Model monitoring and management methods, devices, storage media and related systems

Abstract

This application discloses a model monitoring and management method, apparatus, storage medium, and related system, belonging to the field of communication technology. The method includes: during the monitoring of an AI model, a terminal device determines whether a first condition is met. The first condition includes the terminal device being in a low-mobility state and a high-beam quality state. If the first condition is met, it indicates that the terminal device is in a stable beam transmission and reception state, and then enters a target state to refrain from model monitoring or reduce the model monitoring frequency for a preset time period, thereby relaxing the monitoring of the AI ​​model. In this application, the terminal device can flexibly control the monitoring of the AI ​​model according to the beam transmission and reception environment, thereby optimizing the resource utilization of the terminal device to a certain extent.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a model monitoring and management method, apparatus, storage medium and related system. Background Technology

[0002] In wireless communication systems, artificial intelligence (AI) models can be used to enhance system performance. AI-based beam management can include a decision-making support mechanism based on AI models at the terminal side. This mechanism can incorporate model inference and model monitoring functions in the terminal device. The information generated by these functions can be reported to the network device via model inference reports and model monitoring reports. Summary of the Invention

[0003] This application provides a model monitoring and management method, apparatus, storage medium, and related system, which can optimize resource utilization of terminal devices. The technical solution is as follows:

[0004] Firstly, a model monitoring and management method is provided. This method can be executed by a terminal device, or by a component (such as a circuit, chip, or chip system) configured in the terminal device, or by a logic module or software capable of implementing all or part of the functions of the terminal device. This application does not limit the scope of this method. The following description uses a terminal device as an example.

[0005] In this method, the terminal device monitors an AI model used for beam management. The terminal device enters a target state when a first condition is met, including the terminal device being in a low-mobility state and a high-beam quality state. In the target state, model monitoring is not performed for a preset duration, or the model monitoring frequency is reduced.

[0006] In this application, during the monitoring of the AI ​​model, the terminal device can determine whether a first condition is met. If the first condition is met, it indicates that the terminal device is in a stable beam transceiver state, and it can then enter the target state to relax the monitoring of the AI ​​model. In this way, the terminal device can flexibly control the monitoring of the AI ​​model according to the beam transceiver environment, thereby optimizing the resource utilization of the terminal device to a certain extent.

[0007] In one possible implementation, if the difference between the reference received signal strength and the received signal strength of the serving cell is less than a first threshold, the terminal device determines that it is in a low mobility state; if the difference between the reference received signal strength and the received signal strength of the serving cell is greater than or equal to the first threshold, the terminal device determines that it is not in a low mobility state.

[0008] If the difference between the reference received signal strength and the serving cell's received signal strength is less than the first threshold, it means the current received signal is weaker than the reference point, but the weakness is within an acceptable tolerance range. This indicates that the terminal device has not moved significantly over long distances and is still near the reference point; therefore, the terminal device is determined to be in a low mobility state. If the difference between the reference received signal strength and the serving cell's received signal strength is greater than or equal to the first threshold, it means the current received signal is much weaker than the reference point, exceeding the acceptable tolerance range. This indicates that the terminal device may have moved to a more distant location with even weaker received signals; therefore, the terminal device is determined not to be in a low mobility state.

[0009] In one possible implementation, the terminal device determines that it is in a high beam quality state if the signal quality of the beam currently used by the terminal device is greater than a second threshold; and determines that it is not in a high beam quality state if the signal quality of the beam currently used by the terminal device is less than or equal to the second threshold.

[0010] If the signal quality of the beam currently used by the terminal device is greater than the second threshold, it means that the signal quality of the beam currently used by the terminal device is good, and therefore the terminal device is determined to be in a high beam quality state. If the signal quality of the beam currently used by the terminal device is less than or equal to the second threshold, it means that the signal quality of the beam currently used by the terminal device is poor, and therefore the terminal device is determined not to be in a high beam quality state.

[0011] In one possible implementation, the signal quality of the beam is the L1-RSRP of the beam.

[0012] L1-RSRP is the most important, fundamental, and direct beam quality information in beam management. BAI, as a key metric for quantitatively evaluating AI model performance, is implicitly calculated based on L1-RSRP. L1-RSRP is a real-time, unfiltered measurement from the physical layer, making it faster and more raw, and a reference for beam management and BAI calculation. Therefore, using L1-RSRP as a parameter to measure beam quality is very appropriate.

[0013] In one possible implementation, the first condition also includes that the terminal device is not located in the edge area of ​​the serving cell.

[0014] When the terminal device is in a low-mobility and high-beam-quality state, and is not located in the edge area of ​​the serving cell, its downlink reception conditions are good and the channel quality is stable, thus the beam measured and used by the terminal device is stable. Under these conditions, the channel time-varying nature is low, its predictability is high, and interference and noise have little impact on the accuracy of beam prediction. Therefore, the monitoring intensity of the AI ​​model can be appropriately reduced to optimize resource utilization.

[0015] In one possible implementation, if the received signal strength of the serving cell is greater than a third threshold, and / or if the received signal quality of the serving cell is greater than a fourth threshold, then the terminal device determines that the terminal device is not located in the edge region of the serving cell; otherwise, it determines that the terminal device is located in the edge region of the serving cell.

[0016] If the received signal strength of the serving cell is greater than the third threshold, and / or if the received signal quality of the serving cell is greater than the fourth threshold, it means that the terminal device has a good received signal, indicating that the terminal device is likely located in the central area of ​​the serving cell. Otherwise, it means that the terminal device has a poor received signal, indicating that the terminal device is likely located in the edge area of ​​the serving cell.

[0017] In one possible implementation, the terminal device may enter the target state when the first condition is met by: sending a relaxation monitoring request to the network device when the first condition is met; and entering the target state when receiving the first instruction information sent by the network device.

[0018] In this application, during the monitoring of the AI ​​model, the terminal device can determine whether a first condition is met. If the first condition is met, it indicates that the terminal device is in a stable beam transceiver state, and it can then request to enter the target state from the network device. After receiving the first indication information sent by the network device, the terminal device can enter the target state to relax its monitoring of the AI ​​model. In this way, the terminal device and the network device can flexibly control the monitoring of the AI ​​model according to the beam transceiver environment, thereby optimizing the resource utilization of the terminal device to a certain extent.

[0019] In one possible implementation, after the terminal device sends a relaxation monitoring request to the network device, it may, upon receiving a second instruction from the network device, not enter the target state and continue to determine whether the first condition is met; or, upon receiving a third instruction from the network device, it may not enter the target state and may not determine whether the first condition is met within a second time period.

[0020] In one possible implementation, after the terminal device enters the target state, it can also determine whether the second condition is met while in the target state. The second condition includes that the terminal device is not in a high beam quality state; if the second condition is met, it exits the target state.

[0021] In this application, when the terminal device is in the target state, it can determine whether the second condition is met. If the second condition is met, it indicates that the beam transceiver state is unstable, and the terminal device can exit the target state to resume normal monitoring of the AI ​​model. In this way, the terminal device can flexibly control the monitoring of the AI ​​model according to the beam transceiver environment, thereby optimizing the resource utilization of the terminal device to a certain extent.

[0022] Secondly, a communication device is provided, comprising a processing module and a communication module. The processing module is used to monitor an AI model used for beam management; and, under certain conditions, enters a target state, the first condition including the terminal device being in a low mobility state and a high beam quality state, wherein model monitoring is not performed for a preset duration in the target state, or the model monitoring frequency is reduced in the target state.

[0023] The second aspect is the implementation on the device side, which corresponds to the first aspect. The explanations, supplements, and descriptions of the beneficial effects of the first aspect also apply to the second aspect, and will not be repeated here.

[0024] Thirdly, a communication device is provided, including a processor. The processor is coupled to a memory and can be used to execute instructions or data in the memory to implement the methods in any possible implementation of any of the above aspects. Optionally, the communication device further includes a memory. Optionally, the communication device further includes a communication interface, and the processor is coupled to the communication interface.

[0025] In one implementation, the communication interface can be a transceiver, or an input / output interface.

[0026] In another implementation, the communication device is a chip configured in the terminal device. When the communication device is a chip configured in the terminal device, the communication interface can be an input / output interface.

[0027] Fourthly, a computer program product is provided, comprising: a computer program (also referred to as code or instructions) that, when run, causes a computer to perform the method in any possible implementation of any of the above aspects.

[0028] Fifthly, a computer-readable storage medium is provided that stores a computer program (also referred to as code or instructions) that, when run on a computer, causes the computer to perform the methods in any possible implementation of any of the above aspects.

[0029] Sixthly, embodiments of this application provide a chip system including one or more processors for calling and executing instructions stored in memory, causing the methods in any of the possible implementations of the above aspects to be executed. The chip system may be composed of chips or may include chips and other discrete devices.

[0030] The chip system may include input circuits or interfaces for transmitting information or data, and output circuits or interfaces for receiving information or data.

[0031] In a seventh aspect, a communication system is provided, including the aforementioned terminal device. Optionally, the communication system may further include other devices that communicate with the terminal device. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of a communication system provided in an embodiment of this application;

[0033] Figure 2 This is a flowchart of a model monitoring and management method provided in an embodiment of this application;

[0034] Figure 3 This is a flowchart of another model monitoring and management method provided in the embodiments of this application;

[0035] Figure 4 This is a flowchart of another model monitoring and management method provided in the embodiments of this application;

[0036] Figure 5 This is a flowchart of another model monitoring and management method provided in the embodiments of this application;

[0037] Figure 6 This is a schematic block diagram of a communication device provided in an embodiment of this application.

[0038] Figure 7 This is a schematic block diagram of another communication device provided in the embodiments of this application. Detailed Implementation

[0039] In the following description, specific details such as particular system architectures and technologies are set forth for illustrative purposes and not for limiting purposes, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details.

[0040] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0041] It should be understood that "one or more" as used in this application refers to one, two, or more, and "multiple" as used in this application refers to two or more. In the description of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone.

[0042] To facilitate a clear description of the technical solutions of this application, the terms "first" and "second" are used to distinguish identical or similar items with essentially 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 that the terms "first" and "second" do not necessarily imply that they are different.

[0043] The terms "one embodiment" or "some embodiments" used in this application mean that one or more embodiments of this application include the specific features, structures, or characteristics described in that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in other embodiments," etc., appearing in different parts of this application do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0044] The embodiments of this application can be applied to various communication systems. For example, Global System for Mobile Communications (GSM) systems, General Packet Radio Service (GPRS) systems, Wireless Local Area Network (WLAN) systems (such as Wireless Fidelity (Wi-Fi) systems), Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, sidelink communication systems, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication systems, non-terrestrial network (NTN) communication systems, fourth-generation (4G) mobile communication systems, fifth-generation (5G) mobile communication systems, new radio access technology (NR) systems, and sixth-generation (6G) mobile communication systems. The 5G mobile communication system may include non-standalone (NSA) and / or standalone (SA) networking. It is understood that the embodiments of this application can also be applied to future communication systems, and the embodiments of this application do not limit this application.

[0045] Figure 1 This is a schematic diagram of a communication system 100 provided in an embodiment of this application. The communication system 100 may include network (NW) devices, such as... Figure 1 The network device 110 shown. The communication system 100 may also include terminal devices, such as... Figure 1 The terminal device 120 shown can communicate with the network device via a wireless link. Figure 1 An exemplary network device 110 and a terminal device 120 are shown. Optionally, the communication system 100 may also include multiple network devices and / or multiple terminal devices.

[0046] The network device in this application embodiment can be a network-side device such as an access network device or a core network device.

[0047] Access network equipment is sometimes also called access node. Access network equipment has wireless transceiver capabilities and can communicate with terminal equipment. For example, access network equipment can be a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), next-generation radio access network (NG-RAN) equipment (such as a next-generation NodeB (gNB)) in a 5G mobile communication system, access network equipment or modules of access network equipment in an open RAN (ORAN) system, satellites in an NTN communication system, base stations in a future mobile communication system, or access points (APs) in a Wi-Fi system. Access network equipment can also be modules or units capable of implementing some of the functions of a base station, such as macro base stations, micro base stations, indoor stations, relay nodes, or donor nodes. Multiple access network devices in the communication system 100 can be of the same type or different types. This application does not limit the specific technology or device form used in the access network equipment.

[0048] Core network equipment possesses functions such as data processing, session management, network interconnection, operation administration and maintenance (OAM), and location management function (LMF). Core network equipment can perform user access authentication, service bearer establishment, and data interaction with external networks. Through OAM, it completes network configuration monitoring, resource scheduling optimization, and fault maintenance tasks. Through LMF, it provides terminal location calculation, trajectory tracking, and spatial data analysis. For example, core network equipment can be network elements such as the mobility management entity (MME), serving gateway (SGW), and packet data network gateway (PGW) in a 4G mobile communication system. Alternatively, core network equipment can be network elements such as the access and mobility management function (AMF), session management function (SMF), user plane function (UPF), and LMF in a 5G mobile communication system. Or, core network equipment can be a functional entity specifically providing operation and maintenance services or location services, such as an independent server closely cooperating with the core network. Alternatively, the core network equipment can be a virtualized network element integrating OAM or LMF capabilities within a Network Functions Virtualization (NFV) architecture. The core network equipment can also be a novel core network entity in future communication systems. Multiple core network equipment in communication system 100 can be deployed in a centralized or distributed architecture, with each core network equipment undertaking the same or different types of network functions. This application does not limit the specific technologies or equipment forms used in the core network equipment.

[0049] In this application embodiment, the apparatus for implementing the functions of a network device can be a network device itself, or an apparatus capable of supporting the network device in implementing those functions, such as a processor, circuit, chip, or chip system. This apparatus can be installed in the network device or connected to and used with the network device. In this application embodiment, taking a network device as an example to illustrate the technical solution provided by this application, we will describe it accordingly.

[0050] The terminal device in this application embodiment can be a wireless terminal device capable of receiving network device scheduling and instructions. The wireless terminal device can be a device providing voice and / or data connectivity to a user, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem. For example, the terminal device can communicate with one or more core networks or the Internet via a radio access network (RAN). The terminal device can also be referred to as a terminal, user equipment (UE), mobile terminal (MT), mobile station (MS), mobile unit (MU), radio unit, remote unit, user agent, mobile client, etc. Terminal devices can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), ultra-reliable low-latency communication (URLLC), virtual reality (VR), augmented reality (AR), industrial control, self-driving, remote medical surgery, smart grid, intelligent transportation, smart homes, smart cities, or satellite communication. Terminal devices can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, aircraft (such as drones, helicopters, and airplanes), hot air balloons, ships, robots, robotic arms, or smart home devices. This application does not limit the form of the terminal device.

[0051] In this application embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or any device capable of supporting the terminal device in implementing the functions, such as a processor, circuit, chip, or chip system. This device can be installed in the terminal device or connected to and used with the terminal device. In this application embodiment, taking the terminal device as an example to illustrate the technical solution provided by this application, we will describe it accordingly.

[0052] To facilitate understanding of the embodiments of this application, the technical terms involved in the embodiments of this application will be briefly explained first. Optionally, the explanation of some terms can also refer to the explanation in the 3rd Generation Partnership Project (3GPP) standard protocol.

[0053] 1. Beam

[0054] A beam is a directional energy radiation pattern formed when electromagnetic waves propagate in space. Its energy is concentrated in the target direction, with energy attenuation in non-target directions. The beam described in the embodiments of this application can also be referred to as a beam direction; the two terms can be used interchangeably.

[0055] 2. Beamforming

[0056] Beamforming is a technique that dynamically constructs and tracks the optimal beam pattern by optimizing the amplitude weighting, phase offset, and time delay compensation parameters of a multi-antenna array. Its core objective is to achieve coherent signal superposition in the target direction and energy destructive cancellation in the interference direction, thereby overcoming path loss and improving spatial multiplexing capabilities.

[0057] Beamforming relies on decision-making information provided by beam management (BM). During beam management, network devices can transmit reference signals in multiple candidate beam directions. Terminal devices can measure the signal quality of each reference signal and feed it back to the network devices. The network devices can then switch beams based on this feedback.

[0058] It should be noted that one reference signal corresponds to one beam. That is, if a reference signal is transmitted in a certain beam direction, then that reference signal corresponds to the beam identifier in that beam direction. For example, the beam identifier can be a beam index or a channel state information-reference signal resource indicator (CRI), etc., and this application embodiment does not limit this.

[0059] The signal quality of the reference signal described in the embodiments of this application can also be referred to as the signal quality of the beam corresponding to the reference signal. In other words, the signal quality of a certain beam refers to the signal quality of the reference signal transmitted through that beam.

[0060] 3. Reference signal (RS)

[0061] A reference signal is a known signal used in a communication system for channel estimation or channel sounding. Its core function is to provide channel state information to the receiver, assisting in efficient resource scheduling and data transmission.

[0062] Optionally, the reference signal described in the embodiments of this application may include a channel state information-reference signal (CSI-RS), a synchronization signal / physical broadcast channel block (SSB) reference signal, etc., and the embodiments of this application do not limit this.

[0063] It should be understood that the technical terminology used in the embodiments of this application is for illustrative purposes only and not as a limitation. As technology evolves, technical terminology may also change; however, other technical terms with the same technical meaning should also be applicable to the embodiments of this application.

[0064] The application scenarios involved in the embodiments of this application are described below.

[0065] Beam management involves selecting, maintaining, and optimizing directional beams between network devices and terminal devices to ensure reliable and high-quality communication. Its goal is to establish and maintain suitable beam pairs, i.e., selecting appropriate transmit beams at the transmitting end and appropriate receive beams at the receiving end. Embodiments of this application relate to AI-based (also known as machine learning, ML) beam management.

[0066] AI-based beam management can include a decision-making support mechanism based on AI models at the terminal side. This mechanism can incorporate model inference and model monitoring functions on the terminal device. The information generated by these functions can be reported to the network device via model inference reports and model monitoring reports. Model inference refers to using a trained AI model to obtain predicted signal quality values ​​for a specific beam set. Model monitoring involves comparing the AI ​​model's predictions with actual measurements to obtain performance metrics (such as prediction error and accuracy). For example, the model inference report may include predicted signal quality values ​​for the beams or indicate beams with better predicted signal quality, allowing the network device to make beam switching or scheduling decisions. Similarly, the model monitoring report may include model performance metrics, enabling the network device to evaluate model performance and determine whether model updates or adjustments are necessary.

[0067] The following is a simple illustrative example of the model inference process and the model monitoring process:

[0068] For example, model inference mainly includes two major application scenarios: spatial beam prediction and temporal beam prediction. The following describes the AI ​​use cases (BM-Case 1 and BM-Case 2 as described below) for these two application scenarios:

[0069] 1. BM-Case 1: Based on the measurement results of the reference signal set Set B, perform spatial downlink beam prediction on the reference signal set Set A.

[0070] In BM-Case 1, the network device sends a set of reference signals, Set B. The terminal device measures the signal quality of Set B and uses this measurement as input or part of the input to an AI model. The AI ​​model then predicts the signal quality of the set of reference signals, Set A, to obtain the predicted value for Set A. Based on the AI ​​model's prediction results, the terminal device reports the beam identifiers of the Top K reference signals in Set A to the network device. The Top K reference signals in Set A refer to the K predicted reference signals with the best signal quality in Set A. Set B is a subset of Set A. For example, Set B includes CSI-RS#[2,6], and Set A includes CSI-RS#[1,2,3,4,5,6].

[0071] 2. BM-Case2: Based on the historical measurement results of Set B, perform time-domain downlink beam prediction for Set A.

[0072] In BM-Case 2, the terminal device can measure the signal quality of Set B at one or more past transmission occasions. Using the historical measurement results of Set B as input or part of the input to an AI model, the terminal device predicts the signal quality of Set A at one or more future occasions. Based on the prediction results of the AI ​​model, the terminal device reports the beamform of the TopK reference signal in Set A at one or more future occasions to the network device.

[0073] Optionally, the AI ​​model described in the embodiments of this application may be a long short-term memory network (LSTM) model, a self-attention model (such as a transformer model), a convolutional neural network (CNN) model, a graph neural network (GNN) model, etc., and the embodiments of this application do not limit it.

[0074] It should be noted that the above is only a simple illustrative description of the model inference process using BM-Case1 and BM-Case2 as two AI use cases. The AI ​​use cases described above do not limit the embodiments of this application. In actual applications, terminal devices can also use other AI use cases.

[0075] As described in the model inference process above, the terminal device does not need to measure all reference signals (i.e., Set A), but only a small portion of the reference signals (i.e., Set B). Using the measured values ​​of Set B, the terminal device can obtain the predicted values ​​of Set A through the AI ​​model. In this case, when the terminal device performs model monitoring, it can obtain and report model performance indicators based on the actual measured values ​​of Set B and the predicted values ​​of Set B within the predicted values ​​of Set A.

[0076] Currently, terminal devices continuously monitor the model during model inference. In some cases, when the beam measured and used by the terminal device is stable, the channel time-varying nature is low, the probability of neighbor cell handover is low, and the serving cell beam can consistently maintain its optimal state. Under these conditions, measurement errors are low, the reliability of input feature extraction is high, and the impact of interference and noise on beam prediction accuracy tends to be minimized. Therefore, the monitoring intensity of the terminal device on the AI ​​model can be appropriately reduced. For example, performance index calculations can be paused, and the frequency of model monitoring report submissions can be reduced to save the terminal device's computing and communication resources.

[0077] Therefore, this application provides a model monitoring and management method. During the monitoring of an AI model, the terminal device can relax its monitoring when the terminal device is in a stable beam transmission / reception state. Subsequently, the terminal device can resume normal monitoring of the AI ​​model when the beam transmission / reception state becomes unstable. In this way, the terminal device can flexibly control the monitoring of the AI ​​model according to the beam transmission / reception environment, thereby optimizing the resource utilization of the terminal device to a certain extent.

[0078] The model monitoring and management method provided in this application embodiment will be described in detail below with reference to the corresponding flowcharts. It is understood that the illustrative flowcharts provided in this application embodiment mainly use different devices (such as network devices and terminal devices) as examples of the execution subjects for interactive illustration to illustrate the model monitoring and management method, but this application embodiment does not limit the execution subjects of the interactive illustrations. For example, the devices (such as network devices and terminal devices) in the illustrative flowcharts can also be chips, chip systems, or processors that support the implementation of the model monitoring and management method by the device, or they can be logic modules or software that can implement all or part of the functions of the device.

[0079] As a general statement, the messages or signaling involved in the interaction process of this application embodiment can be standard messages or signaling or newly introduced messages or signaling. This application embodiment does not limit this.

[0080] Understandable, the following text Figures 2 to 5 The network device described in the implementation method can be the one mentioned above. Figure 1 Any of the network devices described in the embodiments can also be devices within a network device (such as processors, chips, or chip systems). (The following...) Figures 2 to 5 The terminal device described in the implementation method can be as described above. Figure 1 Any of the terminal devices described in the embodiments can also be devices within the terminal device (such as processors, chips, or chip systems).

[0081] Figure 2 This is a flowchart of a model monitoring and management method provided in an embodiment of this application. See also... Figure 2 The method may include the following steps:

[0082] Step 201: The terminal device monitors the AI ​​model.

[0083] The AI ​​model is used for beam management. Optionally, the AI ​​model is used to predict the signal quality of the beam.

[0084] This terminal device can periodically acquire performance metrics of the AI ​​model to monitor it. For example, each time the terminal device acquires the performance metrics of the AI ​​model, it does so by: acquiring the performance metrics of the AI ​​model based on the measured values ​​input to the AI ​​model and the predicted values ​​output by the AI ​​model during the latest model inference process.

[0085] Optionally, each time the terminal device obtains the performance metrics of the AI ​​model, it can send a model monitoring report message to the network device, which may include the performance metrics of the AI ​​model.

[0086] For example, the performance metrics of the AI ​​model may include beam accuracy indicator (BAI), etc., but this application embodiment does not limit this.

[0087] Step 202: The terminal device determines whether the first condition is met.

[0088] The first condition can be preset. The first condition reduces the intensity of the terminal device's monitoring of the AI ​​model, effectively relaxing the monitoring of the AI ​​model. The first condition represents that the terminal device is in a stable beam transmission and reception state.

[0089] The terminal device can continue executing step 202 during the execution of step 201. That is, during the model monitoring process, the terminal device can periodically determine whether the first condition is met to determine whether model monitoring can be relaxed.

[0090] Optionally, the first condition may include: the terminal device is in a low mobility state and the terminal device is in a high beam quality state. A low mobility state means that the location of the terminal device changes little. A high beam quality state means that the signal quality of the beam currently used by the terminal device is high. Optionally, the first condition may also include: the terminal device is not located in the edge area of ​​the serving cell. Of course, the first condition may also include other conditions, which are not limited in this embodiment.

[0091] When the terminal device is in a low-mobility state and a high-beam quality state (such as when it is near the TRP of the serving cell), its downlink reception conditions are relatively good and the channel quality is relatively stable. Therefore, the beam measured and used by the terminal device is relatively stable. Under these conditions, the channel time-varying nature is low, the predictability is strong, and the impact of interference and noise on the accuracy of beam prediction is small. Therefore, the monitoring intensity of the AI ​​model can be appropriately reduced to optimize resource utilization.

[0092] When the terminal device is in a low-mobility and high-beam-quality state, and is not located in the edge area of ​​the serving cell, its downlink reception conditions are good and the channel quality is stable. Therefore, the beam measured and used by the terminal device is stable. Under these conditions, the channel time-varying nature is low, its predictability is high, and interference and noise have little impact on the accuracy of beam prediction. Therefore, the monitoring intensity of the AI ​​model can be appropriately reduced to optimize resource utilization.

[0093] In some implementations, the operation of the terminal device to determine whether the terminal device is in a low mobility state can be as follows: determine whether the difference between the reference received signal strength and the received signal strength of the serving cell is less than a first threshold; if the difference between the reference received signal strength and the received signal strength of the serving cell is less than the first threshold, then determine that the terminal device is in a low mobility state; otherwise, determine that the terminal device is not in a low mobility state.

[0094] The operation described above for determining whether the terminal device is in a low mobility state can be implemented based on the following formula 1. Specifically, if formula 1 is satisfied, it means that the terminal device is in a low mobility state; otherwise, it means that the terminal device is not in a low mobility state.

[0095] Formula 1: (SrxlevRef–Srxlev)<SsearchDeltaP.

[0096] Where Srxlev is the received signal strength of the serving cell, in decibels (dB). SrxlevRef is the reference received signal strength, which is the reference value of Srxlev. SsearchDeltaP is the first threshold.

[0097] For example, Srxlev = Qrxlevmeas – (Qrxlevmin + Qrxlevminoffset) – Pcompensation. Qrxlevmeas is the reference signal receiving power (RSRP) value of the serving cell. Qrxlevmin is the minimum RSRP value of the serving cell, which is a preset threshold. Qrxlevminoffset is the minimum RSRP offset of the serving cell, an optional parameter. Pcompensation is the RSRP compensation value, and for example, its calculation formula is: MAX(Pmax – PpowerClass, 0), where PMax is the maximum allowed transmit power of the terminal equipment, and PpowerClass is the maximum transmit power supported by the terminal equipment. Of course, this is not limited to this; Srxlev can also be determined in other ways, and this embodiment does not limit this method.

[0098] For example, the SrxlevRef setting rule is as follows: when a new cell is selected or reselected, or when (Srxlev – SrxlevRef) > 0, or when the duration of TsearchDeltaP in Formula 1 is not met, SrxlevRef is updated to the latest determined Srxlev.

[0099] After selecting or reselecting a new cell, the current Srxlev of the serving cell is set to SrxlevRef. This is because the signal condition of the new cell is an important reference for subsequent measurement and judgment by the terminal equipment during cell handover.

[0100] If (Srxlev – SrxlevRef) > 0, it means that the current Srxlev is higher than the previously set reference value. In this case, SrxlevRef can also be updated to the current Srxlev. This ensures that the reference value can keep up with changes in signal strength in a timely manner, thus making the measurement judgment more consistent with the actual situation.

[0101] If the TsearchDeltaP time formula 1 is not satisfied continuously, i.e., formula 1 is never true, SrxlevRef can still be updated to the current Srxlev. Here, TsearchDeltaP is a time parameter used to limit the update frequency of SrxlevRef, avoiding overly frequent adjustments. TsearchDeltaP specifies how long the terminal device must wait since the most recent SrxlevRef update. For example, TsearchDeltaP can be a time hysteresis value sent by the network device through system messages (such as system information block (SIB) 2 or SIB4, or measurement configuration messages, etc.), such as 1 second.

[0102] For example, t-SearchDeltaP-r16 ENUMERATED {s5, s10, s20, s30, s60, s120, s180, s240, s300, spare7, spare6, spare5, spare4, spare3, spare2, spare1}. Here, t-SearchDeltaP-r16 ENUMERATED refers to the enumeration type for TsearchDeltaP from the 3GPP R16 specification. s5, s10, s20, s30, s60, s120, s180, s240, and s300 represent durations in seconds (s). For example, s5 means 5 seconds, s10 means 10 seconds, and so on. spare7, spare6, spare5, spare4, spare3, spare2, and spare1 refer to additional enumeration values ​​reserved by the protocol that are not defined in the 3GPP R16 specification.

[0103] SsearchDeltaP is a pre-defined threshold value used to indicate the tolerance range for signal strength variations. For example, s-SearchDeltaP-r16 ENUMERATED{dB3, dB6, dB9, dB12, dB15, spare3, spare2, spare1}. Here, s-SearchDeltaP-r16 ENUMERATED refers to the enumeration type for SsearchDeltaP from the 3GPP R16 specification. dB3, dB6, dB9, dB12, and dB15 represent the tolerable signal attenuation; for example, dB3 means a maximum tolerance of 3dB weaker than the reference point, dB6 means a maximum tolerance of 6dB weaker than the reference point, and so on. spare3, spare2, and spare1 are additional enumeration values ​​reserved by the protocol that are not defined in the 3GPP R16 specification.

[0104] If Formula 1 is satisfied, i.e., if (SrxlevRef – Srxlev) < SsearchDeltaP, it means that the current received signal is weaker than the reference point, but the weakness is within an acceptable tolerance range. This indicates that the terminal device has not moved significantly over long distances and is still near the reference point. Therefore, the terminal device is determined to be in a low mobility state. If Formula 1 is not satisfied, i.e., if (SrxlevRef – Srxlev) ≥ SsearchDeltaP, it means that the current received signal is much weaker than the reference point, exceeding the acceptable tolerance range. This indicates that the terminal device may have moved to a more distant location with a worse received signal. Therefore, the terminal device is determined not to be in a low mobility state.

[0105] For example, Formula 1 can be pre-configured by the network device. For instance, Formula 1 can be determined by the low mobility evaluation configuration information sent by the network device to the terminal device. Of course, this is not the only possibility; the terminal device can also obtain Formula 1 through other means, such as pre-configuration within the terminal device or agreement through standard protocols. This application embodiment does not limit this approach.

[0106] In some implementations, the operation of the terminal device to determine whether the terminal device is in a high beam quality state can be: determining whether the signal quality of the beam currently used by the terminal device is greater than a second threshold; if the signal quality of the beam currently used by the terminal device is greater than the second threshold, then the terminal device is determined to be in a high beam quality state; otherwise, the terminal device is determined not to be in a high beam quality state.

[0107] As an example, the signal quality of a beam can be determined based on one or more of the following metrics: layer 1 reference signal received power (L1-RSRP), RSRP, reference signal receiving quality (RSRQ), received signal strength indicator (RSSI), and signal to interference plus noise ratio (SINR). In other words, the signal quality of the beam can be obtained by combining one or more of these metrics.

[0108] As another example, the signal quality of a beam can include one or more of the following indicators: L1-RSRP, RSRP, RSRQ, RSSI, SINR, etc. In this case, each indicator has its corresponding second threshold, which can be preset. Only when each indicator of the beam's signal quality is greater than its corresponding second threshold is the terminal device determined to be in a high beam quality state; otherwise, the terminal device is determined not to be in a high beam quality state. For example, if the beam's signal quality includes L1-RSRP and RSRQ, then the terminal device is determined to be in a high beam quality state only if both L1-RSRP and RSRQ are greater than a certain threshold.

[0109] The operation to determine whether the terminal device is in a high beam quality state can be implemented based on the following formula 2. Specifically, if formula 2 is satisfied, it means that the terminal device is in a high beam quality state; otherwise, it means that the terminal device is not in a high beam quality state.

[0110] Formula 2: Bqual>ThresholdPerformanceAI.

[0111] Bqual refers to the signal quality of the beam currently used by the terminal device. ThresholdPerformanceAI is the second threshold.

[0112] For example, Bqual can be the L1-RSRP of a beam. L1-RSRP is the most important, fundamental, and direct beam quality information in beam management. BAI, as a key indicator for quantitatively evaluating AI model performance, is implicitly calculated based on L1-RSRP. L1-RSRP is a real-time, unfiltered measurement at the physical layer, which is faster and more raw, serving as a reference for beam management and BAI calculation. Therefore, using L1-RSRP as a parameter to measure beam quality is very appropriate. Of course, this is not the only option; other metrics can be used in practical applications.

[0113] ThresholdPerformanceAI is a pre-set threshold value, typically a value much greater than 0. For example, ThresholdPerformanceAI can be a threshold value set by a network device.

[0114] If Formula 2 is satisfied, i.e., if Bqual > ThresholdPerformanceAI, it means that the signal quality of the beam currently used by the terminal device is good, and therefore the terminal device is determined to be in a high beam quality state. If Formula 2 is not satisfied, i.e., if Bqual ≤ ThresholdPerformanceAI, it means that the signal quality of the beam currently used by the terminal device is poor, and therefore the terminal device is determined not to be in a high beam quality state.

[0115] For example, Formula 2 can be pre-configured by the network device. For instance, Formula 2 can be determined by beam quality assessment configuration information sent by the network device to the terminal device. Of course, this is not the only possibility; the terminal device can also obtain Formula 2 through other means, such as pre-configuration within the terminal device or agreement through standard protocols. This application embodiment does not limit this approach.

[0116] In some implementations, the terminal device may determine whether it is located in the edge area of ​​the serving cell by: if the received signal strength of the serving cell is greater than a third threshold, and / or if the received signal quality of the serving cell is greater than a fourth threshold, then the terminal device is determined not to be located in the edge area of ​​the serving cell; otherwise, the terminal device is determined to be located in the edge area of ​​the serving cell.

[0117] The operation described above for determining whether the terminal device is located in the edge area of ​​the serving cell can be implemented based on the following formulas 3 and 4. Specifically, if formula 3 and / or formula 4 are satisfied, it means that the terminal device is not located in the edge area of ​​the serving cell; otherwise, it means that the terminal device is located in the edge area of ​​the serving cell.

[0118] Formula 3: Srxlev>SSearchThresholdP.

[0119] Formula 4: Squal>SsearchThresholdQ.

[0120] Where Srxlev is the received signal strength of the serving cell, in dB. SSearchThresholdP is the third threshold.

[0121] SSearchThresholdP is a pre-set threshold value, typically much greater than 0. For example, SSearchThresholdP can be a threshold value sent by the network device via system messages such as SIB2 or SIB4 or measurement configuration messages.

[0122] If Equation 3 is satisfied, i.e., if Srxlev > SSearchThresholdP, it means that the received signal strength of the terminal device is high, indicating that the terminal device is likely located in the central area of ​​the serving cell. If Equation 3 is not satisfied, i.e., if Srxlev ≤ SSearchThresholdP, it means that the received signal strength of the terminal device is low, indicating that the terminal device is likely located in the edge area of ​​the serving cell.

[0123] Where Squal represents the received signal quality of the serving cell, in dB. SsearchThresholdQ is the fourth threshold.

[0124] For example, Squal = Qqualmeas - (Qqualmin + Qqualminoffset). Qqualmeas is the RSRQ value of the serving cell. Qqualmin is the minimum RSRQ value of the serving cell, which is a preset threshold value. Qqualminoffset is the minimum RSRQ offset of the serving cell, which is an optional parameter. Of course, it is not limited to this, and Squal can also be determined in other ways. This application embodiment does not limit this.

[0125] SsearchThresholdQ is a pre-set threshold value, typically a value much greater than 0. For example, SsearchThresholdQ can be a threshold value sent by the network device via system messages such as SIB2 or SIB4 or measurement configuration messages.

[0126] If Equation 4 is satisfied, i.e., if Srxlev > SSearchThresholdP, it means that the received signal quality of the terminal device is good, indicating that the terminal device is likely located in the central area of ​​the serving cell. If Equation 4 is not satisfied, i.e., if Srxlev ≤ SSearchThresholdP, it means that the received signal quality of the terminal device is poor, indicating that the terminal device is likely located in the edge area of ​​the serving cell.

[0127] For example, Formulas 3 and 4 can be pre-configured by the network device. For instance, Formulas 3 and 4 can be determined by the cell edge evaluation configuration information sent by the network device to the terminal device. Of course, this is not the only possibility; the terminal device can also obtain Formulas 3 and 4 through other means, such as pre-configuration within the terminal device or agreement through standard protocols. This application embodiment does not limit this approach.

[0128] It should be noted that Formula 1 above determines the mobility of the terminal device, while Formulas 3 and 4 determine its location. Generally, when a terminal device is in a state of low mobility or at the edge of a non-serving cell, it can be considered to be in a stable beam transmission and reception state, allowing for relaxed monitoring of the AI ​​model. However, this does not assess the transmission performance of the beam currently used by the terminal device. If, under the conditions of satisfying Formula 1, and Formulas 3 and / or 4, the beam signal quality does not meet certain requirements, it means that the currently used beam does not meet or is about to fail to meet communication needs, resulting in unstable communication quality and questionable reliability of the AI ​​model's predictions. In this situation, it is not suitable to relax monitoring of the AI ​​model. Therefore, in this embodiment, Formula 2 is introduced, i.e., a high beam quality state is introduced as one of the conditions for relaxing model monitoring.

[0129] Generally, satisfying Formulas 1 and 2 indicates that the receiving power of the terminal device is stable and it is in a low-mobility state. Formulas 3 and 4 can be flexibly configured according to needs. For example, in scenarios with high co-channel interference, dense urban areas, or high requirements for signal quality, Formulas 3 and 4 can be configured.

[0130] In some implementations, the first condition may be pre-configured by the network device and sent to the terminal device. For example, the network device may send dynamic performance monitoring configuration (DynPerfMonConfig) information to the terminal device. This dynamic performance monitoring configuration information is used to dynamically activate or deactivate (also known as disable) the performance monitoring configuration, and may include the first condition. For example, the network device may send this dynamic performance monitoring configuration information to the terminal device in a medium access control (MAC) control element (CE) message or downlink control information (DCI). Of course, the network device may also send this dynamic performance monitoring configuration information to the terminal device in other messages; this application embodiment does not limit this approach.

[0131] Of course, it is not limited to this. The terminal device can also obtain the first condition in other ways, such as pre-configuring it in the terminal device or agreeing on it through a standard protocol. This application embodiment does not limit this.

[0132] Step 203: The terminal device enters the target state if the first condition is met.

[0133] In some implementations, model monitoring is not performed in the target state. The target state can be maintained for a preset duration, that is, the target state automatically exits after the preset duration. The preset duration can be pre-set. For example, the preset duration can be pre-set by the network device and sent to the terminal device. Of course, this is not limited to this; the terminal device can also obtain the preset duration in other ways, such as pre-configuring it on the terminal device or agreeing on it through a standard protocol, etc., and this application embodiment does not limit this. The preset duration can be implemented using a timer.

[0134] In other implementations, the model monitoring frequency is reduced in the target state. That is, model monitoring is still performed when the target state is in effect, but the period for obtaining the performance metrics of the AI ​​model during model monitoring is longer than the period in the non-target state. This reduces resource consumption.

[0135] In some implementations, to avoid frequent state switching caused by signal fluctuations, the terminal device can enter the target state only after the terminal device has met the first condition for a certain period of time. That is, if the terminal device meets the first condition for a continuous first duration, it enters the target state; otherwise, it does not enter the target state. The first duration can be preset, for example, it can be the aforementioned TSearchDeltaP, etc., and this application embodiment does not limit this. The first duration can be implemented using a timer.

[0136] Step 204: The terminal device determines whether the second condition is met when it is in the target state.

[0137] The second condition can be preset. The second condition is the condition for exiting the target state. The second condition is used to indicate that the beam transmission and reception status of the terminal device is unstable, such as a sudden abnormality in the beam transmission and reception environment.

[0138] Optionally, the second condition may include: the terminal device is not in a high beam quality state. Determining a high beam quality state is simple and fast, with minimal resource overhead, and can efficiently serve as an indicator of sudden environmental changes. Of course, the second condition may also include other conditions, such as the terminal device not being in a low mobility state, which can indicate unstable communication connections; this embodiment of the application does not limit this.

[0139] When in the target state, the terminal device does not need to determine whether the first condition is met, but can periodically determine whether the second condition is met to determine whether it needs to exit the target state and resume normal model monitoring. Once exiting the target state, the terminal device does not need to determine whether the second condition is met again.

[0140] Step 205: The terminal device exits the target state when the second condition is met.

[0141] In some implementations, the terminal device does not perform model monitoring in the target state, and automatically exits the target state after a preset time. In this case, if the second condition is not detected within the preset time, the terminal device can automatically exit the target state after the preset time. If the second condition is detected within the preset time, it can immediately exit the target state to resume normal model monitoring.

[0142] In other embodiments, the terminal device performs low-frequency model monitoring while in the target state. In this case, if the terminal device does not detect that the second condition is met while in the target state, it can maintain the target state and perform low-frequency model monitoring. However, if it detects that the second condition is met while in the target state, it can exit the target state and resume normal-frequency model monitoring.

[0143] In this embodiment, during the monitoring of the AI ​​model, the terminal device can determine whether a first condition is met. If the first condition is met, it indicates that the terminal device is in a stable beam transceiver state, and it can then enter the target state to relax the monitoring of the AI ​​model. While in the target state, the terminal device can determine whether a second condition is met. If the second condition is met, it indicates that the beam transceiver state is unstable, and it can then exit the target state to resume normal monitoring of the AI ​​model. Thus, the terminal device can flexibly control the monitoring of the AI ​​model according to the beam transceiver environment, thereby optimizing the resource utilization of the terminal device to a certain extent.

[0144] The above text Figure 2 In some implementations, the terminal device can automatically enter the target state based on the first condition. In other implementations, the terminal device needs an instruction from the network device to enter the target state, which will be discussed below. Figure 3 The implementation method is described in detail below.

[0145] Figure 3 This is a flowchart of a model monitoring and management method provided in an embodiment of this application. See also... Figure 3 The method may include the following steps:

[0146] Step 301: The terminal device monitors the AI ​​model.

[0147] The operation of step 301 is similar to that of step 201 above, and will not be described again in this embodiment.

[0148] Step 302: The terminal device determines whether the first condition is met.

[0149] The operation of step 302 is similar to that of step 202 above, and will not be described again in this embodiment.

[0150] Step 303: If the first condition is met, the terminal device sends a relaxation monitoring request to the network device.

[0151] The relaxation of monitoring request information is used to indicate that the first condition has been met, and to request relaxation of monitoring of the AI ​​model. That is, the relaxation of monitoring request information is used to request entry into the target state. Optionally, the relaxation of monitoring request information may carry the AI ​​model's identifier (ID). Of course, it is not limited to this; the relaxation of monitoring request information may also carry other information related to the AI ​​model, and this application embodiment does not limit this.

[0152] For example, the terminal device can send the relaxed monitoring request information to the network device in a MAC CE message or uplink control information (UCI). Alternatively, the terminal device can send the relaxed monitoring request information to the network device in other messages.

[0153] In some implementations, to avoid frequent state switching caused by signal fluctuations, the terminal device may send the relaxation monitoring request information to the network device only after the terminal device has met the first condition for a certain period of time. That is, if the terminal device meets the first condition for a continuous first duration, it sends the relaxation monitoring request information to the network device; otherwise, it does not send the relaxation monitoring request information to the network device.

[0154] Step 304: After receiving the relaxation monitoring request information, the network device sends the first instruction information to the terminal device.

[0155] The first indication information is used to instruct the relaxation of monitoring of the AI ​​model, that is, to instruct the entry into the target state. Optionally, if the target state is that no model monitoring is performed for a preset duration, the first indication information may include the preset duration.

[0156] In some implementations, after receiving the relaxation monitoring request information, the network device can directly send a first instruction message to the terminal device.

[0157] In other implementations, after receiving the relaxation monitoring request information, the network device can determine whether to send a first instruction information to the terminal device based on the historical performance of the AI ​​model and / or the cell beam environment.

[0158] Historical performance data of an AI model can reflect its recent performance. For example, historical performance data can be determined based on the BAI (Balanced AI Analysis) sent by the terminal device to the network device. For instance, if historical performance data indicates good recent performance (e.g., high prediction accuracy), the network device may allow the terminal device to relax its monitoring of the AI ​​model; conversely, if historical performance data indicates poor recent performance (e.g., low prediction accuracy), the network device may not allow the terminal device to relax its monitoring of the AI ​​model.

[0159] The cell beam environment reflects the communication performance of the beam direction currently used by the terminal device. For example, the cell beam environment can be determined based on the beam transmission and reception status of other terminal devices in that beam direction. For instance, if the cell beam environment reflects stable beam transmission and reception in that beam direction, the network device can allow the terminal device to relax its monitoring of the AI ​​model; if the cell beam environment reflects abnormal beam transmission and reception in that beam direction (such as a large number of terminal devices switching beams in a short period, or a sudden deterioration in beam quality), the network device will not allow the terminal device to relax its monitoring of the AI ​​model.

[0160] When the network device allows the terminal device to relax its monitoring of the AI ​​model, it can send a first instruction message to the terminal device. When the network device does not allow the terminal device to relax its monitoring of the AI ​​model, it can send a second or third instruction message to the terminal device.

[0161] The second instruction is used to indicate that the terminal device is not allowed to relax its monitoring of the AI ​​model, but is allowed to submit a relaxation monitoring request again within a second time period.

[0162] The third instruction is used to indicate that the terminal device is not allowed to relax its monitoring of the AI ​​model, and is not allowed to submit a relaxation monitoring request again within the second time period. Optionally, the third instruction may include a second time period. The second time period can be preset. The second time period can be implemented using a timer.

[0163] For example, if the historical performance of an AI model indicates that its recent performance, while somewhat poor, is already very close to the required performance (e.g., the difference between the model's prediction accuracy and the corresponding accuracy threshold is small), then the AI ​​model's performance is likely to reach the required level within a short period. Therefore, while the network device may not currently allow the terminal device to relax its monitoring of the AI ​​model, it may permit the terminal device to submit a relaxation monitoring request again within a short time. In this case, the network device can send a second instruction to the terminal device. Upon receiving the second instruction, the terminal device will not enter the target state (i.e., continue normal model monitoring) and will continue to determine whether the first condition is met. If the first condition is met, it can send a relaxation monitoring request to the network device again.

[0164] For example, if a large number of terminal devices have recently switched beams in the beam direction currently used by the terminal device, it indicates that the beam transmission and reception in that direction is extremely unstable and unlikely to improve in the short term. Therefore, the network device not only prohibits the terminal device from relaxing its monitoring of the AI ​​model this time, but also prohibits the terminal device from submitting a relaxation monitoring request again in the short term. In this case, the network device can send a third instruction to the terminal device. After receiving the third instruction, the terminal device does not enter the target state (i.e., continues normal model monitoring), and does not need to determine whether the first condition is met within the second time period. It can determine whether the first condition is met after the second time period.

[0165] For example, the network device can send a first indication message, a second indication message, or a third indication message to the terminal device via the physical downlink control channel (PDCCH).

[0166] Step 305: After receiving the first instruction information, the terminal device enters the target state.

[0167] In some implementations, model monitoring is not performed in the target state. The target state can be maintained for a preset duration, that is, the target state automatically exits after the preset duration. The preset duration can be set in advance.

[0168] In other implementations, the model monitoring frequency is reduced during the target state. That is, model monitoring continues even in the target state, but the period for obtaining the AI ​​model's performance metrics is longer than in the non-target state. This reduces resource consumption. Furthermore, in this case, frequent requests for model monitoring relaxation from network devices are eliminated, reducing signaling interactions. This is more suitable for scenarios where the terminal device is located at the edge of a non-serving cell and has low mobility.

[0169] In this embodiment, during the monitoring of the AI ​​model, the terminal device can determine whether a first condition is met. If the first condition is met, it indicates that the terminal device is in a stable beam transceiver state, and it can then request to enter the target state from the network device. After receiving the first indication information sent by the network device, the terminal device can enter the target state to relax the monitoring of the AI ​​model. In this way, the terminal device and the network device can flexibly control the monitoring of the AI ​​model according to the beam transceiver environment, thereby optimizing the resource utilization of the terminal device to a certain extent.

[0170] The above text Figure 2 In some implementations, the terminal device can automatically exit the target state based on the second condition. In other implementations, the terminal device needs an instruction from the network device to exit the target state, which will be discussed below. Figure 4 The implementation method is described in detail below.

[0171] Figure 4 This is a flowchart of a model monitoring and management method provided in an embodiment of this application. See also... Figure 4 The method may include the following steps:

[0172] Step 401: The terminal device determines whether the second condition is met when it is in the target state.

[0173] It should be noted that this terminal device can be accessed via the above... Figure 2 The terminal device enters the target state via steps 201 to 203 in the implementation method; alternatively, the terminal device can do so via the above-described... Figure 3 The target state is entered through steps 301 to 305 in the implementation method.

[0174] The operation of step 401 is similar to that of step 204 above, and will not be described again in this embodiment.

[0175] Step 402: If the second condition is met, the terminal device sends a request to the network device to restore monitoring.

[0176] The resumption monitoring request information is used to indicate that the second condition has been met in the target state, and to request the resumption of monitoring of the AI ​​model. That is, the resumption monitoring request information is used to request exit from the target state. Optionally, the resumption monitoring request information may carry the identifier of the AI ​​model. Of course, it is not limited to this; the resumption monitoring request information may also carry other information related to the AI ​​model, and this embodiment does not limit this.

[0177] For example, the terminal device can send the recovery monitoring request information to the network device in a MAC CE message or a UCI message. Alternatively, the terminal device can send the recovery monitoring request information to the network device in other messages.

[0178] Step 403: After receiving the recovery monitoring request information, the network device sends a fourth instruction message to the terminal device.

[0179] After receiving the request to resume monitoring, the network device can choose to activate the original model monitoring configuration or choose to adopt the new model monitoring configuration.

[0180] In this case, the fourth instruction message is used to instruct the model monitoring to continue using the original model monitoring configuration, i.e., to reactivate the original model monitoring configuration. Alternatively, the fourth instruction message is used to instruct the model monitoring to use the new model monitoring configuration, i.e., to activate the new model monitoring configuration.

[0181] For example, the network device can send a fourth instruction message to the terminal device via PDCCH.

[0182] Step 404: After receiving the fourth instruction information, the terminal device exits the target state.

[0183] In some implementations, the terminal device does not perform model monitoring in the target state, and automatically exits the target state after a preset time. In this case, if the second condition is not detected within the preset time, the terminal device can automatically exit the target state after the preset time, and normal model monitoring can be resumed without requesting the network device. However, if the second condition is detected within the preset time, the terminal device can request to exit the target state to resume normal model monitoring.

[0184] In other embodiments, the terminal device performs low-frequency model monitoring while in the target state. In this case, if the terminal device does not detect that the second condition is met while in the target state, it can maintain the target state and perform low-frequency model monitoring. However, if it detects that the second condition is met while in the target state, it can request the network device to exit the target state to resume normal frequency model monitoring.

[0185] In some cases, if the terminal device sends a recovery monitoring request to the network device in step 402 but has not yet received a response from the network device, it can maintain the target state or use the original model monitoring configuration to perform normal model monitoring.

[0186] In this embodiment, the terminal device determines whether the second condition is met when it is in the target state. If the second condition is met, it can request to exit the target state from the network device. After receiving the fourth indication information sent by the network device, the terminal device can exit the target state to resume normal model monitoring. In this way, when the terminal device is in the target state, it can exit the target state in a timely manner when there is a sudden abnormality in the beam transceiver environment, thereby ensuring the performance of the AI ​​model to a certain extent.

[0187] It should be noted that the parameters involved in the model monitoring relaxation mechanism provided in this application embodiment include the aforementioned first condition, preset duration, first duration, and second duration. These parameters can be configured by the network device when the terminal device initially accesses the cell, or they can be configured by the network device during the communication process between the terminal device and the network device. This application embodiment does not limit this configuration.

[0188] Optionally, the network device may send one or more of the first condition, preset duration, first duration, and second duration to the terminal device in the same message, or it may send one or more of the first condition, preset duration, first duration, and second duration to the terminal device in different messages.

[0189] For example, the network device may send one or more of the first condition, preset duration, first duration, and second duration to the terminal device in the model inference configuration information or model monitoring configuration information, or it may send one or more of the first condition, preset duration, first duration, and second duration to the terminal device in the same message as the model inference configuration information or model monitoring configuration information. Of course, one or more of the first condition, preset duration, first duration, and second duration may also be sent to the terminal device in other messages. This application embodiment does not limit this.

[0190] Of course, it is not limited to this. The terminal device may also obtain one or more of the first condition, preset duration, first duration, and second duration through other means, such as pre-configuration in the terminal device or agreement through standard protocols. This application embodiment does not limit this.

[0191] In some implementations, network devices can determine whether to enable the model monitoring relaxation mechanism based on the cell beam environment and / or cell geographical environment, that is, whether to send model monitoring relaxation mechanism parameters to terminal devices.

[0192] Cell beam environment is used to reflect the communication performance of the beam direction currently used by the terminal device.

[0193] The cell geographic environment is used to reflect the geographical situation of the beam direction currently used by the terminal device. For example, the cell geographic environment is used to reflect whether the geographical area corresponding to the beam direction is a densely built-up area, a park, or an area near a train, etc.

[0194] For example, if the cell beam environment indicates a high frequency of recent beam switching by other terminal devices in that beam direction, the model monitoring relaxation mechanism will be temporarily disabled. If the cell beam environment indicates a low frequency of recent beam switching by other terminal devices in that beam direction, the model monitoring relaxation mechanism will be enabled. If the cell geographic environment indicates that the geographic area corresponding to that beam direction is a densely built-up area or near a train, the model monitoring relaxation mechanism will be temporarily disabled. If the cell geographic environment indicates that the geographic area corresponding to that beam direction is a park, the model monitoring relaxation mechanism will be enabled.

[0195] In some implementations, when AI model parameters are modified, AI model rollback occurs, or AI model is replaced, the network device can disable the model monitoring relaxation mechanism. This means it can instruct the terminal device to delete the corresponding model monitoring relaxation mechanism parameters and stop performing the aforementioned checks on the first and second conditions. Alternatively, when AI model parameters are modified, AI model rollback occurs, or AI model is replaced, the network device can reconfigure the model monitoring relaxation mechanism. This means it can reset the model monitoring relaxation mechanism parameters and send them to the terminal device, which can then perform the aforementioned checks on the first and second conditions based on the new model monitoring relaxation mechanism parameters.

[0196] It should be noted that Formulas 1, 3, and 4 involved in the embodiments of this application are part of the 3GPP standard protocol and belong to the traditional radio resource management (RRM) field. The embodiments of this application utilize these existing formulas and introduce a new Formula 2 to implement the model monitoring relaxation mechanism provided in the embodiments of this application. Thus, flexible control of AI model monitoring in beam management is achieved with minimal standard influence and high reliability.

[0197] The following example illustrates a possible implementation of this application embodiment by configuring model monitoring relaxation mechanism parameters in the initial configuration during the initial access of the terminal device:

[0198] Figure 5 This is a flowchart of a model monitoring and management method provided in an embodiment of this application. See also... Figure 5 The method may include the following steps:

[0199] Step 501: After the terminal device is connected, the network device determines whether to enable the model monitoring relaxation mechanism for the terminal device.

[0200] After the terminal device connects, the network device can perform initial configuration of the AI ​​model on the terminal device. During the initial configuration, it can determine whether to enable the model monitoring relaxation mechanism for the terminal device.

[0201] If the network device determines that the model monitoring relaxation mechanism is not enabled for this terminal device, it will not send the model monitoring relaxation mechanism parameters to the terminal device. In this case, the terminal device will normally activate the model inference configuration and model monitoring configuration, and perform normal model inference and model monitoring.

[0202] Step 502: If the network device determines that the model monitoring relaxation mechanism is enabled for the terminal device, it sends the model monitoring relaxation mechanism parameters to the terminal device.

[0203] For example, the network device can send model monitoring relaxation mechanism parameters to the terminal device via PDCCH.

[0204] Step 503: The terminal device activates the model inference configuration, activates the model monitoring configuration, and determines whether the first condition is met.

[0205] After initial access, the terminal device can activate the corresponding AI model configuration. For example, it can activate the model inference configuration to perform relevant inference through the AI ​​model and send a model inference report to the network device. It can also activate the model monitoring configuration to monitor the AI ​​model and send a model monitoring report to the network device. In this embodiment, a model monitoring relaxation mechanism can also be executed, that is, during the model monitoring process, it can determine whether a first condition is met to determine whether monitoring of the AI ​​model needs to be relaxed.

[0206] Step 504: If the terminal device determines that the first condition is met, it sends a relaxation monitoring request to the network device.

[0207] Step 505: The network device sends a first instruction message, a second instruction message, or a third instruction message to the terminal device.

[0208] Step 506: If the terminal device receives the first instruction information, it enters the target state. While in the target state, it determines whether the second condition is met. If it is met, it exits the target state.

[0209] Step 507: If the terminal device receives the second instruction information, it will not enter the target state, and will continue to determine whether the first condition is met.

[0210] Step 508: If the terminal device receives the third instruction information, it will not enter the target state, and will not determine whether the first condition is met within the second time period. After the second time period, it will determine whether the first condition is met.

[0211] It should be understood that Figures 2 to 5 The flowcharts or scene diagrams shown are for illustrative purposes only and are not intended to limit the embodiments of this application to the examples illustrated. In fact, those skilled in the art can interpret the embodiments based on... Figures 2 to 5 The examples in the document can be transformed into equivalent ways to obtain more implementations.

[0212] The above text combined Figures 2 to 5 This document describes in detail the model monitoring and management method provided in the embodiments of this application. The following will combine... Figures 6 to 7 The device embodiments of this application are described in detail below. It should be understood that the communication device of this application embodiment can execute the various model monitoring and management methods of the foregoing embodiments of this application, that is, the specific working processes of the various products below can be referred to the corresponding processes in the foregoing method embodiments.

[0213] In the embodiments described above, the network device may execute some or all of the steps in each embodiment; the terminal device may execute some or all of the steps in each embodiment. These steps or operations are merely examples, and other operations or variations thereof may also be performed in the embodiments of this application. Furthermore, the steps may be executed in different orders as presented in the embodiments, and it is not necessary to execute all the operations in the embodiments of this application. The sequence number of each step 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.

[0214] Figure 6 This is a schematic block diagram of a communication device provided in an embodiment of this application. Figure 6 As shown, the communication device 600 may include a communication module 620. The communication module 620 can implement corresponding communication functions, which can be internal communication functions of the communication device 600 or communication functions between the communication device 600 and other devices. Optionally, the communication module 620 may also be referred to as a communication interface or transceiver module. Optionally, the communication device 600 also includes a processing module 610. The processing module 610 can implement corresponding processing functions.

[0215] Optionally, the communication device 600 further includes a storage module, which can be used to store instructions and / or data; the processing module 610 can read the instructions and / or data in the storage module so that the communication device 600 can implement the aforementioned method embodiments.

[0216] In one possible design, the communication device 600 may correspond to the terminal device in the above method embodiments, or to a component (such as a circuit, chip, or chip system) configured in the terminal device. The communication device 600 can be used to perform the steps or processes performed by the terminal device in any of the above method embodiments.

[0217] For example, the processing module 610 is used to: monitor the AI ​​model, which is used for beam management; and enter a target state when a first condition is met, the first condition including the terminal device being in a low mobility state and a high beam quality state, and no model monitoring is performed within a preset time period in the target state, or the model monitoring frequency is reduced in the target state.

[0218] For example, the processing module 610 is configured to: determine that the terminal device is in a low mobility state if the difference between the reference received signal strength and the received signal strength of the serving cell is less than a first threshold; and determine that the terminal device is not in a low mobility state if the difference between the reference received signal strength and the received signal strength of the serving cell is greater than or equal to the first threshold.

[0219] For example, the processing module 610 is configured to: determine that the terminal device is in a high beam quality state if the signal quality of the beam currently used by the terminal device is greater than a second threshold; and determine that the terminal device is not in a high beam quality state if the signal quality of the beam currently used by the terminal device is less than or equal to the second threshold.

[0220] For example, the signal quality of the beam is the L1-RSRP of the beam.

[0221] For example, the first condition also includes that the terminal device is not located in the edge area of ​​the serving cell.

[0222] For example, the processing module 610 is configured to: determine that the terminal device is not located in the edge region of the serving cell if the received signal strength of the serving cell is greater than a third threshold, and / or if the received signal quality of the serving cell is greater than a fourth threshold; otherwise, determine that the terminal device is located in the edge region of the serving cell.

[0223] For example, the communication module 620 is configured to: send a relaxation monitoring request to the network device when a first condition is met. The processing module 610 is configured to: enter the target state upon receiving a first instruction from the network device.

[0224] For example, the processing module 610 is configured to: upon receiving a second indication message sent by the network device, not enter the target state, and continue to determine whether the first condition is met; or, upon receiving a third indication message sent by the network device, not enter the target state, and not determine whether the first condition is met within a second time period.

[0225] For example, the processing module 610 is used to: determine whether a second condition is met when the target state is in which the second condition includes that the terminal device is not in a high beam quality state; and exit the target state when the second condition is met.

[0226] The above are merely examples; for detailed steps or procedures, please refer to the descriptions in the foregoing embodiments.

[0227] Figure 7 This is a schematic block diagram of a communication device 700 provided in an embodiment of this application. The communication device 700 may be a network device, a terminal device, or a circuit, chip, chip system, or processor for implementing the above methods. The communication device 700 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0228] like Figure 7 As shown, the communication device 700 may include one or more processors 710, which may also be referred to as processing units or processing modules, and can implement certain control functions. The processor 710 may 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 700 (e.g., a base station, baseband chip, user equipment, user chip), execute software programs, and process data from the software programs.

[0229] In an alternative design, the processor 710 may also store instructions and / or data that can be executed by the processor 710 to cause the communication device 700 to perform the methods described in the above method embodiments.

[0230] In another alternative design, the communication device 700 may include a communication interface 720 for implementing receiving and transmitting functions. For example, the communication interface 720 may be a transceiver circuit, interface, interface circuit, or transceiver. The transceiver circuit, interface, interface circuit, or transceiver for implementing receiving and transmitting functions may be separate or integrated. The aforementioned transceiver circuit, interface, interface circuit, or transceiver may be used for reading and writing code / data, or it may be used for transmitting or relaying signals.

[0231] Optionally, the communication device 700 may include one or more memories 730, which may store instructions that can be executed on the processor 710, causing the communication device 700 to perform the methods described in the above method embodiments. Optionally, the memories 730 may also store data. Optionally, the processor 710 may also store instructions and / or data. The processor 710 and the memories 730 may be provided separately or integrated together.

[0232] It should be understood that, in one possible design, the steps in the method embodiments provided in this application can be implemented by integrated logic circuits in the processor's hardware or by instructions in software form. The steps of the methods disclosed in the embodiments of this application can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software modules can reside in mature storage media in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are not provided here.

[0233] In one implementation, the communication device 700 may correspond to the network device in the above method embodiments and may be used to execute the various steps and / or processes executed by the network device in the above method embodiments. The processor 710 may be used to execute instructions stored in the memory 730, and when the processor 710 executes the instructions stored in the memory, the processor 710 is used to execute the various steps and / or processes of the above method embodiments corresponding to the network device.

[0234] In another implementation, the communication device 700 may correspond to the terminal device in the above method embodiments, and may be used to execute the various steps and / or processes executed by the terminal device in the above method embodiments. The processor 710 may be used to execute instructions stored in the memory 730, and when the processor 710 executes the instructions stored in the memory, the processor 710 is used to execute the various steps and / or processes of the above method embodiments corresponding to the terminal device.

[0235] It should be understood that the aforementioned processing device can be one or more chips. For example, the processing device can be a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a system-on-chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0236] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0237] According to the method provided in the embodiments of this application, this application also provides a chip system, which includes one or more processors for calling and executing instructions stored in memory, thereby causing the method described in the embodiments of this application to be executed. The chip system may be composed of chips or may include chips and other discrete devices.

[0238] The chip system may include input circuits or interfaces for transmitting information or data, and output circuits or interfaces for receiving information or data.

[0239] According to the method provided in the embodiments of this application, this application also provides a communication system, which includes the aforementioned network device and terminal device.

[0240] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute the various steps or processes executed by the network device or terminal device in any of the foregoing method embodiments.

[0241] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when run on a computer, causes the computer to execute the various steps or processes executed by the network device or terminal device in any of the foregoing method embodiments.

[0242] The computer-readable storage medium may be the aforementioned volatile memory or non-volatile memory, or it may include both volatile memory and non-volatile memory.

[0243] In the embodiments of this application, the terms and English abbreviations are exemplary examples given for ease of description and should not be construed as limiting the application in any way. This application does not preclude the possibility of defining other terms that can achieve the same or similar functions in existing or future agreements.

[0244] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When these computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated.

[0245] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0246] It should be 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.

[0247] In summary, the above descriptions are merely optional embodiments of the technical solutions of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A model monitoring management method characterized by, The method is applied to a terminal device, and the method comprises: monitoring an artificial intelligence (AI) model, the AI model being used for beam management; entering a target state if a first condition is met, the first condition comprising that the terminal device is in a low mobility state and a high beam quality state, and the target state being a state in which model monitoring is not performed for a preset time length or a state in which the frequency of model monitoring is reduced; the method further comprises: determining that the terminal device is in a low mobility state if a difference between a reference received signal strength and a received signal strength of a serving cell is less than a first threshold value; determining that the terminal device is in a high beam quality state if the signal quality of a beam currently used by the terminal device is greater than a second threshold value.

2. The method of claim 1, wherein, the method further comprises: determining that the terminal device is not in a low mobility state if the difference between the reference received signal strength and the received signal strength of the serving cell is greater than or equal to the first threshold value.

3. The method of claim 1, wherein, the method further comprises: determining that the terminal device is not in a high beam quality state if the signal quality of the beam currently used by the terminal device is less than or equal to the second threshold value.

4. The method of claim 3, wherein, The signal quality of the beam is a layer one reference signal received power (L1-RSRP) of the beam.

5. The method of claim 1, wherein, The first condition further comprises that the terminal device is not located at an edge area of a serving cell.

6. The method of claim 5, wherein, the method further comprises: if the received signal strength of the serving cell is greater than a third threshold value and / or if the received signal quality of the serving cell is greater than a fourth threshold value, determining that the terminal device is not located at the edge area of the serving cell; otherwise, determining that the terminal device is located at the edge area of the serving cell.

7. The method of claim 1, wherein, the entering of the target state if the first condition is met comprises: sending a relaxed monitoring application information to a network device if the first condition is met; entering the target state if first indication information sent by the network device is received.

8. The method of claim 7, wherein, after the sending of the relaxed monitoring application information to the network device, the method further comprises: if second indication information sent by the network device is received, not entering the target state and continuing to determine whether the first condition is met; or if third indication information sent by the network device is received, not entering the target state and not determining whether the first condition is met for a second time length.

9. The method of any one of claims 1 to 8, wherein, after the entering of the target state, the method further comprises: determining whether a second condition is met while being in the target state, the second condition comprising that the terminal device is not in a high beam quality state; exiting the target state if the second condition is met.

10. A communications device, characterized by The communication device comprises at least one processor coupled with a memory, the memory storing a program or instructions, and the processor executes the program or instructions to enable the communication device to perform the method of any one of claims 1 to 9.

11. A communication system, characterized by The communication system comprises the communication device of claim 10.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer programs or instructions that, when executed, cause a computer to perform the method of any one of claims 1 to 9.

13. A chip system, characterized by The chip system comprises one or more processors for calling and running instructions stored in a memory, so that the method of any one of claims 1 to 9 is performed.

Images