the corresponding implementation method in aspect one, which will not be repeated here.

[0066] It should be noted that any of the possible implementations of any of the above aspects can be combined, provided that the solutions do not contradict each other. Attached Figure Description

[0067] Figure 1 A schematic diagram of an AI-based beam management process provided for this application;

[0068] Figure 2 A schematic diagram of an AI-based CSI feedback enhancement process provided for this application;

[0069] Figure 3 A flowchart illustrating the process by which a network device configures a terminal-side AI model, as provided in this application;

[0070] Figure 4 A schematic diagram of a CU-DU separation architecture in an open RAN architecture provided for this application;

[0071] Figure 5 This application provides a schematic diagram of the system architecture of the RIC architecture within an open RAN architecture;

[0072] Figure 6 A schematic diagram of the system architecture of a communication system provided in this application;

[0073] Figure 7 A schematic diagram of the system architecture of another communication system provided in this application;

[0074] Figure 8 A schematic diagram of the architecture of a communication system provided in this application;

[0075] Figure 9 A schematic diagram of the composition of a communication device provided in this application;

[0076] Figure 10 A flowchart illustrating a model performance reporting method provided in this application;

[0077] Figure 11 A flowchart illustrating another model performance reporting method provided in this application;

[0078] Figure 12 A flowchart illustrating another model performance reporting method provided in this application;

[0079] Figure 13 A flowchart illustrating another model performance reporting method provided in this application;

[0080] Figure 14 A flowchart illustrating another model performance reporting method provided in this application;

[0081] Figure 15 A flowchart illustrating another model performance reporting method provided in this application;

[0082] Figure 16 A flowchart illustrating another model performance reporting method provided in this application;

[0083] Figure 17 A flowchart illustrating another model performance reporting method provided in this application;

[0084] Figure 18 A flowchart illustrating another model performance reporting method provided in this application;

[0085] Figure 19 This is a schematic diagram of the structure of a communication device provided in this application. Detailed Implementation

[0086] To facilitate understanding of the technical solutions of the embodiments of this application, a brief introduction to the relevant technologies of this application is given below.

[0087] 1. Applications of Artificial Intelligence in Communication Networks

[0088] With the development of communication networks, the number of services they support is also increasing. These networks need to meet the diverse requirements of various services, such as ultra-high speed, ultra-low latency, ultra-high reliability, and / or massive connectivity. Furthermore, the spectrum used by current communication networks is becoming increasingly concentrated, placing higher demands on base station energy efficiency. These factors have led to increasingly complex network planning, configuration, and resource scheduling. If network planning, configuration, and resource scheduling are still performed based on manual experience or simple algorithms, problems such as long processing times, high costs, poor self-optimization capabilities, and poor adaptability of scheduling algorithms will arise.

[0089] In related technologies, artificial intelligence (AI) and machine learning (ML) can be used for network planning, configuration, and resource scheduling in communication networks. When applying AI and ML to communication networks, a large amount of data from the network is first acquired. AI and ML algorithms are then used to train models and / or make inferences based on this data, outputting the training and / or decision results (such as predictions of future business data volume over a certain period). Applying AI and ML to communication networks can improve the efficiency of network planning, configuration, and resource scheduling, thus achieving network intelligence.

[0090] Current applications of artificial intelligence in communication networks include, but are not limited to, at least one of the following: 1.1 AI-based beam management; 1.2 AI-based mobility management; 1.3 AI-based positioning; 1.4 AI-based channel state information (CSI) feedback enhancement. These applications are described below:

[0091] 1.1 AI-based beam management

[0092] like Figure 1 The diagram illustrates the AI-based beam management process. This process includes: the terminal or network side scanning a preset beam set B (SetB) and determining the scanning results; the terminal and / or network side using an AI model to predict SetA based on the scanning results of SetB; determining the Top-K beams in SetA; and the terminal selecting the optimal beam from the Top-K beams. Here, SetA is a beam set that includes SetB, or SetA is a beam set different from SetB. Optionally, the Top-K beams can be the K beams in SetA with the optimal reference signal received power (RSRP) for layer 1 (L1).

[0093] 1.2 AI-based mobility management

[0094] In mobility management without AI, network devices configure terminals to report measurements and make corresponding handover decisions based on the reported measurement results. With AI, terminals can reduce the number of measurement reports. Network devices, based on AI models, predict measurement results reported less frequently by terminals and select the optimal cell for handover based on the prediction results. Methods to reduce the number of measurement reports by terminals include: the network device reducing the number of measurement beams configured for the terminal, or the terminal reducing the number of beam measurements performed.

[0095] 1.3 AI-based positioning

[0096] When using AI for positioning, there are two scenarios: direct positioning based on AI and positioning assisted by AI.

[0097] AI-based direct location can be further divided into the following cases:

[0098] Case 1: Positioning is performed directly on the terminal side based on an AI model. For example, the terminal measures the positioning signal and uses an AI model to predict the positioning measurement results to obtain the final positioning result.

[0099] Case 2b: Location management function (LMF) is used for positioning. In this process, the LMF obtains the terminal's location assistance information and its own positioning measurement results, and uses an AI model to predict the location assistance information and positioning measurement results to obtain the final positioning result.

[0100] Case 3b: Access network equipment assists LMF in positioning. In this process, the LMF obtains positioning assistance information from the access network equipment, as well as its own positioning measurement results, and uses an AI model to predict the positioning assistance information and positioning measurement results to obtain the final positioning result.

[0101] AI-assisted localization includes the following cases:

[0102] Case 2a: Terminal Model-Assisted Localization (LMF) for Positioning. In this process, the terminal determines the positioning measurement results and uses the terminal-side AI model to predict the positioning measurement results, obtaining the prediction results. The terminal sends the prediction results to the LMF, and the LMF performs positioning assistance based on the terminal's prediction results.

[0103] Case 3a: Access network device model-assisted localization (LMF). In this process, the access network device determines the localization measurement results and uses its own AI model to predict the results. The access network device then sends the prediction results to the LMF, which uses these predictions to perform localization assistance.

[0104] 1.4 AI-based CSI feedback enhancement

[0105] First, let's explain CSI. CSI describes the known channel properties of a communication link. CSI typically includes information on scattering, fading, and power attenuation experienced by the signal during transmission from the transmitter to the receiver, such as multipath effects, environmental fading, and distance-induced attenuation. The transmitter and receiver optimize the data transmission process based on CSI information to improve transmission quality.

[0106] Currently, channel state information (CSI) can be determined through channel estimation. The specific process is as follows: the network device sends a reference signal, and the terminal measures the reference signal to determine its CSI information. After that, the terminal reports the CSI to the network device, which then performs CSI acquisition or beam management based on the CSI. Alternatively, the terminal may not report the CSI but instead determine the receive beam based on the CSI.

[0107] In current 5G new radio (NR) systems, codebooks are typically used as the feedback tool for Computational Signal Indication (CSI). Multiple codebook schemes, such as Type I and Type II codebooks, are designed for different levels of feedback accuracy. However, current codebooks are usually designed for uniformly arranged antenna arrays and are not optimized for special antennas such as 3D antennas, resulting in significant limitations in codebook performance.

[0108] AI-based CSI feedback enhancement can be optimized for specific channel environments, thereby improving CSI feedback performance. In the AI-based CSI feedback process, the high-dimensional channel information feedback task is treated as an end-to-end CSI image compression and restoration task. For example... Figure 2 As shown, the AI-based CSI feedback enhancement process includes: the encoder (usually located at the terminal) uses an encoder to extract and compress features from the complete channel information, obtaining a bitstream that meets the feedback requirements. The encoder's feedback link sends the bitstream information to the decoder (usually located at the base station). The decoder uses a decoder to decompress and reconstruct features from the bitstream information, recovering the complete channel information. The encoder and decoder are jointly optimized during end-to-end training to achieve the best CSI reconstruction performance. In actual deployment, the encoder and decoder need to be used in pairs; that is, the compressed CSI output by a certain encoder needs to be recovered using the corresponding decoder.

[0109] Furthermore, CSI prediction can be based on AI, which means adding new air interface resource overhead to the existing CSI to predict the CSI of unknown time-frequency resources. Depending on the data correlation category, AI-based CSI prediction includes, but is not limited to, at least one of the following: 1) CSI prediction based on time correlation, i.e., predicting the CSI of the next moment or the next time period based on the CSI of the previous period. This method is typically applied in time-varying channels or high-speed mobile scenarios. 2) CSI prediction based on frequency-based correlation, such as predicting and reconstructing the downlink CSI based on the uplink CSI of FDD. 3) CSI prediction based on spatial-based correlation. 4) CSI prediction based on the correlation of channels between adjacent users.

[0110] 2. Configuration of the AI ​​model on the terminal side

[0111] like Figure 3 The diagram illustrates the process of configuring the AI ​​model on the terminal side using network devices. Figure 3 As shown, the process includes:

[0112] Step 301: The network device sends a terminal capability query request to the terminal. Correspondingly, the terminal receives the terminal capability query request from the network device.

[0113] In some embodiments, a terminal capability query request is used to request a query about the terminal's model capabilities. As an example, the terminal capability query request is: UECapabilityEnqiry.

[0114] Step 302: The terminal sends terminal capability information to the network device. Correspondingly, the network device receives the terminal capability information from the terminal.

[0115] In some embodiments, the terminal capability information is the terminal's model capability. Optionally, when the model is available in the terminal, the initial state of the model is an active state. As an example, the terminal capability information is: UECapabilityInformation.

[0116] Step 303: The network device sends a radio resource control (RRC) reconfiguration to the terminal. Correspondingly, the terminal receives the RRC reconfiguration from the network device.

[0117] In some embodiments, the RRC reconfiguration in this step can be another configuration (OtherConfig). As an example, the RRC reconfiguration in this step is: RRCReconfiguration(ieOtherConfig).

[0118] Step 304: The terminal sends terminal assistance information to the network device. Correspondingly, the network device receives the terminal assistance information from the terminal.

[0119] As an example, the terminal assistance information is: UEAssistanceInformation.

[0120] Step 305: The network device sends an RRC reconfiguration message to the terminal. Correspondingly, the terminal receives the RRC reconfiguration from the network device. Optionally, the RRC reconfiguration message in this step includes, but is not limited to, at least one of the following: a measurement configuration matching the model, and an inference configuration matching the model. As an example, the RRC reconfiguration in this step is: RRCReconfiguration.

[0121] Step 306: Monitor the model performance of the network device and / or terminal monitoring terminal.

[0122] In some implementations, the terminal monitors the performance metrics of its own model and reports these metrics to the network device. The network device monitors model performance based on these metrics and manages the model accordingly. As an example, in a model-based beam management scenario, the beam management model is initially in an active state. The terminal compares the top k results measured in setA with the top k results predicted in setA based on setB to determine the performance metrics and reports them to the network device. The network device then manages the model based on these performance metrics. As an example, monitoring the terminal's model performance includes managing the model as follows: activation / deactivation / inference / monitoring.

[0123] In some implementations, the terminal reports actual measurement results and prediction results obtained from model inference to the network device. The network device derives the model's performance metrics based on the actual measurement results and prediction results, and manages the model based on these performance metrics. As another example, in a model-based beam management scenario, the beam management model is initially in an active state. The terminal determines and reports the top k results measured in setA and the top k results predicted in setA by setB to the network device. The network device determines the model performance based on the top k results measured in setA and the top k results predicted in setA by setB. The network device manages the model based on its performance metrics.

[0124] The management of the model by the network device includes, but is not limited to, activation, deactivation, inference, and monitoring. After the network device performs deactivation management on the model, the terminal will no longer send new prediction results to the network device.

[0125] 3. Open Radio Access Network (RAN) Architecture

[0126] like Figure 4 The diagram shown is an architectural schematic of a central unit (CU) - distributed unit (DU) separation architecture in an open RAN architecture provided by an embodiment of this application; as shown Figure 4 As shown, the open RAN architecture includes core network equipment, access network equipment, and terminals. The core equipment and terminals include AI modules; the access network equipment follows a CU-DU separation architecture, including a CU and a DU. Optionally, the CU is also called a central unit or control unit. Both the CU and DU also include AI modules. The control unit CU can be further divided into a central unit control plane (CU-CP) and a central unit user plane (CU-UP). Both the CU-CP and CU-UP also include AI modules. The number of devices in the above system architecture can be one or more, and the number of AI modules in each device can also be one or more; for clarity, only one AI module is shown in the figure.

[0127] The aforementioned AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, each AI module can perform different functions. An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0128] The core network equipment mentioned above connects to the access network equipment via the NG interface. The access network equipment connects to the terminal via the Uu interface. The CU connects to the DU via the F1 interface. When the CU is divided into CU-CP and CU-UP, CU-CP connects to the DU via the F1-C interface; CU-UP connects to the DU via the F1-U interface.

[0129] It should be understood that the Open RAN architecture may also include Figure 4 Other components besides those shown are not limited in this application embodiment.

[0130] like Figure 5 The diagram illustrates a system architecture diagram of a RIC architecture within an open RAN architecture provided in this application embodiment. This system architecture includes a RAN intelligent controller (RIC). The RIC includes near-real-time (NRT) RICs and non-real-time (Non-RT) RICs. The near-real-time RIC is used for model training and inference. For example, it is used to train an AI model and then use that AI model for inference. The near-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or radio units (RUs)) and / or terminals. This information can be used as training data or inference data. Optionally, the near-real-time RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, the near-real-time RIC delivers the inference result to the DU, and the DU sends it to the RU.

[0131] Non-real-time RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers the inference result to a DU, which then forwards it to an RU. Near-real-time and non-real-time RICs can also be configured as separate network elements. Optionally, near-real-time and non-real-time RICs can also be part of other devices; for example, a near-real-time RIC can be located in a RAN node (e.g., in a CU or DU), while a non-real-time RIC can be located in Operations, Administration and Maintenance (OAM), a cloud server, a core network device, or other network devices.

[0132] The following is a detailed description of the solutions provided in the embodiments of this application. Before introducing the embodiments of this application, the following points should be noted.

[0133] In the description of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0134] In the description of this application, A sending a message to B can be understood as A sending a message to B through one or more network elements.

[0135] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and / or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0136] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0137] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0138] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0139] It is understood that in this application, "...when" and "if" both refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require a judgment action to be performed during implementation, nor do they imply any other limitations.

[0140] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0141] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, and in the various implementation methods / methods / implementations within each embodiment, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the various implementation methods / methods / implementations within each embodiment are consistent and can be mutually referenced. The technical features in different embodiments and the various implementation methods / methods / implementations within each embodiment can be combined according to their inherent logical relationships to form new embodiments, implementation methods, methods, or implementation approaches. The embodiments described below do not constitute a limitation on the scope of protection of this application.

[0142] The technical solutions of this application embodiment can be used in various communication systems, including 3GPP communication systems such as 4th generation (4G) systems (e.g., Long Term Evolution (LTE) systems), 5th generation (5G) systems (e.g., New Radio (NR) systems), LTE and 5G hybrid networking systems, integrated communication and sensing systems, non-terrestrial networks (NTN), device-to-device (D2D) communication systems, vehicle-to-everything (V2X) communication systems, machine-type communication (MTC) systems, Internet of Things (IoT) systems, or other future communication systems. The communication system can also be a non-3GPP communication system; there is no limitation on this.

[0143] The communication systems described above are merely illustrative examples, and are not limited to those described herein. The communication systems provided in this application do not impose any limitations on the solutions described herein. This will be explained uniformly here and will not be repeated below.

[0144] Figure 6 This is a schematic diagram illustrating one possible, non-limiting system. For example... Figure 6 As shown, the communication system includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (e.g., Figure 6 110a and 110b (collectively referred to as 110) and at least one terminal (such as Figure 6 RAN100, denoted as RAN100, comprises RAN nodes 120a-120j, collectively referred to as RAN120. RAN100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 6 (Not shown in the image). Terminal 120 is connected to RAN node 110 wirelessly. RAN node 110 is connected to core network 200 wirelessly or via wired connection. The core network node in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0145] In one possible implementation, a core network node can refer to a device in the core network 200 that provides service support to terminal 120. In this embodiment, the core network node in the core network 200 includes a sensing function (SF) network element. The SF network element is mainly used to implement sensing functions, which may include sensing control functions and / or sensing computation functions. Furthermore, the SF network element can also support sensing billing functions when terminal 120 and / or RAN node 110 perform sensing. For example, the sensing control function may include determining sensing devices, sensing nodes, etc. A sensing device can be understood as a device that sends and / or receives sensing signals. Further, the sensing device also performs corresponding signal processing based on the received echo signals to obtain sensing measurement data. For example, the sensing device can be RAN node 110 or terminal 120, etc. A sensing node can refer to a network node in the wireless network that participates in the sensing service process. The sensing computation function may include performing corresponding signal processing on the echo signals received by the sensing device to obtain sensing measurement data, and further processing based on the sensing measurement data and application information to obtain sensing results, etc.

[0146] For example, an SF network element can sometimes be called a communication device; for instance, an SF network element can be understood as a communication device with core network sensing capabilities. Furthermore, an SF network element can also be called a sensing server, etc., without limitation.

[0147] In one possible scenario, the function of the SF network element can be implemented by the network data analytics function (NWDAF) network element, or the SF network element and the NWDAF network element can be co-located.

[0148] Optionally, in addition to SF network elements, core network nodes in core network 200 may also include at least one of the following: access and mobility management function (AMF) network elements, session management function (SMF) network elements, user plane function (UPF) network elements, policy control function (PCF) network elements, unified data management (UDM) network elements, application function (AF) network elements, network exposure function (NEF) network elements, network slice selection function (NSSF) network elements, or location management function (LMF) network elements, etc. Of course, core network 200 may also include other core network nodes without restriction.

[0149] The AMF (Agency Flow Management) network element is deployed in the core network 200 to provide mobility management and connectivity management for the network, such as user location updates, user registration with the network, and user handover. The AMF network element can act as an intermediate route between the LMF, SMF, and RAN 100. The SMF network element is mainly responsible for session management in the mobile network, such as session establishment, modification, and release. The UPF (User Plane Function) network element is a user plane function element, mainly responsible for connecting to external networks and processing user packets, such as forwarding and charging. The PCF (Programmable Flow Function) network element is mainly responsible for providing policies to the AMF and SMF, such as Quality of Service (QoS) policies and slice selection policies. The UDM (User DM) network element is used to store user data, such as subscription information and authentication / authorization information. The AF (Agency Flow) network element is responsible for providing services to the 3GPP network. The NEF (Network Flow Function) network element is mainly used to open the capabilities of various network functions and is responsible for converting internal and external information. The LMF network element is a device or component deployed in the core network 200 to provide positioning functions for the terminal 120; for example, the LMF network element can initiate a positioning process to locate a specific terminal.

[0150] In this application, network elements may also be referred to as entities or functional entities. For example, an SF network element may also be referred to as an SF entity or an SF functional entity. In addition, the aforementioned AMF network elements, SMF network elements, UPF network elements, PCF network elements, UDM network elements, AF network elements, NEF network elements, and LMF network elements may have other names in future communication systems, and this application does not impose specific limitations on them.

[0151] In one possible implementation, RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as a 4G, 5G mobile communication system, or a future-oriented evolution system. RAN 100 can also be an open RAN (O-RAN or ORAN), a cloud radio access network (CRAN), an NTN network (such as an NTN supporting pass-through mode and / or regenerative mode, or an NTN supporting eye-viewing mode (earth fixed cell) and / or non-eye-viewing mode (earth moving cell), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0152] RAN node 110, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and assists terminals in achieving wireless access. Multiple RAN nodes 110 in RAN 100 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative, for example... Figure 6 Network element 120i can be a helicopter or a drone, and it can be configured as a mobile base station. For terminals 120j that access RAN 100 through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes referred to as communication devices, for example... Figure 6 Network elements 110a and 110b can be understood as communication devices with base station functions, while network elements 120a-120j can be understood as communication devices with terminal functions.

[0153] For RAN node 110, in one possible scenario, RAN node 110 can be a base station, an evolved NodeB (eNodeB, also known as eNB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a future communication base station in a future mobile communication system, or an access node in a WiFi system, etc. RAN node 110 can also be a macro base station (such as...) Figure 6 110a), micro base stations or indoor stations (such as Figure 6The network equipment can be a relay node or donor node, or a wireless controller in a CRAN scenario. Examples include: satellite base stations, radio network controllers (RNCs), base station controllers (BSCs), base transceiver stations (BTSs), home base stations (e.g., home evolved NodeBs, or home NodeBs, HNBs), relay stations, balloon stations, drone stations, wireless backhaul nodes, or grant nodes (G nodes) in satellite telemetry. It is understood that network equipment can be ground-based or non-ground-based (e.g., satellites, drones, high-altitude communication equipment). Furthermore, the names of network equipment with base station functions may differ in communication systems employing different wireless access technologies; this application does not limit this. Optionally, RAN node 110 can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, in vehicle-to-everything (V2X) technology, the access network equipment can be a roadside unit (RSU). RAN node 110 is also known as the next generation-RAN (NG-RAN) node.

[0154] In another possible scenario, multiple RAN nodes 110 collaborate to assist the terminal in achieving wireless access, with each RAN node 110 implementing a portion of the base station's functions. For example, a RAN node 110 can be a CU, DU, CU-CP, CU-user plane (UP), or radio unit (RU), etc. CUs and DUs can be configured separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0155] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0156] In one possible scenario, terminal 120 can be a device used to implement wireless communication functions, such as a terminal, a chip or circuit that can be used in the terminal, or an entity associated with the terminal. Specifically, terminal 120 can be user equipment (UE), access terminal, terminal unit, terminal station, mobile station (MS), mobile station, remote station, remote terminal, mobile device, wireless communication equipment, terminal agent or terminal device, subscriber unit, smartphone, wireless data card, tablet computer, wireless modem, laptop computer, machine type communication (MTC) terminal, tag, etc., in a 5G network or a future evolved public land mobile network (PLMN). The access terminal can be a cellular phone, cordless phone, Session Initiation Protocol (SIP) phone, Wireless Local Loop (WLL) station, Personal Digital Assistant (PDA), handset with wireless communication capabilities, computing device or other processing device connected to a wireless modem, in-vehicle device or wearable device, virtual reality (VR) terminal, augmented reality (AR) terminal, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical care, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, or terminal node (T-node) in StarSpark, etc. In one possible implementation, terminal 120 can be mobile or fixed. It is understood that the terminal and the mobile user can be completely independent. All user-related information can be stored in a subscriber identity module (SIM) card, which can be used on the terminal device. The terminal can then interact with network-side devices by sending and / or receiving signals over the air interface.

[0157] The chip or circuit in the terminal includes components inside the terminal, such as at least one of a chip, a central processing unit (CPU), a network processing unit (NPU), and a terminal radio frequency module.

[0158] Entities associated with the terminal include terminal-side servers, computing / processing nodes, computing / processing entities, computing / processing units, and servers such as over-the-top (OTT) servers. OTT refers to various services provided to users by a third party other than the network operator via the operator's network. Examples of OTT services include OTT voice communication services, OTT multimedia services, and OTT data processing services. The terminal interacts with relevant information (e.g., data) through communication with this associated network entity. For example, this associated network entity and the terminal may belong to the same vendor. Since model training, model selection, etc., may not be executed on the terminal but rather on the terminal-side OTT server, the term "terminal" in this embodiment also includes the terminal-side OTT server.

[0159] It should be understood that the terminal in this embodiment may also be referred to as the "UE side" or the "UE part".

[0160] In one possible implementation, the network device (e.g., access node or core network node) and the terminal in this embodiment can also be referred to as communication devices. These devices can be general-purpose or dedicated devices. The network device may include an access node (RAN node), an operation administration and maintenance (OAM) device, or a core network node. For the OAM device, it may include devices in the element management system (EMS) or the network management system (NMS). It should be understood that the network device in this embodiment can also be referred to as a "network side" or a "network part." This embodiment does not specifically limit its use in this regard.

[0161] In one possible implementation, the relevant functions of the terminal or network device in this application embodiment can be implemented by one device, multiple devices working together, or one or more functional modules within a single device. This application embodiment does not specifically limit this. It is understood that the above functions can be network elements in hardware devices, software functions running on dedicated hardware, a combination of hardware and software, or virtualization functions instantiated on a platform (e.g., a cloud platform).

[0162] It should be noted that a RAN node can be a device or a component within a device in the aforementioned NG-RAN, such as an ng-eNB node, a gNB node, or a transmission point (TP), transmission and reception point (TRP) within an ng-eNB node and a gNB node, or a central unit (CU) integrated on the NG-RAN. A RAN node can also be a network element with transmission capabilities, such as a transmission measurement function (TMF) network element. In some embodiments, a RAN node can also be an access node in an O-RAN system. A RAN typically consists of a series of modules, such as antennas, RRUs, and BBUs. Traditional RAN architectures define the overall reception and output of a RAN node but do not restrict the transmission and communication between internal modules. O-RAN architectures define the architectural connections and standardized interfaces between various modules within the RAN, allowing the RAN to be decoupled into multiple standard modules, thereby enabling the combination and replacement of modules.

[0163] For example, such as Figure 7The diagram illustrates a possible, non-limiting O-RAN system architecture. The Service Management and Orchestration Framework (SMO), as the network management device in the O-RAN, is used for the operation and management of devices within the O-RAN. The Non-Real-Time RAN Intelligent Controller (Non-RT RIC), located within the SMO module, implements non-real-time intelligent management of RAN functions, such as AI / ML workflows including model training and updates, and guides applications / functions within the Near-RT RIC based on policies. The Near-Real-Time RAN Intelligent Controller (Near-RT RIC) enables near-real-time intelligent management of the RAN. Through data collection and related operations on the E2 interface, it achieves near-real-time control and optimization of O-RAN modules and resources.

[0164] The O-RAN central unit (O-CU) comprises the O-RAN central unit control plane (O-CU-CP) and the O-RAN central unit user plane (O-CU-UP). The O-CU implements the radio resource control (RRC) layer, the packet data convergence protocol (PDCP) layer, the service data adaptation protocol (SDAP) layer, and other control functions. Specifically, the O-CU-CP implements the RRC layer functions and the PDCP control plane functions. The O-CU-UP implements the SDAP layer functions and the PDCP user plane functions.

[0165] The O-RAN distributed unit (O-DU) is used to implement the radio link control (RLC) layer, media access control (MAC) layer, and higher physical layer (Higher PHY). The higher physical layer functions include one or more of the following: forward error correction (FEC) encoding / decoding, scrambling / descrambling, or modulation / demodulation.

[0166] The O-RAN radio unit (O-RU) is used to implement lower physical layer (PHY) functions and radio frequency (RF) functions. These PHY functions include one or more of the following: Fast Fourier Transform (FFT) / Inverse Fast Fourier Transform (iFFT), digital beamforming, or extraction and filtering of the physical random access channel (PRACH). In other words, the O-RU possesses functions similar to TRP and RRH RF devices, as well as PHY processing capabilities. Furthermore, the O-RU, O-CU, and O-DU can also be used as a single unit, i.e., the O-eNB / gNB, to implement the aforementioned functions.

[0167] O-RAN cloud (O-Cloud) is a cloud computing platform that includes physical infrastructure nodes for hosting O-RAN functions such as RIC and O-DU. O-Cloud supports software components (such as operating systems, virtual machine monitoring, and container runtimes), management, and orchestration functions.

[0168] In one possible scenario, the O-RAN system also includes a sensing unit (SU). The SU is mainly used to implement sensing-related functions, such as sending sensing signals and / or receiving echo signals of sensing signals, performing corresponding signal processing based on the received echo signals to obtain sensing measurement data, and performing sensing-related processing, etc.

[0169] As one possible implementation, a RAN node may include at least one of CU, DU, SU, and RU. A communication interface exists between CU and SU. A communication interface may or may not exist between SU ​​and DU. If no communication interface exists between SU ​​and DU, SU and DU can communicate through CU.

[0170] In the O-RAN architecture, the module that receives the report of the difference between the twin channel and the measurement channel can be CU, RT RIC, Non-RT RIC, etc. DU is responsible for receiving signals, signal processing, multipath measurement, and channel difference calculation.

[0171] For example, an O-RAN system includes communication interfaces between newly added internal components and other communication interfaces. For instance, the A1 interface serves as the interface between Non-RT RICs and Near-RT RICs, used for intelligent and dynamic control of radio resources within the O-RAN. Non-RT RICs can provide policies, enriched information, and ML model updates to Near-RT RICs via the A1 interface, while Near-RT RICs can provide policy feedback to Non-RT RICs via the A1 interface.

[0172] The E2 interface is an open interface between two endpoints used to connect the Near-RT RIC and the RAN node. The RAN node includes the CU and DU in 5G, the O-RAN compatible eNB in ​​4G, and the O-CU (O-CU-CP and / or O-CU-UP) and / or O-DU in O-RAN. The Near-RT RIC can obtain data collection and feedback from the RAN node through the E2 node, and the RAN node can obtain control feedback from the Near-RT RIC through the E2 node.

[0173] The O1 interface is the interface between the management entity in the SMO and the O-RAN module, used for operation management. This interface enables network management (such as fault management, configuration management, billing management, performance management, and security management, also known as FCAPS management), software management, and file management. The O2 interface is the interface between the SMO and the infrastructure management framework that supports O-RAN virtual network functions.

[0174] The Open Fronthaul (FH) CUS-Plane interface includes a control plane (C-Plane), a user plane (U-Plane), and a synchronization plane (S-Plane). The control plane is used for real-time control between the O-DU and O-RU, such as transmitting beamforming weights from the O-DU to the O-RU or performing power control from the O-DU to the O-RU. The user plane is used to transmit communication data between the DU and RU for access network devices and terminals. The synchronization plane is used by the O-DU to provide clock synchronization to the O-RU. The Open FH M-Plane interface is the management plane interface, used for connection between the O-RU and O-DU, as well as the SMO, enabling management, monitoring, and configuration functions.

[0175] In addition, the NG interface is the interface between RAN nodes (e.g., base stations, CUs, CU-CPs, CU-UPs) and the core network; NG-u is the user plane NG interface; and NG-c is the control plane NG interface. The Xn interface is the interface between NR RAN nodes; Xn-u is the user plane Xn interface; and Xn-c is the control plane Xn interface. The X2 interface is the interface between LTE RAN nodes; X2-u is the user plane X2 interface; and X2-c is the control plane X2 interface. In NR systems, the X2 interface is mainly used in E-UTRA-NR dual connectivity scenarios (E-UTRA-NR dualconnectivity, EN-DC), where the primary base station is an LTE RAN node connected to the LTE core network via the X2 interface. The E1 interface is the interface between CU-CPs and CU-UPs; the F1-C interface is the interface between CU-CPs and DUs; and the F1-U interface is the interface between CU-UPs and DUs.

[0176] In some embodiments, the communication device in this application can implement AI / ML workflow (also known as model operation), including data collection, model training, model transfer, model update, model inference, model monitoring, and model management.

[0177] The model performance reporting method provided in this application can be applied to scenarios involving communication between terminals and network devices. For example, as Figure 8 The diagram shown is an architectural schematic of a communication system 80 provided in an embodiment of this application. The communication system 80 includes a terminal 801 and a network device 802.

[0178] The terminal 801 is used to obtain the performance indicators of the deactivated first model and report the performance indicators of the first model to the network device 802.

[0179] In some embodiments, terminal 801 may periodically report the performance indicators of the first model to network device 802 based on a period specified by network device 802. Alternatively, terminal 801 may report the performance indicators of the first model to network device 802 when a condition threshold is met, based on a condition threshold specified by network device 802.

[0180] In some other embodiments, terminal 801 and network device 802 negotiate the monitoring period for the first model to achieve periodic monitoring of the first model. Specifically, terminal 801 can determine the monitoring period for the first model based on its performance and then inform network device 802 of this monitoring period. Terminal 801 and network device 802 can update the monitoring period for the first model in real time based on its performance.

[0181] In some other embodiments, the network device 802 may manage the first model based on the performance indicators of the first model reported by the terminal 801, or the monitored model performance of the first model. Managing the first model includes at least one of the following: activating the first model, maintaining the first model in a deactivated state, and issuing inference configuration information.

[0182] In one possible implementation, Figure 9 This is a schematic diagram illustrating the composition of a communication device 900 provided in an embodiment of this application. Figure 6 The network devices and terminals shown can all be used Figure 9 The shown composition structure, or including Figure 9 The component shown; or, Figure 6 The components (e.g., chips) in the network devices and terminals shown can all be adopted. Figure 9 The shown composition structure, or including Figure 9 The components are shown. It is understood that the communication device 900 includes means of the necessary form, such as modules, units, elements, circuits, or interfaces, to be appropriately configured together to perform this solution.

[0183] like Figure 9 As shown, the communication device 900 includes one or more processors 91. The processors 91 are used to implement the processing and determination processes performed by the various devices in the following embodiments. The processor 91 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, while the central processing unit can be used to control the communication device (e.g., a RAN node, terminal, or chip), execute software programs, and process data from the software programs.

[0184] Optionally, in one design, the processor 91 may include a program 93 (sometimes referred to as code or instructions) that can be run on the processor 91 to cause the communication device 900 to perform the methods described in the following embodiments.

[0185] Optionally, the communication device 900 may include one or more memories 92 storing a program 94 (sometimes referred to as code or instructions) that can be run on the processor 91 to cause the communication device 900 to perform the methods described in the following method embodiments.

[0186] Optionally, the processor 91 and / or memory 92 may include AI modules 97 and 98, which are used to implement AI-related functions. These AI modules can be implemented through software, hardware, or a combination of both. For example, the AI ​​modules may include an intelligent controller (RIC) module. For instance, the AI ​​modules may be near real-time RICs or non-real-time RICs.

[0187] Optionally, the processor 91 and / or memory 92 may also store data. The processor and memory may be configured separately or integrated together.

[0188] Optionally, the communication device 900 may further include a transceiver 95, which is used to implement the transmission and reception processes performed by the various devices in the following embodiments. The processor 91, sometimes referred to as a processing unit, controls the communication device (e.g., a RAN node or terminal). The transceiver 95, sometimes referred to as a transceiver unit, transceiver, transceiver circuit, or transceiver, etc., may also include an antenna 96 in the communication device 900.

[0189] It should be pointed out that, Figure 9 The structural composition shown does not constitute a limitation on the communication device, except... Figure 9 In addition to the components shown, the communication device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0190] In this embodiment of the application, the chip system may be composed of chips or may include chips and other discrete devices.

[0191] Furthermore, the actions, terms, etc., involved in the various embodiments of this application can be referenced interchangeably without limitation. The message names or parameter names in the messages exchanged between the various devices in the embodiments of this application are merely examples, and other names may be used in specific implementations without limitation.

[0192] The following is combined with Figures 1 to 9 The method for reporting model performance provided in the embodiments of this application is described below.

[0193] It should be noted that in the following embodiments of this application, the message names between network elements, the names of each parameter, or the names of each piece of information are just examples. In other embodiments, they may be other names. The model performance reporting method provided in this application does not specifically limit them.

[0194] It is understood that in the embodiments of this application, each network element may execute some or all of the steps in the embodiments of this application. These steps or operations are merely examples, and the embodiments of this application may also execute other operations or variations thereof. Furthermore, the steps may be executed in different orders as presented in the embodiments of this application, and it is not necessary to execute all the operations in the embodiments of this application.

[0195] It is understood that this application uses terminals and network devices as examples to illustrate the execution of the interaction, but this application does not limit the execution subject of the interaction. For example, the method executed by the terminal in this application can also be executed by a module applied to the terminal (e.g., a chip, chip system, or processor), or by a logical node, logical module, or software that can implement all or part of the terminal's functions; similarly, the method executed by the network device in this application can also be executed by a module applied to the network device (e.g., a chip, chip system, or processor), or by a logical node, logical module, or software that can implement all or part of the network device's functions. This application does not specifically limit these aspects.

[0196] Figure 10 This is a flowchart illustrating a model performance reporting method provided in an embodiment of this application. In this embodiment, the terminal obtains the performance metrics of a deactivated first model and reports these metrics to the network device, thereby solving the technical problem in related technologies where the terminal does not report the performance metrics of the deactivated model to the network device, preventing the network device from obtaining the terminal's model performance. The functions and actions of each device in the communication system provided in this embodiment are described below, such as... Figure 10 As shown, the model performance reporting method includes the following steps:

[0197] Step 1001: The terminal obtains the first information.

[0198] The first information is used to indicate the performance metrics of the first model that is deactivated in the terminal.

[0199] In some embodiments, the terminal determines a deactivated first model and monitors the performance metrics of the first model. Based on the monitored performance metrics of the first model, the terminal generates first information. The terminal may include at least one deactivated model, and the first model may be some or all of the at least one deactivated model. In this embodiment, the example of the first model being one of the at least one deactivated model is mainly used for illustration.

[0200] The first model in this application embodiment can be understood with reference to the artificial intelligence model or machine learning model in the related technologies described above. For example, the first model includes, but is not limited to, at least one of the following: a beam management model for beam management, a positioning model for positioning, a channel state information model for channel state information management, and a mobility management model for mobility management. A detailed understanding of this model can be found in the descriptions in the related technologies described above, and will not be repeated here.

[0201] In some implementations, the model's performance metrics are relevant indicators used to characterize the model's performance, such as the model's error rate and the rate of change of model error.

[0202] As an example, the first model is a beam management model. The performance metrics of the beam management model include the error rate between the beams obtained from model inference and the beams obtained from beam measurement. For example, the error rate is obtained by comparing the top K beams obtained by inferring setB using the beam management model with the top K measurement results obtained by beam measurement of setB.

[0203] As another example, the first model is a mobility management model. The performance indicators of the mobility management model include the error rate between the cell measurement results obtained by model inference and the measurement results obtained by actual cell measurement.

[0204] Step 1002: The terminal sends first information to the network device. Correspondingly, the network device receives the first information from the terminal.

[0205] In some embodiments, after generating first information, the terminal sends the first information to the network device. After receiving the first information from the terminal, the network device determines the performance indicators of the first model based on the first information.

[0206] In the embodiments of this application, the network device can be an access network device or a core network device. If the network device is an access network device and the access network device is an open RAN architecture, the network device can also be a CU or DU in the access network device. This application does not limit this.

[0207] In one possible implementation, the model performance reporting method provided in this disclosure can be applied to the following scenarios described in the above-mentioned related technologies: 1.1 AI-based beam management; 1.2 AI-based mobility management; 1.3 AI-based positioning; 1.4 AI-based CSI feedback enhancement, etc. This disclosure does not limit the application of these scenarios.

[0208] In this embodiment, the terminal obtains the performance metrics of the deactivated model and reports these metrics to the network device. This allows the network device to obtain the model's performance metrics even for the deactivated model. This solves the technical problem in related technologies where the network device cannot obtain the terminal's model performance after model deactivation.

[0209] In some embodiments, the terminal may determine the performance metrics that need to be reported for the deactivation model based on instructions from the network device. Combined with Figure 10 ,like Figure 11 As shown, the process by which the terminal determines the performance metrics that need to be reported for the deactivation model based on the instructions from the network device includes:

[0210] Step 1101: The network device sends the second information to the terminal. Correspondingly, the terminal receives the second information from the network device.

[0211] The second piece of information is used to instruct the terminal to report the performance metrics of the deactivated model when the model is in a deactivated state.

[0212] The network device may not send a second message to the terminal, but may pre-determine through protocol specifications that the terminal must report the performance indicators of the deactivated model when the model is in a deactivated state. This application does not impose any restrictions on this.

[0213] As one implementation, the second information can be carried in the inference configuration sent by the network device to the terminal. Optionally, the network device sends both measurement configuration and inference configuration to the terminal.

[0214] The measurement configuration includes at least one of the following: a measurement configuration for actual measurements, or a measurement configuration reused for AI / ML functions during model activation. For example, in a beam management scenario, the measurement configuration includes: a beam measurement configuration for actual measurements, or a reused setB (the measurement configuration used during model activation).

[0215] The inference configuration contains the aforementioned second information, instructing the terminal to still report model performance metrics even when the model is in an inactive state. As an example, the second information can occupy a bit in the inference configuration. When the bit is of the first value, it indicates that the terminal still needs to report model performance metrics even when the model is in an inactive state. When the bit is of the second value, it indicates that the terminal does not need to report model performance metrics even when the model is in an inactive state.

[0216] Based on this, the network device can instruct the terminal to still report the model's performance metrics even when the model is in a deactivated state by displaying an instruction. This allows the network device to obtain the performance metrics of the deactivated model.

[0217] In some embodiments, the scenarios in which a terminal sends first information to a network device include: Scenario 1, where the terminal periodically sends first information to the network device; Scenario 2, where the terminal sends first information to the network device when preset conditions are met; and Scenario 3, where the terminal sends first information to the network device based on a request from the network device. Scenario 1 to Scenario 3 will be described below:

[0218] Scenario 1: The terminal periodically sends the first information to the network device.

[0219] In scenario 1, combined with Figure 10 ,like Figure 12 As shown, step 1002 above can be specifically implemented through the following step 1201:

[0220] Step 1201: The terminal sends first information to the network device in a first cycle. Correspondingly, the network device receives the first information sent by the terminal in the first cycle.

[0221] In one implementation, the terminal periodically monitors the performance indicators of the first model in a first cycle and sends the monitored model performance indicators to the network device. In this application, the first cycle can be replaced by a reporting cycle or a terminal reporting cycle, etc., and is not limited thereto.

[0222] In one possible implementation, the network device may pre-configure the first cycle for the terminal before the terminal sends the first information to the network device in the first cycle. For example... Figure 12 As shown, the process of the network device pre-configuring the terminal for the first cycle includes:

[0223] Step 1202: The network device sends first configuration information to the terminal. Correspondingly, the terminal receives the first configuration information from the network device.

[0224] The first configuration information is used to configure the period for the performance indicators of the reporting model, such as the first period.

[0225] As one implementation, the first configuration information can also be carried in the aforementioned inference configuration. In other words, the network device can use the inference configuration to instruct the terminal that the model's performance metrics still need to be reported when the model is in an inactive state, and to instruct the terminal on the period for reporting the inactive model's performance metrics.

[0226] As another implementation, the network device may not configure the first cycle to the terminal, but instead agree on the cycle of the performance indicators of the terminal's reporting model through protocols or specifications. This application does not limit this.

[0227] As an example, the first configuration information includes the specific value of the first period. In other words, the network device directly configures the period length of the first period to the terminal, and the terminal periodically reports the performance indicators of the first model based on the period length of the first period.

[0228] As another example, the first configuration information includes the index of the first period in the first period mapping table; wherein, the first period mapping table includes the mapping relationship between model performance and the period for reporting model performance indicators. In other words, the network device configures the index of the first period in the first period mapping table to the terminal. The terminal looks up the period length of the corresponding period in the first period mapping table based on this index. After that, the terminal periodically reports the performance indicators of the first model based on the period length of the first period.

[0229] In this application, the first-cycle mapping table can be a mapping table pre-configured by the network device to the terminal, or it can be a mapping table agreed upon through protocols or specifications, etc., and this application does not limit it in this regard. Optionally, the model performance of the terminal in the first-cycle mapping table can specifically be the model performance error rate, the model performance error change rate, etc., and this application does not limit it in this regard.

[0230] Optionally, the first period mapping table can be used to characterize the mapping relationship between the model performance error rate and the monitoring period; or, the mapping relationship between the model performance error change rate and the monitoring period. The reporting period can be a specific period, or a period value obtained according to a period calculation formula. The period calculation formula may include, but is not limited to, the product of a preset reporting period and a preset coefficient, or the ratio of the product of one preset reporting period and a preset coefficient to another preset period, etc. This application does not limit the specifics of this formula.

[0231] As an example, taking the first cycle mapping table as an example to characterize the mapping relationship between the model performance error rate and the product of the preset monitoring period and the preset coefficient, as shown in Table 1 below, the first cycle mapping table includes four sets of mapping relationships between the model performance error rate and the reporting period. Each set corresponds to an index, and the model performance error rate and the reporting period are different in different sets:

[0232] Table 1. Mapping Table for the First Period

[0233] Index (Idx) Model performance error rate Terminal reporting cycle 1 Greater than 50% Period 1 2 Greater than 25% and less than 50% (period 1 * coefficient 1) / period 2 3 Greater than 5% and less than 25% (Period 1 * coefficient 2) / Period 3 4 Less than 5% (Period 1 * coefficient 3) / Period 4

[0234] The values ​​of period 1, period 2, period 3, period 4, and coefficients 1, 2, and 3 in Table 1 above can be configured according to requirements; the model performance error rate corresponding to each period is provided as an example, and this application does not limit it.

[0235] Based on Table 1 above, when the value of the index configured by the network device to the terminal is 1, the terminal determines the period length of reporting the performance indicators of the first model as: the period length of period 1.

[0236] When the value of the index configured by the network device to the terminal is 2, the terminal determines the period length for reporting the performance index of the first model as: (period 1 * coefficient 1) / period 2.

[0237] When the value of the index configured by the network device to the terminal is 3, the terminal determines the period length for reporting the performance indicators of the first model as: (period 1 * coefficient 2) / period 3.

[0238] When the index value configured by the network device to the terminal is 4, the terminal determines the period length for reporting the performance indicators of the first model as: period 1 * coefficient 3) / period 4.

[0239] It should be noted that, in one possible implementation, the terminal can directly determine the period for reporting the performance indicators of the first model based on the model performance error rate of the first model and the aforementioned first period mapping table, without the need for instructions from the network device. This application does not limit this.

[0240] Based on the above scheme, the network device configures the first cycle to the terminal, and the terminal can report the performance indicators of the first model based on the first cycle configured by the network device.

[0241] Scenario 2: The terminal sends the first information to the network device when preset conditions are met.

[0242] In scenario 2, combined Figure 10 ,like Figure 13 As shown, step 1002 above can be specifically implemented through the following step 1301:

[0243] Step 1301: When the performance index of the first model meets the first preset threshold, the terminal sends first information to the network device. Correspondingly, the network device receives the first message sent by the terminal when the performance index of the first model meets the first preset threshold.

[0244] In one implementation, the terminal monitors the performance metrics of the first model in real time, and when the performance metrics of the first model meet a first preset threshold, it sends a first message to the network device. The network device receives the first message from the terminal.

[0245] In one possible implementation, before the terminal sends the first information to the network device, the network device may pre-configure a first preset threshold for the terminal. For example... Figure 13 As shown, the process by which the network device pre-configures a first preset threshold for the terminal includes:

[0246] Step 1302: The network device sends the fourth information to the terminal. Correspondingly, the terminal receives the fourth information from the network device.

[0247] The fourth piece of information is used to indicate the first preset threshold.

[0248] As one implementation, the fourth piece of information can also be carried in the aforementioned inference configuration. In other words, the network device can instruct the terminal through the inference configuration that the model's performance metrics still need to be reported when the model is in an inactive state, and instruct the terminal to report the first preset threshold of the performance metrics of the inactive model.

[0249] The network device may not configure a first preset threshold for the terminal, but may instead define a first preset threshold for the performance indicators of the terminal's reporting model through protocols or specifications. This application does not impose any restrictions on this.

[0250] As an example, the first preset threshold is 50%, and the performance index of the first model satisfies the first preset threshold, which is that the performance change rate of the first model is greater than 50% (or less than or equal to 50%). In other words, when the performance change rate of the first model is greater than 50% (or less than or equal to 50%), the terminal reports the performance index of the first model to the network device.

[0251] In some implementations, if the performance index of the first model meets a first preset threshold, the terminal may not directly report the performance index of the first model to the network device. Instead, it may indicate to the network device that the performance index of the first model meets the first preset threshold, and the network device will then determine whether the terminal needs to report the performance index of the first model.

[0252] If the network device determines, based on its own performance or the current network conditions, that the terminal needs to report the performance indicators of the first model, it sends a request message to the terminal requesting the terminal to report the performance indicators of the first model; the terminal reports the performance indicators of the first model to the network device based on the network device's request.

[0253] If the network device determines, based on its own performance or the current network conditions, that it does not need the terminal to report the performance indicators of the first model, it sends a rejection message to the terminal to refuse the terminal from reporting the performance indicators of the first model; the terminal does not report the performance indicators of the first model to the network device.

[0254] Based on the above scheme, the network device configures a first preset threshold to the terminal, and the terminal can report the performance indicators of the first model based on the first preset threshold configured by the network device.

[0255] Scenario 3: The terminal sends the first information to the network device based on the network device's request.

[0256] In scenario 3, combined with Figure 10 ,like Figure 14As shown, step 1002 above can be specifically implemented through steps 1401 and 1402:

[0257] Step 1401: The network device sends a first request message to the terminal. Correspondingly, the terminal receives the first request message from the network device.

[0258] The first request message is used to request the reporting of performance metrics for the first model.

[0259] Step 1402: In response to the first request message, the terminal sends first information to the network device. Correspondingly, the network device receives the first message sent by the terminal in response to the first request message.

[0260] In some embodiments, when the network device needs to obtain the performance metrics of the first model, it sends a first request message to the terminal. After receiving the first request message, the terminal obtains the performance metrics of the first model and sends the performance metrics of the first model to the network device.

[0261] In some other embodiments, when the network device receives an indication message from the terminal indicating that the model performance metrics meet a first preset threshold, it sends a first request message to the terminal. After receiving the first request message, the terminal obtains the performance metrics of the first model and sends the performance metrics of the first model to the network device. In this case, as... Figure 14 As shown, prior to step 1401, the method further includes:

[0262] Step 1403: When the performance indicators of the first model meet the first preset threshold, the terminal sends the fifth information to the network device. Correspondingly, the network device receives the fifth information from the terminal.

[0263] The fifth piece of information is used to indicate that the performance indicators of the first model meet the first preset threshold.

[0264] In one implementation, when the performance index of the first model meets the first preset threshold, the terminal indicates in the fifth information that the performance index of the first model meets the first preset threshold through corresponding bits. After receiving the first information, the network device determines whether the terminal needs to report the performance index of the first model. The specific process can be referred to the relevant description in Scenario 2 above, and will not be elaborated here.

[0265] The understanding of the first preset threshold can be referred to the understanding of the first preset threshold in Scenario 2 above, and this application does not limit it.

[0266] Based on the above scheme, the network device requests the performance indicators of the first model from the terminal, and the terminal can report the performance indicators of the first model to the network device based on the request from the network device.

[0267] The above, in conjunction with scenarios 1 to 3, provides a detailed explanation of the process by which the terminal sends the first information to the network device.

[0268] In some embodiments, after the terminal sends first information to the network device, the network device monitors the performance of the first model based on the performance indicators of the first model in the first information, and manages the first model based on the performance indicators of the first model. For example... Figure 11 As shown, the process by which the network device manages the first model can be specifically implemented through the following steps 1102:

[0269] Step 1102: The network device sends a sixth message to the terminal. Correspondingly, the terminal receives the sixth message from the network device.

[0270] The sixth piece of information is used to indicate management operations for the first model. Optionally, the management operations include at least one of the following: activating the first model, maintaining the first model in a deactivated state, and issuing inference configuration information.

[0271] Based on this, after receiving the performance indicators of the first model, the network device can perform management operations such as activating or deactivating the first model and issuing inference configuration information based on the performance indicators of the first model, thereby realizing the management of the deactivated model.

[0272] In some embodiments, after receiving the performance metrics of the first model, the network device monitors the first model based on these metrics. The network device may monitor the first model periodically based on a monitoring period. This monitoring period may be the same as or different from the first period described above. In other words, the network device may monitor the first model immediately after receiving its performance metrics; alternatively, it may not monitor the first model immediately after receiving its performance metrics, but rather after the monitoring period has elapsed, thereby reducing the overhead of monitoring the first model.

[0273] When monitoring the first model using network devices, the monitoring cycle can be adjusted based on the performance indicators of the first model. Combined with... Figure 10 ,like Figure 15 As shown, adjusting the monitoring cycle based on the performance indicators of the first model can be achieved through the following steps 1501 and 1502.

[0274] Step 1501: In response to the monitoring period corresponding to the current performance index of the first model meeting the preset conditions, the terminal determines that the first model needs to be adjusted.

[0275] The monitoring period is the period during which the network device and / or terminal periodically monitor the performance of the first model; the preset conditions include: the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model; or, the monitoring period corresponding to the current performance index of the first model meets the period threshold condition.

[0276] Step 1502: The terminal sends the seventh information to the network device. Correspondingly, the network device receives the seventh information from the terminal.

[0277] The seventh piece of information is used by the network device to determine a new monitoring cycle.

[0278] In some implementations, the terminal monitors the performance metrics of the first model in real time and determines whether the monitoring period corresponding to the current performance metrics of the first model meets preset conditions. When it is determined that the monitoring period corresponding to the current performance metrics meets the preset conditions, the terminal sends a seventh message to the network device to instruct the network device to determine a new monitoring period.

[0279] Optionally, the seventh information may indicate the length of a new monitoring period to the network device. The network device monitors the first model according to the length of the monitoring period indicated by the seventh information.

[0280] Optionally, the seventh information may also indicate multiple cycle lengths to the network device. The network device selects one cycle length from the multiple cycle lengths as the new monitoring cycle based on current network performance and / or model performance metrics. The network device monitors the first model according to the cycle length of the seventh information's monitoring cycle.

[0281] As one implementation method, when the seventh information indicates a new monitoring cycle, the terminal can pre-indicate the need to adjust the monitoring cycle to the network device, which then determines whether to adjust the monitoring cycle. For example... Figure 15 As shown, this process can be implemented through steps 1503 to 1505.

[0282] Step 1503: The terminal sends the eighth message to the network device. Correspondingly, the network device receives the eighth message from the terminal.

[0283] The eighth piece of information is used to indicate the monitoring cycle that needs to be adjusted.

[0284] As one implementation, when the terminal detects that the monitoring period of the first model needs adjustment, it indicates to the network device that the current monitoring period needs adjustment. This allows the network device to determine whether to adjust the monitoring period based on the terminal's instruction.

[0285] Step 1504: The network device sends a second request message to the terminal. Correspondingly, the terminal receives the second request message from the network device.

[0286] The second request message is used to request the terminal to report the adjusted cycle for monitoring the performance of the first model.

[0287] As one implementation, when the network device determines to adjust the monitoring cycle based on the terminal's instruction, the network device requests the terminal to report the adjusted monitoring cycle of the first model's performance.

[0288] If the network device determines, based on the terminal's instruction, not to adjust the monitoring cycle, the network device refuses to allow the terminal to report the adjusted monitoring cycle for the first model's performance; or, the network device requests the terminal to report the adjusted monitoring cycle for the first model's performance.

[0289] Step 1505: In response to the second request message, the terminal sends the seventh information to the network device. Correspondingly, the network device receives the seventh information sent by the terminal in response to the second request message.

[0290] In one implementation, the network device receives the seventh information sent by the terminal and determines an adjusted monitoring period for the performance of the first model based on the seventh information. Thereafter, the network device monitors the performance of the first model based on the adjusted monitoring period.

[0291] As another implementation, the network device can also request the current model performance of the first model from the terminal, and calculate and determine an adjusted monitoring period for the first model's performance based on the current model performance. Afterward, the network device monitors the model performance of the first model based on the adjusted monitoring period.

[0292] Based on this, the terminal can report the adjusted monitoring cycle of the first model to the network device based on the network device's request.

[0293] In some embodiments, the terminal can determine a new monitoring period for the first model based on either Method 1 or Method 2: Method 1, the terminal determines the new monitoring period based on a second period mapping table; Method 2, the terminal determines the new monitoring period based on a period threshold condition. These are described in detail below.

[0294] Method 1: The terminal determines the new monitoring cycle based on the second cycle mapping table.

[0295] In some embodiments, the terminal obtains a second period mapping table, which includes a mapping relationship between model performance and monitoring periods. Based on the current model performance of the first model, the terminal queries the second period mapping table to determine the monitoring period corresponding to the current model performance. Afterward, the terminal determines whether the monitoring period corresponding to the current model performance is the same as the current monitoring period of the first model. If they are the same, it means that the current monitoring period is compatible with the current model performance, and no adjustment to the monitoring period is needed. If they are different, it means that the current monitoring period is incompatible with the current model performance, and the monitoring period needs to be adjusted.

[0296] In other words, given the preset conditions, including the fact that the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model, combined with... Figure 15 ,like Figure 16 As shown, the methods for the terminal to determine the new monitoring cycle include:

[0297] Step 1601: The network device sends second configuration information to the terminal. Correspondingly, the terminal receives the second configuration information from the network device.

[0298] The second configuration information is used to configure the second cycle mapping table.

[0299] Step 1602: The terminal determines the monitoring period corresponding to the current performance index of the first model in the second period mapping table, which is the new monitoring period.

[0300] In some embodiments, the terminal determines whether the monitoring period corresponding to the current performance index of the first model in the second period mapping table is the same as the current monitoring period of the first model. If they are different, the terminal determines the monitoring period corresponding to the current performance index of the first model in the second period mapping table as the new monitoring period. After determining the new monitoring period, the terminal can report the new monitoring period to the network device based on the methods described in step 1502 and / or steps 1503-1505 above.

[0301] In method 1, the terminal can directly indicate the specific value of the new monitoring period to the network device, or indicate the index of the new monitoring period in the second period mapping table. In other words, the seventh information includes the specific value of the new monitoring period; or, the seventh information includes the index of the new monitoring period in the second period mapping table.

[0302] As an example, the seventh piece of information includes the specific value of the new monitoring period. The network device monitors the first model based on the specific value of the new monitoring period in the seventh piece of information.

[0303] As another example, the seventh piece of information includes the index of the new monitoring period in the second period mapping table. Based on the index of the new monitoring period in the seventh piece of information, the network device queries the second period mapping table to determine the period length corresponding to that index. Afterward, the network device monitors the first model based on the period length corresponding to that index.

[0304] Optionally, the second period mapping table can be used to characterize the mapping relationship between the model performance error rate and the monitoring period; or, the mapping relationship between the model performance error change rate and the monitoring period. The monitoring period can be a specific period or a period value obtained according to a period calculation formula. The period calculation formula can include, but is not limited to, the product of a preset monitoring period and a preset coefficient, or the ratio of the product of one preset monitoring period and a preset coefficient to another preset period, etc. This application does not limit this. As an example, taking the second period mapping table as a way to characterize the mapping relationship between the model performance error rate and the product of the preset monitoring period and the preset coefficient, the second period mapping table is shown in Table 2 below. This second period mapping table includes four sets of mapping relationships between the model performance error rate and the monitoring period, each set corresponding to an index. The model performance error rate and monitoring period are different in different sets.

[0305] Table 2, Second Period Mapping Table

[0306] Index (Idx) Model performance error rate Monitoring cycle 1 Greater than 50% Period 5 2 Greater than 25% and less than 50% (Period 5 * coefficient 4) / Period 6 3 Greater than 5% and less than 25% (Period 5 * Coefficient 5) / Period 7 4 Less than 5% (Period 5 * Coefficient 6) / Period 8

[0307] The values ​​of period 5, period 6, period 7, period 8, and coefficients 4, 5, and 6 in Table 2 above can be configured according to requirements; the model performance error rate corresponding to each period is provided as an example, and this application does not limit it.

[0308] Based on Table 2 above, when the value of the index configured by the network device to the terminal is 1, the terminal determines the period length for monitoring the performance indicators of the first model to be: the period length of period 5.

[0309] When the index value configured by the network device to the terminal is 2, the terminal determines the period length for monitoring the performance index of the first model as: (period 5 * coefficient 4) / period 6.

[0310] When the value of the index configured by the network device to the terminal is 3, the terminal determines the period length for monitoring the performance index of the first model as: (period 5 * coefficient 5) / period 7.

[0311] When the index value configured by the network device to the terminal is 4, the terminal determines the period length for monitoring the performance index of the first model as: period 5 * coefficient 6) / period 8.

[0312] The second-cycle mapping table can be a mapping table pre-configured by the network device for the terminal, or it can be a mapping table agreed upon through protocols or specifications; this application does not limit this. Optionally, the model performance can specifically be the model performance error rate, the model performance error change rate, etc.; this application does not limit this.

[0313] Method 2: The terminal determines the new monitoring cycle based on the periodic threshold condition.

[0314] In Method 2, the preset conditions include that the monitoring period corresponding to the current performance index of the first model meets the period threshold condition, such as... Figure 16 As shown, in Method 2, the method for the terminal to determine the new monitoring cycle also includes:

[0315] Step 1603: The network device sends third configuration information to the terminal. Correspondingly, the terminal receives the third configuration information from the network device.

[0316] The third configuration information is used to configure periodic threshold conditions.

[0317] As an example, the periodic threshold condition includes: greater than the periodic threshold, or less than or equal to the periodic threshold, where the periodic threshold is N times the second period, and N is an integer greater than or equal to 2; the second period is a monitoring period predetermined by the network device and the terminal. In other words, the network device instructs the terminal to report a new monitoring period to the network device if the new monitoring period is greater than N times the predetermined monitoring period, or less than or equal to N times the predetermined monitoring period. As an example, N is 2.

[0318] Step 1604: The terminal determines a new monitoring cycle based on the third configuration information.

[0319] In some embodiments, the network device configures periodic threshold conditions to the terminal. The terminal obtains the current performance index of the first model and determines the monitoring period corresponding to the current performance index of the first model based on the current performance index of the first model. After that, the terminal determines whether the monitoring period corresponding to the current performance index of the first model meets the periodic threshold conditions. If it does, the terminal determines the monitoring period corresponding to the current performance index of the first model as the new monitoring period. After determining the new monitoring period, the terminal can report the new monitoring period to the network device according to the methods described in step 1502 and / or steps 1503-1505 above.

[0320] Based on method 1 or method 2 described above, the terminal can select a new monitoring period when the performance of the first model fluctuates, achieving the effect of dynamically adjusting the monitoring period. This process can ensure the monitoring effectiveness of the network device in monitoring the first model while reducing signaling interaction between the terminal and the network device.

[0321] In some embodiments, the terminal may report multiple new monitoring cycles to the network device, so that the network device can select a suitable new monitoring cycle from the multiple new monitoring cycles.

[0322] In one possible implementation, after the terminal reports a new monitoring cycle for the first model to the network device, the network device monitors the first model based on the new monitoring cycle and manages the first model based on the monitoring results. The process of the network device managing the first model can refer to step 1102 above, and will not be repeated here.

[0323] The model performance reporting method provided in this application can be applied to various network architectures. The following example illustrates the application of this model performance reporting method to an open RAN architecture.

[0324] When applying this model performance reporting method to an open RAN architecture, it can be specifically applied to a CU (referred to as scenario 4) or a DU (referred to as scenario 5) within the open RAN architecture, as detailed below. In other words, the network device in this embodiment can be a CU or a DU.

[0325] Scenario 4: Apply this model performance reporting method to the CU in an open RAN architecture.

[0326] In scenario 4, the CU manages the models on the terminal, monitors model performance, and performs operations such as model activation and deactivation. For example... Figure 17 As shown, in scenario 4, the model performance reporting method provided in this application embodiment includes:

[0327] Step 1701: The CU sends the measurement configuration and inference configuration of the first model to the DU. Correspondingly, the DU receives the measurement configuration and inference configuration of the first model from the CU.

[0328] As an example, the inference configuration includes at least one of the following: a first-cycle mapping table, a second-cycle mapping table, and a reporting cycle for the performance metrics of the first model reported by the terminal.

[0329] Optionally, the measurement configuration and inference configuration are used to indicate the measurement configuration for set B and the measurement configuration for set A in the beam management scenario when the first model is in an active state; when the first model is in an inactive state, the terminal and DU retain the previously indicated measurement configuration for set B and the measurement configuration for set A.

[0330] The specific details of the above measurement and inference configurations can be found in the description above, and will not be repeated here.

[0331] Step 1702: The DU sends the measurement configuration and inference configuration of the first model to the terminal. Correspondingly, the terminal receives the measurement configuration and inference configuration of the first model from the DU.

[0332] Step 1703: The terminal sends a first reporting message to the DU. Correspondingly, the DU receives the first reporting message from the terminal.

[0333] In one possible implementation, the first reporting message is used to report the performance indicators of the first model, or the monitoring period of the first model, etc. Its specific implementation can be referred to the description in the previous embodiments, and this application does not limit it.

[0334] Step 1704: DU sends the first reporting message to CU. Correspondingly, CU receives the first reporting message from DU.

[0335] Step 1705: Based on the first reported message, the CU performs performance monitoring and / or functional decisions on the first model.

[0336] Step 1706: The CU sends a new inference configuration to the DU. Correspondingly, the DU receives the new inference configuration from the CU.

[0337] Step 1707: The DU sends a new inference configuration to the terminal. Correspondingly, the terminal receives the new inference configuration from the DU.

[0338] Optionally, the above inference configuration is the inference configuration obtained by the CU after performing performance monitoring and / or functional decisions on the first model.

[0339] As one implementation, if the inference configuration of the first model changes, the CU sends the new inference configuration of the first model to the terminal; the CU also sends the corresponding information to the DU so that the DU can determine that the inference configuration of the first model has changed or determine the state of the first model, such as the state of the first model changing from active to inactive, or the state of the first model changing from inactive to active.

[0340] As another implementation, inference configuration is used to instruct the DU to perform corresponding processing after receiving measurement information reported by the terminal. For example, the CU configures the terminal to perform beam management, and the CU monitors the model performance of the first model to determine that the first model can be reactivated; at this time, the CU reconfigures a new inference configuration to instruct the terminal to report the top k beams after inference of the first model to the DU, and the DU performs beam management based on the top k optimal beams reported by the terminal.

[0341] Scenario 5: Apply this model performance reporting method to the DU in an open RAN architecture.

[0342] In scenario 5, the DU manages the models in the terminal, monitors model performance, and performs operations such as model activation and deactivation. The optional CU sends measurement and reporting configurations to the terminal. For example... Figure 18 As shown, in scenario 5, the model performance reporting method provided in this application embodiment includes:

[0343] Step 1801: The DU sends the fourth configuration information to the terminal. Correspondingly, the terminal receives the fourth configuration information from the DU.

[0344] The fourth configuration information is used to configure at least one of the following: a first periodic mapping table, a second periodic mapping table, and the reporting period for the performance metrics of the first model reported by the terminal.

[0345] Step 1802: The CU sends the measurement configuration and inference configuration of the first model to the DU. Correspondingly, the DU receives the measurement configuration and inference configuration of the first model from the CU.

[0346] In some embodiments, the CU determines the measurement configuration and inference configuration of the terminal, and instructs the measurement configuration and inference configuration to the DU and the terminal, respectively. For example, the measurement configuration of set B and the measurement configuration of set A in a beam management scenario when the model is active. When the model is deactivated, the terminal and the DU retain the measurement configuration of set B when the model is active, as issued by the CU. The CU determines the measurement configuration of set A in non-AI / ML scenarios, as well as the inference cycle of set B when it is active and the inference cycle of set B stored after deactivation.

[0347] Step 1803: The DU sends the measurement configuration and inference configuration of the first model to the terminal. Correspondingly, the terminal receives the measurement configuration and inference configuration of the first model from the DU.

[0348] Step 1804: The terminal sends a second reporting message to the DU. Correspondingly, the DU receives the second reporting message from the terminal.

[0349] In one possible implementation, the first reporting message is used to report the performance indicators of the first model, or the monitoring period of the first model, etc. Its specific implementation can be referred to the description in the previous embodiments, and this application does not limit it.

[0350] Step 1805: DU performs performance monitoring and functional decisions on the first model based on the messages reported by the terminal.

[0351] Step 1806: The CU sends a new inference configuration to the DU. Correspondingly, the DU receives the new inference configuration from the CU.

[0352] Step 1807: The DU sends a new inference configuration to the terminal. Correspondingly, the terminal receives the new inference configuration from the DU.

[0353] Optionally, the above inference configuration is a configuration that the DU reports to the CU after performing performance monitoring and / or functional decisions on the first model, and the CU determines the inference configuration based on the performance monitoring results and / or functional decision results of the first model.

[0354] The model in the embodiments of this application can be understood as an AI model, or an ML model, or an AI function, or an ML function, and this application does not limit it in this way.

[0355] The above mainly describes the solutions provided by the embodiments of this application from the perspective of interaction between network elements. Correspondingly, the embodiments of this application also provide a communication device for implementing the various methods described above. The communication device can be a terminal in the above method embodiments, or a device containing the terminal, or a component usable in a terminal; the communication device can be a network device in the above method embodiments, or a device containing the network device, or a component usable in a network device; or, the communication device can be a terminal in the above method embodiments, or a device containing the terminal, or a component usable in a terminal. It is understood that, in order to achieve the above functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0356] This application embodiment can divide the communication device into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be understood that the module division in this application embodiment is illustrative and is only a logical functional division. In actual implementation, there may be other division methods.

[0357] for example, Figure 19 This is a schematic diagram of a communication device 1900 provided in an embodiment of this application. The communication device 1900 includes a transceiver module 1910. Optionally, it includes a processing module 1920. The transceiver module 1910, also known as a transceiver unit, is used to implement transceiver functions, and may be, for example, a transceiver circuit, transceiver, transceiver device, or communication interface.

[0358] Taking the communication device 1900 as a terminal in the above method embodiment, or a device containing the above terminal, or a component that can be used in the terminal as an example, then: the transceiver module 1910 is used to acquire first information, the first information being used to indicate the performance index of the first model deactivated in the terminal; the transceiver module 1910 is also used to send the first information to the network device.

[0359] In one possible implementation, the transceiver module 1910 is further configured to receive second information from the network device; the second information is configured to instruct the terminal to report the performance metrics of the deactivated model when the model state is in a deactivated state.

[0360] In one possible implementation, the transceiver module 1910 is also used to send first information to the network device in a first cycle.

[0361] In one possible implementation, the transceiver module 1910 is further configured to receive first configuration information from the network device; wherein the first configuration information is used to configure the period of the performance indicators of the reporting model, and the period of the performance indicators of the reporting model includes the first period.

[0362] In one possible implementation, the first configuration information includes the specific value of the first period; or, the first configuration information includes the index of the first period in the first period mapping table; wherein, the first period mapping table includes the mapping relationship between model performance and the period of reporting model performance indicators.

[0363] In one possible implementation, the processing module 1920 is used to instruct the transceiver module 1910 to send first information to the network device when the performance index of the first model meets the first preset threshold.

[0364] In one possible implementation, the transceiver module 1910 is further configured to receive fourth information from the network device; wherein the fourth information is used to indicate a first preset threshold.

[0365] In one possible implementation, the transceiver module 1910 is further configured to receive a first request message from the network device; the processing module 1920 is further configured to respond to the first request message and instruct the transceiver module 1910 to send first information to the network device; wherein the first request message is used to request the reporting of performance indicators of the first model.

[0366] In one possible implementation, the processing module 1920 is further configured to instruct the transceiver module 1910 to send fifth information to the network device when the performance index of the first model meets the first preset threshold; wherein the fifth information is used to indicate that the performance index of the first model meets the first preset threshold.

[0367] In one possible implementation, the transceiver module 1910 is further configured to receive sixth information from the network device; the sixth information is used to indicate management operations on the first model; the management operations include at least one of the following: activating the first model, maintaining the deactivated state of the first model, and sending inference configuration information.

[0368] In one possible implementation, the processing module 1920 is further configured to determine that the monitoring period of the first model needs to be adjusted in response to the monitoring period corresponding to the current performance index of the first model meeting a preset condition; wherein, the monitoring period is the period during which the network device and / or terminal periodically monitor the model performance of the first model; the preset condition includes: the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model; or, the monitoring period corresponding to the current performance index of the first model meets the period threshold condition; the transceiver module 1910 is further configured to send a seventh message to the network device; the seventh message is used by the network device to determine the new monitoring period.

[0369] In one possible implementation, the transceiver module 1910 is further configured to send an eighth message to the network device; the eighth message is used to indicate the current monitoring cycle that needs to be adjusted; the transceiver module 1910 is further configured to receive a second request message from the network device; wherein the second request message is used to request the terminal to report the adjusted monitoring cycle of the first model's performance; the transceiver module 1910 is further configured to send a seventh message to the network device in response to the second request message.

[0370] In one possible implementation, if the preset conditions include that the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model, the transceiver module 1910 is further configured to receive second configuration information from the network device; the second configuration information is used to configure a second period mapping table; the second period mapping table includes the mapping relationship between model performance and monitoring period; the processing module 1920 is further configured to determine the monitoring period corresponding to the current performance index of the first model in the second period mapping table as a new monitoring period.

[0371] In one possible implementation, the seventh information includes the specific value of the new monitoring period; or, the seventh information includes the index of the new monitoring period in the second period mapping table.

[0372] In one possible implementation, if the monitoring period corresponding to the current performance index of the first model meets the period threshold condition under the preset conditions, the transceiver module 1910 is further configured to receive third configuration information from the network device; the third configuration information is used to configure the period threshold condition.

[0373] In one possible implementation, the network device is a centralized unit (CU), or the network device is a distributed unit (DU).

[0374] Taking the communication device 1900 as a network device in the above method embodiment, or a device containing the above network device, or a component that can be used in a network device as an example, then: the transceiver module 1910 is used to receive first information from the terminal, the first information being used to indicate the performance index of the first model that is deactivated in the terminal.

[0375] In one possible implementation, the transceiver module 1910 is used to send second information to the terminal; the second information is used to instruct the terminal to report the performance indicators of the deactivated model when the model state is in the deactivated state.

[0376] In one possible implementation, the first information is sent by the terminal in a first cycle.

[0377] In one possible implementation, the transceiver module 1910 is used to send first configuration information to the terminal; wherein the first configuration information is used to configure the period of the performance indicators of the reporting model, and the period of the performance indicators of the reporting model includes the first period.

[0378] In one possible implementation, the first configuration information includes the specific value of the first period; or, the first configuration information includes the index of the first period in the first period mapping table; wherein, the first period mapping table includes the mapping relationship between model performance and the period of reporting model performance indicators.

[0379] In one possible implementation, the first information is sent by the terminal to the network device when the performance index of the first model meets a first preset threshold.

[0380] In one possible implementation, the transceiver module 1910 is used to send fourth information to the terminal; wherein the fourth information is used to indicate a first preset threshold.

[0381] In one possible implementation, the transceiver module 1910 is used to send a first request message to the terminal; the transceiver module 1910 is used to receive first information sent by the terminal in response to the first request message; wherein, the first request message is used to request the reporting of performance indicators of the first model.

[0382] In one possible implementation, the transceiver module 1910 is used to receive fifth information from the terminal; wherein the fifth information is used to indicate that the performance index of the first model meets the first preset threshold.

[0383] In one possible implementation, the transceiver module 1910 is used to send a sixth message to the terminal; the sixth message is used to indicate a management operation on the first model; the management operation includes at least one of the following: activating the first model, keeping the first model in a deactivated state, and sending inference configuration information.

[0384] In one possible implementation, the transceiver module 1910 is used to receive seventh information from the terminal; the seventh information is used by the network device to determine a new monitoring period; wherein, the seventh information is sent by the terminal when the monitoring period corresponding to the current performance index of the first model meets preset conditions; the monitoring period is the period during which the network device and / or the terminal periodically monitors the model performance of the first model; the preset conditions include: the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model; or, the monitoring period corresponding to the current performance index of the first model meets the period threshold condition.

[0385] In one possible implementation, the transceiver module 1910 is used to receive eighth information from the terminal; the eighth information is used to indicate the current monitoring cycle that needs to be adjusted; and to send a second request message to the terminal; wherein the second request message is used to request the terminal to report the adjusted monitoring cycle of the first model's performance; the transceiver module 1910 is used to receive seventh information sent by the terminal in response to the second request message.

[0386] In one possible implementation, when the preset conditions include the fact that the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model, the transceiver module 1910 is used to send second configuration information to the terminal; the second configuration information is used to configure the second period mapping table; the second period mapping table includes the mapping relationship between model performance and monitoring period.

[0387] In one possible implementation, the seventh information includes the specific value of the new monitoring period; or, the seventh information includes the index of the new monitoring period in the second period mapping table.

[0388] In one possible implementation, if the monitoring period corresponding to the current performance index of the first model meets the period threshold condition under the preset conditions, the transceiver module 1910 is used to send third configuration information to the terminal; the third configuration information is used to configure the period threshold condition.

[0389] In one possible implementation, the network device is a centralized unit (CU), or the network device is a distributed unit (DU).

[0390] All relevant content of each step involved in the above method embodiments can be referred to in the functional description of the corresponding functional module, and will not be repeated here. Optionally, the communication device 1900 may further include a storage module 1930, which can be used to store instructions and / or data, and the processing module 1920 can read the instructions and / or data in the storage module 1930.

[0391] In this embodiment, the communication device 1900 is presented in an integrated manner, divided into various functional modules. Here, "module" can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory executing one or more software or firmware programs, integrated logic circuits, and / or other devices that can provide the aforementioned functions. In a simple embodiment, those skilled in the art will understand that the communication device can employ... Figure 9 The communication device shown is in the form of 900.

[0392] Specifically, Figure 19 The functions / implementation process of the transceiver module 1910 and the processing module 1920 can be obtained through... Figure 9 The processor 91 in the communication device 900 shown calls computer execution instructions stored in the memory 92 to implement the function. Alternatively, Figure 19 The function / implementation process of the processing module 1920 in the middle can be obtained through Figure 9 The processor 91 in the communication device 900 shown calls computer execution instructions stored in the memory 92 to implement the communication. Figure 19 The function / implementation process of the transceiver module 1910 in the middle can be obtained through Figure 9 This is achieved through the transceiver 95 in the communication device 900 shown.

[0393] Since the communication device provided in this application embodiment can execute the above-described model performance reporting method, the technical effects it can achieve can be referred to the above-described method embodiment, and will not be repeated here.

[0394] It should be understood that one or more of the above modules or units can be implemented by software, hardware, or a combination of both. When any of the above modules or units are implemented by software, the software exists as computer program instructions and is stored in memory. The processor can be used to execute the program instructions and implement the above method flow. The processor can be built into a SoC (System-on-a-Chip) or ASIC, or it can be a separate semiconductor chip. In addition to the core that executes software instructions for computation or processing, the processor may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), or logic circuits that implement dedicated logic operations.

[0395] When the above modules or units are implemented in hardware, the hardware can be any one or any combination of a central processing unit (CPU), microprocessor, digital signal processing (DSP) chip, microcontroller unit (MCU), artificial intelligence processor, ASIC, SoC, FPGA, PLD, application-specific digital circuit, hardware accelerator, or non-integrated discrete device, which can run the necessary software or perform the above method flow independently of software.

[0396] Optionally, embodiments of this application also provide a communication device (e.g., the communication device may be a chip or a chip system), which includes a processor for implementing the methods in any of the above method embodiments. In one possible design, the communication device further includes a memory. The memory is used to store necessary program instructions and data, and the processor can call the program code stored in the memory to instruct the communication device to execute the methods in any of the above method embodiments. Of course, the memory may not be included in the communication device. When the communication device is a chip system, it may be composed of chips or may include chips and other discrete devices; embodiments of this application do not specifically limit this.

[0397] Optionally, embodiments of this application also provide a computer-readable storage medium storing a computer program or instructions that, when run on a communication device, enable the communication device to execute the methods described in any of the above method embodiments or any implementation thereof.

[0398] Optionally, embodiments of this application also provide a communication system, which includes the network device and the terminal described in the above method embodiments.

[0399] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. 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, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs).

[0400] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, the disclosure, and the appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0401] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of the application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Thus, if such modifications and modifications fall within the scope of the claims and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A method for reporting model performance, characterized in that, include: Obtain first information, which is used to indicate the performance metrics of the first model that is deactivated in the terminal; Send the first information to the network device.

2. The method according to claim 1, characterized in that, Before sending the first information to the network device, the method further includes: The terminal receives second information from the network device; the second information is used to instruct the terminal to report the performance indicators of the deactivated model when the model state is in a deactivated state.

3. The method according to claim 1 or 2, characterized in that, Sending the first information to the network device includes: The first information is sent to the network device in a first cycle.

4. The method according to claim 3, characterized in that, Before sending the first information to the network device, the method further includes: The system receives first configuration information from the network device; wherein the first configuration information is used to configure the period of the performance indicators of the reporting model, and the period of the performance indicators of the reporting model includes the first period.

5. The method according to claim 4, characterized in that, The first configuration information includes the specific value of the first period; or, The first configuration information includes the index of the first period in the first period mapping table; wherein, the first period mapping table includes the mapping relationship between model performance and the period for reporting model performance indicators.

6. The method according to claim 1 or 2, characterized in that, Sending the first information to the network device includes: When the performance index of the first model meets the first preset threshold, the first information is sent to the network device.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: The network device receives a sixth message; the sixth message is used to indicate a management operation for the first model; the management operation includes at least one of the following: activating the first model, maintaining the first model in a deactivated state, and issuing inference configuration information.

8. The method according to any one of claims 1-7, characterized in that, The method further includes: In response to the fact that the monitoring period corresponding to the current performance index of the first model meets a preset condition, it is determined that the monitoring period of the first model needs to be adjusted; wherein, the monitoring period is the period during which the network device and / or the terminal periodically monitors the model performance of the first model; the preset condition includes: the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model; or, the monitoring period corresponding to the current performance index of the first model meets a period threshold condition. A seventh message is sent to the network device; the seventh message is used by the network device to determine a new monitoring cycle.

9. The method according to claim 8, characterized in that, When the preset conditions include the fact that the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model, the method further includes: The system receives second configuration information from the network device; the second configuration information is used to configure a second periodic mapping table; the second periodic mapping table includes a mapping relationship between model performance and monitoring period. The monitoring period corresponding to the current performance index of the first model in the second period mapping table is determined as the new monitoring period.

10. The method according to claim 9, characterized in that, The seventh piece of information includes the specific value of the new monitoring cycle; or, The seventh piece of information includes the index of the new monitoring period in the second period mapping table.

11. The method according to claim 8, characterized in that, When the preset conditions include the monitoring period corresponding to the current performance parameters of the first model meeting the period threshold condition, the method further includes: Receive third configuration information from the network device; the third configuration information is used to configure the periodic threshold condition.

12. The method according to any one of claims 1-11, characterized in that, The network device is a centralized unit (CU), or... The network device is a distribution unit (DU).

13. A method for reporting model performance, characterized in that, include: Receive first information from the terminal, the first information being used to indicate the performance metrics of the first model that is deactivated in the terminal.

14. The method according to claim 13, characterized in that, Before receiving the first information, the method further includes: Send a second message to the terminal; the second message is used to instruct the terminal to report the performance indicators of the deactivated model when the model state is in a deactivated state.

15. The method according to claim 13 or 14, characterized in that, The first information is sent by the terminal in a first cycle.

16. The method according to claim 15, characterized in that, Before receiving the first information from the terminal, the method further includes: Send first configuration information to the terminal; wherein the first configuration information is used to configure the period of the performance indicators of the reporting model, and the period of the performance indicators of the reporting model includes the first period.

17. The method according to claim 16, characterized in that, The first configuration information includes the specific value of the first period; or, The first configuration information includes the index of the first period in the first period mapping table; wherein, the first period mapping table includes the mapping relationship between model performance and the period for reporting model performance indicators.

18. The method according to claim 13 or 14, characterized in that, The first information is sent by the terminal to the network device when the performance index of the first model meets the first preset threshold.

19. The method according to any one of claims 13-18, characterized in that, The method further includes: A sixth message is sent to the terminal; the sixth message is used to indicate a management operation for the first model; the management operation includes at least one of the following: activating the first model, keeping the first model in an inactive state, and sending inference configuration information.

20. The method according to any one of claims 13-19, characterized in that, The method further includes: The network device receives a seventh message from the terminal; the seventh message is used to determine a new monitoring period; wherein the seventh message is sent by the terminal when the monitoring period corresponding to the current performance index of the first model meets a preset condition; the monitoring period is the period during which the network device and / or the terminal periodically monitors the model performance of the first model; the preset condition includes: the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model; or, the monitoring period corresponding to the current performance index of the first model meets a period threshold condition.

21. The method according to claim 20, characterized in that, When the preset conditions include the fact that the monitoring period corresponding to the current performance index of the first model is different from the current monitoring period of the first model, the method further includes: Send second configuration information to the terminal; the second configuration information is used to configure a second period mapping table; the second period mapping table includes the mapping relationship between model performance and monitoring period.

22. The method according to claim 21, characterized in that, The seventh piece of information includes the specific value of the new monitoring cycle; or, The seventh piece of information includes the index of the new monitoring period in the second period mapping table.

23. The method according to claim 20, characterized in that, When the preset conditions include the monitoring period corresponding to the current performance index of the first model meeting the period threshold condition, the method further includes: Send third configuration information to the terminal; the third configuration information is used to configure the periodic threshold condition.

24. The method according to any one of claims 13-23, characterized in that, The network device is a centralized unit (CU), or... The network device is a distributed unit (DU).

25. A communication device, characterized in that, include: A functional unit for performing the method as described in any one of claims 1-24; wherein the action performed by the functional unit is implemented by hardware or by hardware executing corresponding software.

26. A communication device, characterized in that, include: processor; The processor is connected to a memory for storing computer execution instructions, and the processor executes the computer execution instructions stored in the memory to enable the communication device to implement the method as described in any one of claims 1-24.

27. A computer-readable storage medium, characterized in that, Includes instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-24.

28. A chip, characterized in that, The chip includes a processor; the processor is connected to a memory for storing computer execution instructions, and the processor executes the computer execution instructions stored in the memory to enable the communication device to implement the method as described in any one of claims 1-24.

29. A computer program product containing instructions, characterized in that, When it is operated on a communication device, it causes the communication device to perform the method as described in any one of claims 1-24.

Images