Wireless communication method and apparatus, and terminal and network-side device

Abstract

The present application belongs to the field of communications. Provided are a wireless communication method and apparatus, and a terminal and a network-side device. The wireless communication method comprises: a terminal activating a first model in a first function; and within active time of the first model, the terminal executing a first operation on the basis of a monitoring result of at least one of the performance of the first model and a resource of the terminal, wherein the first operation comprises at least one of the following: continuing to operate the first model, performing model reselection, deactivating the first model, deactivating the first function and performing function reselection.

Description

Wireless communication method, device, terminal, and network-side equipment

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on December 29, 2023, with application number 202311874217.0 and invention name “Wireless Communication Method, Apparatus, Terminal and Network Side Equipment”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of communications, and more specifically, to a wireless communication method, apparatus, terminal, and network-side equipment. Background Art

[0004] Artificial Intelligence (AI) is widely used in various fields. Therefore, AI can be used to improve the network performance of fifth-generation (5G) mobile communication technology. Specifically, the main method is to enhance or replace existing algorithms or processing modules with neural network-based algorithms and AI models.

[0005] However, the terminal needs to consume a large amount of computing resources when performing AI model calculations, which is not only costly, but may also fail to complete the calculation on time due to insufficient resources. This not only reduces the performance of the terminal, but may also have a negative impact on network performance. Summary of the Invention

[0006] The embodiments of the present application provide a wireless communication method, apparatus, terminal, and network-side equipment, which can avoid the problem of reduced terminal performance caused by incompatibility between the AI ​​model and the terminal's resources.

[0007] In a first aspect, a wireless communication method is provided, comprising:

[0008] The terminal activates the first model under the first function;

[0009] During the activation time of the first model, the terminal performs a first operation based on a monitoring result of at least one of performance of the first model and resources of the terminal;

[0010] The first operation includes at least one of the following:

[0011] Continue to run the first model, reselect the model, deactivate the first model, deactivate the first function, and reselect the function.

[0012] In a second aspect, a wireless communication method is provided, including:

[0013] The network side device sends the model configuration of the first model to the terminal;

[0014] The model configuration of the first model includes at least one of the following:

[0015] an activation indication of the first model;

[0016] an instruction to monitor at least one of performance of the first model and resources of the terminal;

[0017] At least one of a first threshold value and a second threshold value corresponding to a first indicator for characterizing model performance, the first threshold value being greater than the second threshold value;

[0018] a third threshold value corresponding to a second indicator used to characterize a resource situation of the terminal;

[0019] The activation time of the first model.

[0020] According to a third aspect, a wireless communication device is provided, including:

[0021] an activation unit, used for activating the first model under the first function;

[0022] an execution unit, configured to execute a first operation based on a monitoring result of at least one of performance of the first model and resources of the terminal within an activation time of the first model;

[0023] The first operation includes at least one of the following:

[0024] Continue to run the first model, reselect the model, deactivate the first model, deactivate the first function, and reselect the function.

[0025] According to a fourth aspect, a wireless communication device is provided, including:

[0026] a communication unit, configured to send a model configuration of the first model to a terminal;

[0027] The model configuration of the first model includes at least one of the following:

[0028] an activation indication of the first model;

[0029] an instruction to monitor at least one of performance of the first model and resources of the terminal;

[0030] At least one of a first threshold value and a second threshold value corresponding to a first indicator for characterizing model performance, the first threshold value being greater than the second threshold value;

[0031] a third threshold value corresponding to a second indicator used to characterize a resource situation of the terminal;

[0032] The activation time of the first model.

[0033] In a fifth aspect, a terminal is provided, comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0034] In a sixth aspect, a terminal is provided, including a processor and a communication interface, wherein the processor is configured to:

[0035] Activate the first model under the first function;

[0036] performing a first operation based on a monitoring result of at least one of performance of the first model and resources of the terminal within an activation time of the first model;

[0037] The first operation includes at least one of the following:

[0038] Continue to run the first model, reselect the model, deactivate the first model, deactivate the first function, and reselect the function.

[0039] In the seventh aspect, a network side device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the second aspect are implemented.

[0040] In an eighth aspect, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is configured to:

[0041] Sending a model configuration of the first model to the terminal;

[0042] The model configuration of the first model includes at least one of the following:

[0043] an activation indication of the first model;

[0044] an instruction to monitor at least one of performance of the first model and resources of the terminal;

[0045] At least one of a first threshold value and a second threshold value corresponding to a first indicator for characterizing model performance, the first threshold value being greater than the second threshold value;

[0046] a third threshold value corresponding to a second indicator used to characterize a resource situation of the terminal;

[0047] The activation time of the first model.

[0048] In the ninth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented.

[0049] In the tenth aspect, a wireless communication system is provided, comprising: a terminal and a network side device, wherein the terminal can be used to execute the steps of the method described in the first aspect, and the network side device can be used to execute the steps of the method described in the second aspect.

[0050] In the eleventh aspect, a chip is provided, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method as described in the first aspect, or to implement the method as described in the second aspect.

[0051] In the twelfth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0052] In an embodiment of the present application, the wireless communication method includes: the terminal activates the first model under the first function; during the activation time of the first model, the terminal performs a first operation based on the monitoring result of at least one of the performance of the first model and the resources of the terminal; wherein the first operation includes at least one of the following: continuing to run the first model, reselecting the model, deactivating the first model, deactivating the first function, and reselecting the function. In this way, when the first function or the first model is not compatible with the resources of the terminal, the terminal can avoid the problem of the inherent performance of the terminal (such as encoding, decoding, measurement, etc.) being reduced or the resource utilization of the terminal being too low due to the terminal continuing to run the first model by executing the first operation, thereby ensuring the performance of the terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0054] FIG1 is an example of a communication system applicable to an embodiment of the present application.

[0055] FIG2 is an example of a structure of a neural network provided according to an embodiment of the present application.

[0056] FIG3 is an example of a neuron structure provided according to an embodiment of the present application.

[0057] FIG4 is an example of a principle of model-based CSI prediction provided according to an embodiment of the present application.

[0058] FIG5 is a schematic comparison diagram of the performance of predicting CSI at different future moments based on models provided according to an embodiment of the present application.

[0059] FIG6 is a schematic flowchart of a wireless communication method provided according to an embodiment of the present application.

[0060] FIG7 is a schematic flowchart of another wireless communication method provided according to an embodiment of the present application.

[0061] FIG8 is a schematic flowchart of function reselection with downward capability of a terminal according to an embodiment of the present application.

[0062] FIG9 is a schematic flowchart of a terminal performing capability-upward function reselection according to an embodiment of the present application.

[0063] FIG10 is a schematic flowchart of extending the activation time of a terminal according to an embodiment of the present application.

[0064] FIG11 is a schematic block diagram of a wireless communication device according to an embodiment of the present application.

[0065] FIG12 is a schematic block diagram of another wireless communication device provided according to an embodiment of the present application.

[0066] FIG13 is a schematic block diagram of a communication device provided according to an embodiment of the present application.

[0067] FIG14 is a schematic diagram of the hardware structure of a terminal provided according to an embodiment of the present application.

[0068] FIG15 is a schematic block diagram of a network-side device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0069] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0070] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0071] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result, etc. in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result, etc. based on the judgment result.

[0072] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the technology described can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) systems. thGeneration, 6G) communication system.

[0073] FIG1 is a schematic diagram of a communication system architecture provided in an embodiment of the present application.

[0074] As shown in FIG1 , the communication system architecture includes a terminal 11 and a network-side device 12 .

[0075] The terminal 11 may be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipborne equipment, pedestrian user equipment (PUE), smart home (home appliances with wireless communication functions, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM or self-service machine, etc. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. The vehicle-mounted device may also be referred to as a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application.

[0076] The network side device 12 may include an access network device.

[0077] Access network equipment may also be referred to as radio access network (RAN) equipment, radio access network functions, or radio access network units. Access network equipment may include base stations, wireless local area network (WLAN) access points (AS), or wireless fidelity (WiFi) nodes. Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B (home evolved Node B), Transmission Reception Point (TRP) or other appropriate terms in the field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.

[0078] In order to facilitate a better understanding of the embodiments of the present application, the technologies related to the present application are explained.

[0079] (1) Artificial intelligence

[0080] Artificial intelligence is currently being widely used in various fields. AI modules can be implemented in a variety of ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers.

[0081] FIG2 is an example of a structure of a neural network provided according to an embodiment of the present application.

[0082] As shown in Figure 2, the structure of the neural network includes an input layer, a hidden layer (also called a hidden layer), and an output layer. The input of the input layer is X1~X n , the output of the output layer is Y. It should be understood that this application uses a neural network as an example for illustration, but does not limit the specific type of AI module.

[0083] FIG3 is an example of a neuron structure provided according to an embodiment of the present application.

[0084] As shown in Figure 3, the neural network is composed of neurons. The output of the neuron is z, z = a1w1+…+a k w k +…+a K w K . Among them a1~a K is the input, w1~w K is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Activation functions include the Sigmoid function, the tanh function, the Rectified Linear Unit (ReLU) (also known as the linear rectification function), and so on.

[0085] Neural network parameters are optimized using optimization algorithms. An optimization algorithm is a type of algorithm that minimizes or maximizes an objective function (sometimes called a loss function). The objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, a neural network model f(.) is constructed. With the model, the predicted output f(x) can be obtained based on the input x, and the difference between the predicted value and the true value (f(x) - Y) can be calculated. This is the loss function. The goal is to find the appropriate values ​​W and b that minimize the value of this loss function. The smaller the loss value, the closer the AI ​​model is to the real world.

[0086] Optimization algorithms are typically based on the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two steps: forward propagation of signals and backward propagation of errors. During forward propagation, input samples are passed from the input layer, processed layer by layer through each hidden layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, the error back propagation phase begins. Error back propagation involves propagating the output error layer by layer through the hidden layers to the input layer in some form, distributing the error to all units in each layer. This error signal is then generated for each unit in each layer, which serves as the basis for adjusting the weights of each unit. This process of adjusting the weights of each layer, through forward propagation of signals and backward propagation of errors, is repeated over and over again. This process of continuous weight adjustment is the network's learning and training process. This process continues until the error in the network output is reduced to an acceptable level, or until a pre-set number of learning cycles has been completed.

[0087] Depending on the type of solution, the selected AI algorithm and the adopted AI model will also vary.

[0088] Generally speaking, the primary approach to improving 5G network performance with AI is to enhance or replace existing algorithms or processing modules with neural network-based algorithms and AI models. In specific scenarios, neural network-based algorithms and AI models can achieve better performance than deterministic algorithms. These neural networks include deep neural networks, convolutional neural networks, and recurrent neural networks. Using existing AI tools, neural networks can be built, trained, and validated.

[0089] Replacing modules in existing systems with AI / machine learning (ML) methods can effectively improve system performance.

[0090] It should be noted that the AI ​​model in the embodiments of the present application may also be referred to as an AI unit, an ML (machine learning) model, an ML unit, an AI structure, an AI feature, a machine learning model, a neural network, a neural network function, a neural network function, etc., or an AI model may also refer to a processing unit that can implement specific algorithms, formulas, processing procedures, capabilities, etc. related to AI, or an AI model may be a processing method, algorithm, function, module or unit for a specific data set, or an AI model may be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as a graphics processing unit (GPU), a neural network processing unit (NPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), etc. This application does not make specific limitations on this.

[0091] FIG4 is an example of a principle of model-based CSI prediction provided according to an embodiment of the present application.

[0092] As shown in FIG4, the historical CSI (for example, the CSI t K ~CSI t0) is input to the AI ​​model (i.e., CSI prediction model), which analyzes the time domain variation characteristics of the channel and outputs the future CSI (for example, CSI t N ~CSI t N+M ).

[0093] FIG5 is a schematic comparison diagram of the performance of predicting CSI at different future moments based on models provided according to an embodiment of the present application.

[0094] As shown in Figure 5, CSI prediction offers significant performance gains compared to non-prediction solutions. Furthermore, the achievable prediction accuracy (e.g., minimum mean squared error (MMSE)) varies depending on the future time of the prediction (e.g., 1ms to 5ms as shown in the figure).

[0095] Of course, in addition to the above-mentioned AI-based CSI prediction use cases, AI can also achieve one or more of the following use cases: CSI compression, positioning enhancement, beam management, load balancing, resource allocation, channel estimation, power amplifier nonlinear suppression, signal demodulation, etc.

[0096] However, running AI model calculations on a terminal consumes significant computing resources, which is not only costly but also potentially prevents the calculation from completing on time due to insufficient resources. This not only reduces terminal performance but can also negatively impact network performance. Solutions using AI models in communication systems often employ relatively simple monitoring methods. Typically, a single monitor is activated to monitor terminal or model performance, and then a model is selected or switched based on the monitoring results. However, model selection or switching based on a single monitoring result is often aggressive and fails to improve network performance while ensuring terminal performance. For example, if only model performance is monitored, the terminal's inherent performance (such as encoding, decoding, and measurement capabilities) may degrade or resource utilization may be excessively low. Furthermore, if only terminal performance is monitored, model performance may be too low or resource utilization may be too low. Furthermore, simply switching or selecting models fails to maximize the benefits of network performance from the functions or models running on the terminal. For example, a model may perform well but underutilize terminal resources.

[0097] In view of this, the present application proposes a wireless communication method, which can maximize the gain of the functions or models running on the terminal on network performance without interfering with the inherent performance of the terminal (such as encoding, decoding, measurement, etc.) by dynamically balancing the capabilities of the model and the resources of the terminal and enriching the operations performed by the terminal based on the monitoring results, thereby further improving the network performance.

[0098] The wireless communication method provided in the embodiments of the present application is described in detail below through some embodiments and their application scenarios in conjunction with the accompanying drawings.

[0099] FIG6 is a schematic flowchart of a wireless communication method 210 according to an embodiment of the present application.

[0100] As shown in FIG6 , the wireless communication method 210 may include at least part of the following contents:

[0101] S211: The terminal activates the first model under the first function.

[0102] Exemplarily, the first function may be any function based on AI or ML, for example, the first function may be a CSI prediction function\compression function.

[0103] Exemplarily, the first model may be any model based on AI or ML. For example, the first function may be a CSI prediction model\compression model.

[0104] For example, a function has models with different capabilities, arranged from highest to lowest. Models with higher capabilities require more terminal resources. Capabilities refer to the computational complexity and computing power of the model. Terminal resources refer to hardware resources such as peak power, graphics processing unit (GPU), central processing unit (CPU), memory, and heat dissipation.

[0105] Exemplarily, the terminal activating the first model may also be understood as: the terminal starting the first model, or the terminal running the first model.

[0106] S212: within the activation time of the first model, the terminal performs a first operation based on a monitoring result of at least one of performance of the first model and resources of the terminal;

[0107] The first operation includes at least one of the following:

[0108] Continue to run the first model, reselect the model, deactivate the first model, deactivate the first function, and reselect the function.

[0109] Exemplarily, the performed model reselection includes at least one of the following: performing a model reselection with downward capability or performing a model reselection with upward capability.

[0110] Exemplarily, the performing function reselection includes at least one of the following: performing function reselection with downward capability, and performing function reselection with upward capability.

[0111] In this embodiment, when the first function or the first model is not compatible with the resources of the terminal, the terminal can avoid the problem of the inherent performance of the terminal (such as encoding, decoding, measurement, etc.) being reduced or the resource utilization of the terminal being too low due to the terminal continuing to run the first model by executing the first operation, thereby ensuring the performance of the terminal. In addition, through the first operation, a dynamic balance can be achieved as much as possible between the performance of the model running on the terminal and the resources of the terminal, that is, without interfering with the inherent performance of the terminal (such as encoding, decoding, measurement, etc.), the gain of the function or model running on the terminal on network performance can be maximized, thereby further improving network performance. Therefore, the wireless communication method provided in the embodiment of the present application can improve network performance on the basis of ensuring terminal performance.

[0112] In some embodiments, before S211, the method 210 further includes:

[0113] The terminal receives a basic monitoring configuration (basic_monitoring_config) from a network-side device;

[0114] The basic monitoring configuration includes at least one of the following:

[0115] Window time or counter;

[0116] Basic remaining resource threshold.

[0117] To prevent excessive terminal resource load (for example, power consumption, GPU utilization, CPU utilization, GPU temperature, and CPU temperature) after enabling a function, which could lead to a decline in the terminal's inherent functions (such as encoding / decoding, measurement, and perception), the terminal activates a window time or counter T and a basic remaining resource threshold, Thresholdbasic. The window time or counter T can be flexibly configured, with Thresholdbasic being the only configuration. The terminal monitors its remaining resources (remaining computing power, remaining CPU / GPU power, power, and other indicators that can support AI model operation) within the preset time monitoring granularity. Each monitoring cycle, counter T decrements by 1 until T equals 0, or the monitoring period continues until the end of window time T. If the remaining resources or capabilities consistently exceed Thresholdbasis during each monitoring session, the terminal has no other functions to execute and can at least support the basic (e.g., minimum) AI model for this function.

[0118] It should be noted that the basic monitoring configuration, namely the window time or counter size and the basic remaining resource threshold Thresholdbasic, is related to the functionality or model. A functionality or model can have one or more basic monitoring configurations. The terminal can obtain the basic monitoring configuration during the process of establishing a connection with the network and trigger it through subsequent signaling, or can obtain the basic monitoring configuration directly through signaling, or can obtain the basic monitoring configuration when obtaining the functionality, or can obtain the basic monitoring configuration as model auxiliary information when obtaining the model.

[0119] It should be understood that this application does not specifically limit the role of the basic monitoring configuration.

[0120] For example, the basic monitoring configuration can be used by the terminal to determine the functions or models that can be activated, or can be used to determine whether to activate a certain function or model, or can be used to determine whether to send a request to a network device to obtain a certain function or model, or can be used to determine whether to send a request to a network device to request the activation of a function or model, or can be used to determine whether to report the monitoring results of the terminal's resources to the network side device.

[0121] In some embodiments, before S211, the method 210 further includes:

[0122] The terminal sends a first request to the network device, where the first request is used to request activation of the first function or request the network device to determine the first function;

[0123] The terminal receives a response to the first request from the network-side device, where the response to the first request includes an activation indication of the first function;

[0124] The terminal monitors the resources of the terminal to obtain a first resource monitoring result;

[0125] The terminal sends the first resource monitoring result to the network side device, and the first resource monitoring result is used by the network side device to determine the model configuration of the first model.

[0126] Exemplarily, driven by the service or wireless link environment, the terminal autonomously determines that the function (i.e., the first function, such as CSI prediction / compression) needs to be activated and / or the network-side device determines that the function needs to be activated to improve the current communication quality. The terminal initiates an activation request for the AI ​​function (i.e., the first request), and the network side sends activation signaling for the AI ​​function (i.e., a response to the first request).

[0127] Exemplarily, the function activation signaling includes the basic monitoring configuration, that is, the function activation signaling includes at least one of the following:

[0128] Window time or counter T;

[0129] Basic remaining resource threshold Thresholdbasic.

[0130] In some embodiments, before S211, the method 210 further includes:

[0131] The terminal receives a model configuration of the first model;

[0132] The model configuration of the first model includes at least one of the following:

[0133] an activation indication of the first model;

[0134] an instruction to monitor at least one of performance of the first model and resources of the terminal;

[0135] At least one of a first threshold value and a second threshold value corresponding to a first indicator for characterizing model performance, the first threshold value being greater than the second threshold value;

[0136] a third threshold value corresponding to a second indicator used to characterize a resource situation of the terminal;

[0137] The activation time of the first model.

[0138] Exemplarily, the model configuration of the first model includes at least one of the following:

[0139] 1. An activation instruction for the first model; for example, including at least one of the following:

[0140] information specifically indicating the first model;

[0141] The basic monitoring configuration is included as model auxiliary information.

[0142] 2. An indication to monitor at least one of the performance of the first model and the resources of the terminal.

[0143] 3. At least one of a first threshold value and a second threshold value corresponding to a first indicator used to characterize model performance, wherein the first threshold value is greater than the second threshold value.

[0144] For example, assume that the first threshold is denoted by A and the second threshold is denoted by a, where a is less than A. The detection result of the first indicator can be a specific numerical value or a variable value. Accordingly, A or a can also be a specific numerical value or a variable value. For example, if the detection result of the first indicator is SGCS, A can be configured to be 0.8, or it can be configured to be a 10% improvement over the previous SGCS.

[0145] 4. a third threshold value corresponding to a second indicator used to characterize the resource status of the terminal;

[0146] Exemplarily, the second indicator may be the total resource utilization of the terminal, and the third threshold may be the upper limit of the total resource utilization after the terminal activates the first function.

[0147] Exemplarily, the second indicator may be the remaining resources of the terminal, and the third threshold may be the lower bound of the remaining resources after the terminal activates the first function.

[0148] 5. The activation time of the first model.

[0149] Exemplarily, the activation time of the first model may be determined by the terminal according to specific services.

[0150] Exemplarily, the network-side device may determine the function requested by the terminal (ie, the first function).

[0151] 6. The basic monitoring configuration.

[0152] In some embodiments, the S212 includes:

[0153] The terminal performs the first operation based on any one of the first threshold value and the second threshold value, the first indicator, the second indicator, and the third threshold value.

[0154] Exemplarily, the terminal monitors the first indicator and the second indicator simultaneously to obtain a monitoring result of the first indicator and a monitoring result of the second indicator. Then, the terminal performs the first operation based on either the first threshold value or the second threshold value, the monitoring result of the first indicator, the monitoring result of the second indicator, and the third threshold value.

[0155] In this embodiment, the terminal dynamically adjusts the selected AI model based on the monitoring results of the model performance and the monitoring results of the terminal's resources, and even replaces the AI ​​function or even stops using it when the monitoring results of the terminal's resources are very poor. This can ensure the performance of the terminal, and also ensure the performance of the functions or models running on the terminal, and thus ensure network performance.

[0156] In addition, by monitoring the performance of the model and the resources of the terminal in parallel, it is helpful to balance the performance of the AI ​​model and the resource situation of the terminal.

[0157] In some embodiments, the terminal performs the first operation based on any one of the first threshold value and the second threshold value, the first indicator, the second indicator, and the third threshold value, which may be implemented as follows:

[0158] When the monitoring result of the first indicator is greater than or equal to the first threshold value and the monitoring result of the second indicator is less than or equal to the third threshold value, the terminal continues to run the first model; or

[0159] When the monitoring result of the first indicator is greater than or equal to the first threshold value and the monitoring result of the second indicator is greater than the third threshold value, the terminal reselects a model with a lower capability; or

[0160] When the monitoring result of the first indicator is less than the first threshold value and the monitoring result of the second indicator is greater than the third threshold value, the terminal reselects a model with a lower capability; or

[0161] When the monitoring result of the first indicator is less than the first threshold value and the monitoring result of the second indicator is less than or equal to the third threshold value, the terminal reselects a model with upward capability; or

[0162] When the monitoring result of the first indicator is less than or equal to the second threshold value and the monitoring result of the second indicator is less than or equal to the third threshold value, the terminal reselects a model with upward capability; or

[0163] When the monitoring result of the first indicator is less than or equal to the second threshold value and the monitoring result of the second indicator is greater than the third threshold value, the terminal performs at least one of the following: deactivating the first model, deactivating the first function, and reselecting a function with downward capability.

[0164] For example, assume that the first threshold is recorded as A, the second threshold is recorded as a, and a is smaller than A. The relationship between the monitoring result of the first indicator, the monitoring result of the second indicator, and the first operation can be shown in the following table.

[0165] Table 1

[0166] As shown in Table 1, as long as the first model is activated within the time period, the terminal can perform corresponding actions according to the monitoring results in Table 1.

[0167] In some embodiments, the S212 includes:

[0168] Determining, by the terminal, whether to monitor resources of the terminal based on either the first threshold value or the second threshold value and a monitoring result of the first indicator;

[0169] When monitoring resources of the terminal, the terminal performs the first operation based on a monitoring result of the second indicator and the third threshold value;

[0170] In the case of not monitoring the resources of the terminal, the terminal continues to run the first model.

[0171] Exemplarily, the terminal selects whether to trigger the terminal to monitor the resources of the terminal by comparing the first threshold value and any one of the second threshold values ​​and the monitoring result of the first indicator. When the terminal is triggered to monitor the resources of the terminal, the first operation is performed based on the monitoring result of the second indicator and the third threshold value. When the terminal is not triggered to monitor the resources of the terminal, the terminal continues to run the first model.

[0172] In this embodiment, the monitoring of terminal resources is triggered by the monitoring results of the model performance, and the selected AI model is dynamically adjusted based on the monitoring results of the terminal resources. Even when the monitoring results of the terminal resources are very poor, the AI ​​function is replaced or even stopped. This can ensure the performance of the terminal, the performance of the functions or models running on the terminal, and thus the network performance.

[0173] In addition, triggering the monitoring of terminal resources through the monitoring results of the model's performance is equivalent to sacrificing the terminal's resources in pursuit of extreme performance, maximizing the gain of the functions or models running on the terminal on network performance, and thus improving network performance.

[0174] It should be noted that for the method of triggering terminal resource monitoring through the monitoring results of the model's performance, as well as the method of monitoring the performance of the parallel monitoring model and the terminal's resources mentioned above, the network side device can indicate which monitoring method to use to the terminal according to the specific situation, or the terminal can decide which monitoring method to use by itself. This application does not make any specific restrictions on this.

[0175] In some embodiments, the method 210 further includes:

[0176] When the monitoring result of the first indicator is greater than the first threshold value, the terminal determines not to monitor the resources of the terminal.

[0177] In some embodiments, the terminal determines whether to monitor the resources of the terminal based on any one of the first threshold value and the second threshold value and the monitoring result of the first indicator, which can be implemented as follows:

[0178] When the monitoring result of the first indicator is less than or equal to the first threshold value, the terminal determines to monitor the resources of the terminal;

[0179] The terminal performs the first operation based on the monitoring result of the second indicator and the third threshold value, which can be implemented as follows:

[0180] When the monitoring result of the second indicator is greater than the third threshold value, the terminal reselects a model with a lower capability; or

[0181] When the detection result of the second indicator is less than or equal to the third threshold value, the terminal reselects a model with improved capability.

[0182] In some embodiments, the terminal determines whether to monitor the resources of the terminal based on any one of the first threshold value and the second threshold value and the monitoring result of the first indicator, which can be implemented as follows:

[0183] When the monitoring result of the first indicator is less than or equal to the second threshold value, the terminal determines to monitor the resources of the terminal;

[0184] The terminal performs the first operation based on the monitoring result of the second indicator and the third threshold value, which can be implemented as follows:

[0185] When the monitoring result of the second indicator is greater than the third threshold value, the terminal performs at least one of the following: deactivating the first model, deactivating the first function, and reselecting a function with a lower capability; or

[0186] When the monitoring result of the second indicator is less than or equal to the third threshold value, the terminal reselects a model with improved capability.

[0187] For example, assume that the first threshold is recorded as A, the second threshold is recorded as a, and a is smaller than A. The relationship between the monitoring result of the first indicator, the monitoring result of the second indicator, and the first operation can be shown in the following table.

[0188] Table 2

[0189] As shown in Table 2, as long as the first model is activated within the time period, the terminal can perform corresponding actions according to the monitoring results in Table 2.

[0190] In some embodiments, the S212 includes:

[0191] When the first model is the model with the highest capability under the first function and the monitoring result of the second indicator is less than or equal to the third threshold value, function reselection with higher capability is performed.

[0192] Exemplarily, if the model selected by the terminal is already the model with the greatest capability under the current function, and the total resource utilization of the terminal is still ≤ the third threshold (for example, B), it means that the total resource utilization of the terminal is low and it is impossible to reselect a model with higher capability under the first function. In this case, the terminal can reselect a function with higher capability.

[0193] In some embodiments, the method 210 further includes:

[0194] In a case where at least one of the first model, the first function, and the function with a lowered capability is deactivated, the terminal sends a second request to the network side device, where the second request is used to request to reduce the capability;

[0195] The terminal receives a response to the second request from the network-side device, where the response to the second request includes an activation indication of a second function, and a capability of the second function is less than a capability of the first function.

[0196] Exemplarily, when the first function is deactivated and / or function reselection with downward capability is performed, the terminal sends a second request to the network side device, and receives a response to the second request from the network side device.

[0197] In this embodiment, when at least one of the following is deactivated: the first model, the first function, and reselection of a function with downward capability, the terminal can perform function downgrade processing based on the current function (ie, the first function) to ensure the performance of the terminal.

[0198] In some embodiments, after the terminal sends the second request to the network-side device, the method 210 further includes:

[0199] The terminal monitors the resources of the terminal to obtain a second resource monitoring result;

[0200] The terminal sends the second resource monitoring result to the network side device, and the second resource monitoring result is used by the network side device to determine the model configuration of the second model under the second function.

[0201] In this embodiment, before the model is activated after the function is downgraded, the window time or counter T and the basic remaining resource threshold Thresholdbasic can be started to perform resource monitoring again. The reason for restarting the resource monitoring before the model is activated is that the utilization rate of other functions of the terminal, excluding the resources occupied by the AI ​​function, is still very high. Although the AI ​​function can be barely turned on, the performance is not up to standard. It is hoped that the total resource utilization of the terminal will be reduced by waiting for another window period. If the total resource utilization is still not released after waiting for a window period, the low resource utilization brought by the lower-level function (i.e., the second function) is exchanged for the basic model performance.

[0202] In some embodiments, the method 210 further includes:

[0203] In the case of reselecting a function with an upward capability, the terminal sends a third request to the network side device, where the third request is used to request an upgrade function;

[0204] The terminal receives a response to the third request from the network-side device, where the response to the third request includes an activation indication of a third function, and a capability of the third function is greater than a capability of the first function.

[0205] In this embodiment, when reselecting a function with increased capability, the terminal can perform a function upgrade based on the current function (i.e., the first function), enable the selection of a more powerful function, and thereby ensure that the function or model running on the terminal has a gain on network performance, thereby further improving network performance.

[0206] In this case, there is no need to enable resource monitoring before activating the upgraded model. The reason for not re-enabling resource monitoring before activating the upgraded model is that the total resource utilization of the terminal is very low, indicating that the terminal is currently idle and can use most of its resources for AI functions. Therefore, there is no need to wait for the terminal's resources to be released through a window period.

[0207] In some embodiments, the method 210 further includes:

[0208] Before the model activation time of the first model expires, if the terminal does not reselect the model activated by the terminal, the terminal sends a fourth request to the network side device, where the fourth request is used to request to extend the activation time of the first model;

[0209] The terminal receives a response to the fourth request from the network device, where the response to the fourth request includes a duration of the first model.

[0210] Exemplarily, if the model activated by the terminal remains unchanged within the activation time of the first model, the current model (i.e., the first model) is considered to be an adapted model. Before the activation time of the first model expires, the terminal can request the network side device to extend the activation time of the first model.

[0211] The following is an illustrative description of the wireless communication method provided in the embodiment of the present application from the perspective of interaction between the terminal and the network side device.

[0212] FIG7 is a schematic flowchart of a wireless communication method 220 according to an embodiment of the present application.

[0213] As shown in FIG7 , the wireless communication method 220 may include at least part of the following:

[0214] S221, the network side device sends the model configuration of the first model to the terminal;

[0215] The model configuration of the first model includes at least one of the following:

[0216] an activation indication of the first model;

[0217] an instruction to monitor at least one of performance of the first model and resources of the terminal;

[0218] At least one of a first threshold value and a second threshold value corresponding to a first indicator for characterizing model performance, the first threshold value being greater than the second threshold value;

[0219] a third threshold value corresponding to a second indicator used to characterize a resource situation of the terminal;

[0220] The activation time of the first model.

[0221] In some embodiments, before S221, the method 220 further includes:

[0222] The network side device sends basic monitoring configuration to the terminal;

[0223] The basic monitoring configuration includes at least one of the following:

[0224] Window time or counter;

[0225] Basic remaining resource threshold.

[0226] In some embodiments, the method 220 further includes:

[0227] The network side device receives a first request from the terminal, where the first request is used to request activation of a first function or request the network device to determine the first function;

[0228] The network-side device sends a response to the first request to the terminal, where the response to the first request includes an activation indication of the first function;

[0229] The network-side device receives a first resource monitoring result from the terminal, and the first resource monitoring result is used by the network-side device to determine a model configuration of the first model.

[0230] In some embodiments, the method 220 further includes:

[0231] The network side device receives a second request from the terminal, where the second request is used to request to reduce a function;

[0232] The network-side device sends a response to the second request to the terminal, where the response to the second request includes an activation indication of a second function, and a capability of the second function is less than a capability of the first function.

[0233] In some embodiments, the method 220 further includes:

[0234] The network side device receives a third request from the terminal, where the third request is used to request an upgrade function;

[0235] The network-side device sends a response to the third request to the terminal, where the response to the third request includes an activation indication of a third function, and a capability of the third function is greater than a capability of the first function.

[0236] In some embodiments, the method 220 further includes:

[0237] The network-side device receives a fourth request from the terminal, where the fourth request is used to request to extend the activation time of the first model;

[0238] The network-side device sends a response to the fourth request to the terminal, where the response to the fourth request includes the duration of the first model.

[0239] It should be understood that the interaction process of the method 220 may refer to the interaction process involved in the above method 210, and to avoid repetition, it will not be repeated here.

[0240] The wireless communication method provided in this application is described below with reference to specific embodiments.

[0241] Example 1:

[0242] FIG8 is a schematic flowchart of function reselection with downward capability of a terminal according to an embodiment of the present application.

[0243] As shown in Figure 8, the terminal sends a first request to the network side device, where the first request is used to request activation of the first function or request the network device to determine the first function; then, the terminal receives a response to the first request from the network side device, where the response to the first request includes an activation indication of the first function; the terminal monitors the resources of the terminal, and after obtaining a first resource monitoring result, sends the first resource monitoring result to the network side device. After receiving the first resource monitoring result, the network side device determines the model configuration of the first model under the first function based on the first resource monitoring result, and sends the model configuration of the first model to the terminal.

[0244] After receiving the model configuration of the first model, the terminal activates the first model based on the model configuration of the first model, and within the activation time of the first model, the terminal performs a first operation based on a monitoring result of at least one of performance of the first model and resources of the terminal;

[0245] The first operation includes at least one of the following:

[0246] Continue to run the first model, reselect the model, deactivate the first model, deactivate the first function, and reselect the function.

[0247] Furthermore, in the event of at least one of deactivating the first model, deactivating the first function, and reselecting a function with a lowered capability, the terminal sends a second request to the network-side device, the second request being used to request a lowered capability; then, the terminal receives a response to the second request from the network-side device, the response to the second request including an activation indication of a second function, the capability of the second function being less than the capability of the first function. The terminal monitors its resources to obtain a second resource monitoring result; upon receiving the second resource monitoring result, the network-side device determines a model configuration for the second model under the second function based on the second resource monitoring result, and sends the model configuration of the second model to the terminal.

[0248] Example 2:

[0249] FIG9 is a schematic flowchart of a terminal performing capability-upward function reselection according to an embodiment of the present application.

[0250] As shown in Figure 9, the terminal sends a first request to the network side device, where the first request is used to request activation of the first function or request the network device to determine the first function; then, the terminal receives a response to the first request from the network side device, where the response to the first request includes an activation indication of the first function; the terminal monitors the resources of the terminal, and after obtaining a first resource monitoring result, sends the first resource monitoring result to the network side device; after receiving the first resource monitoring result, the network side device determines the model configuration of the first model under the first function based on the first resource monitoring result, and sends the model configuration of the first model to the terminal.

[0251] After receiving the model configuration of the first model, the terminal activates the first model based on the model configuration of the first model, and within the activation time of the first model, the terminal performs a first operation based on a monitoring result of at least one of performance of the first model and resources of the terminal;

[0252] The first operation includes at least one of the following:

[0253] Continue to run the first model, reselect the model, deactivate the first model, deactivate the first function, and reselect the function.

[0254] Furthermore, when reselecting a function with increased capability, the terminal sends a third request to the network device, the third request being used to request a function upgrade; the terminal receives a response to the third request from the network device, the response to the third request including an activation indication of a third function, the capability of the third function being greater than the capability of the first function. The network device then sends a model configuration of the second model for the third function to the terminal.

[0255] Example 3:

[0256] FIG10 is a schematic flowchart of extending the activation time of a terminal according to an embodiment of the present application.

[0257] As shown in Figure 10, the terminal sends a first request to the network side device, where the first request is used to request activation of the first function or request the network device to determine the first function; then, the terminal receives a response to the first request from the network side device, where the response to the first request includes an activation indication of the first function; the terminal monitors the resources of the terminal, and after obtaining a first resource monitoring result, sends the first resource monitoring result to the network side device; after receiving the first resource monitoring result, the network side device determines the model configuration of the first model under the first function based on the first resource monitoring result, and sends the model configuration of the first model to the terminal.

[0258] After receiving the model configuration of the first model, the terminal activates the first model based on the model configuration of the first model, and within the activation time of the first model, the terminal performs a first operation based on a monitoring result of at least one of performance of the first model and resources of the terminal;

[0259] The first operation includes at least one of the following:

[0260] Continue to run the first model, reselect the model, deactivate the first model, deactivate the first function, and reselect the function.

[0261] Furthermore, before the model activation time of the first model expires, if the terminal does not reselect the model activated by the terminal, the terminal sends a fourth request to the network side device, and the fourth request is used to request to extend the activation time of the first model; the terminal receives a response to the fourth request from the network device, and the response to the fourth request includes the duration of the first model.

[0262] It should be understood that Figures 8 and 9 are merely examples of the present application and should not be construed as limiting the present application. For example, in other alternative embodiments, the response to the first request and the model configuration of the first model may be combined into a single signaling message for transmission. For another example, the first request and the first resource monitoring result may also be combined into a single signaling message for transmission. This application does not impose any specific limitations on this.

[0263] The wireless communication method provided in the embodiment of the present application can be executed by a wireless communication device. In the embodiment of the present application, the wireless communication device provided in the embodiment of the present application is described by taking the wireless communication method executed by the wireless communication device as an example.

[0264] FIG11 shows a schematic block diagram of a wireless communication device 300 according to an embodiment of the present application.

[0265] As shown in FIG11 , the wireless communication device 300 includes:

[0266] An activation unit 310, configured to activate a first model under a first function;

[0267] An execution unit 320 is configured to execute a first operation based on a monitoring result of at least one of performance of the first model and resources of the terminal within an activation time of the first model;

[0268] The first operation includes at least one of the following:

[0269] Continue to run the first model, reselect the model, deactivate the first model, deactivate the first function, and reselect the function.

[0270] In some embodiments, the apparatus 300 further includes a first receiving unit, and before the activation unit 310 activates the first model under the first function, the first receiving unit is configured to:

[0271] Receive basic monitoring configuration from network-side devices;

[0272] The basic monitoring configuration includes at least one of the following:

[0273] Window time or counter;

[0274] Basic remaining resource threshold.

[0275] In some embodiments, the apparatus 300 further includes a first communication unit, and before the activation unit 310 activates the first model under the first function, the first communication unit is configured to:

[0276] Sending a first request to a network-side device, where the first request is used to request activation of the first function or request the network device to determine the first function;

[0277] receiving a response to the first request from the network-side device, where the response to the first request includes an activation indication of the first function;

[0278] Monitoring the resources of the terminal to obtain a first resource monitoring result;

[0279] The first resource monitoring result is sent to the network side device, where the first resource monitoring result is used by the network side device to determine the model configuration of the first model.

[0280] In some embodiments, the apparatus 300 further includes a second receiving unit, and before the activation unit 310 activates the first model under the first function, the second receiving unit is configured to:

[0281] receiving a model configuration of the first model;

[0282] The model configuration of the first model includes at least one of the following:

[0283] an activation indication of the first model;

[0284] an instruction to monitor at least one of performance of the first model and resources of the terminal;

[0285] At least one of a first threshold value and a second threshold value corresponding to a first indicator for characterizing model performance, the first threshold value being greater than the second threshold value;

[0286] a third threshold value corresponding to a second indicator used to characterize a resource situation of the terminal;

[0287] The activation time of the first model.

[0288] In some embodiments, the execution unit 320 is specifically configured to:

[0289] The first operation is performed based on any one of the first threshold value and the second threshold value, the first indicator, the second indicator, and the third threshold value.

[0290] In some embodiments, the execution unit 320 is specifically configured to:

[0291] When the monitoring result of the first indicator is greater than or equal to the first threshold value and the monitoring result of the second indicator is less than or equal to the third threshold value, continue to run the first model; or

[0292] When the monitoring result of the first indicator is greater than or equal to the first threshold value and the monitoring result of the second indicator is greater than the third threshold value, reselecting a model with a lower capability; or

[0293] When the monitoring result of the first indicator is less than the first threshold value and the monitoring result of the second indicator is greater than the third threshold value, reselecting a model with a lower capability; or

[0294] When the monitoring result of the first indicator is less than the first threshold value and the monitoring result of the second indicator is less than or equal to the third threshold value, reselecting a model with improved capability; or

[0295] When the monitoring result of the first indicator is less than or equal to the second threshold value and the monitoring result of the second indicator is less than or equal to the third threshold value, reselecting a model with improved capability; or

[0296] When the monitoring result of the first indicator is less than or equal to the second threshold value and the monitoring result of the second indicator is greater than the third threshold value, perform at least one of the following: deactivate the first model, deactivate the first function, and reselect a function with downward capability.

[0297] In some embodiments, the execution unit 320 is specifically configured to:

[0298] Determining whether to monitor resources of the terminal based on either the first threshold value or the second threshold value and a monitoring result of the first indicator;

[0299] Performing the first operation based on a monitoring result of the second indicator and the third threshold value while monitoring resources of the terminal;

[0300] The first model continues to run without monitoring the resources of the terminal.

[0301] In some embodiments, the execution unit 320 is further configured to:

[0302] When the monitoring result of the first indicator is greater than the first threshold value, it is determined not to monitor the resources of the terminal.

[0303] In some embodiments, the execution unit 320 is specifically configured to:

[0304] When the monitoring result of the first indicator is less than or equal to the first threshold value, determining to monitor the resources of the terminal;

[0305] When the monitoring result of the second indicator is greater than the third threshold value, reselecting a model with a lower capability; or

[0306] When the detection result of the second indicator is less than or equal to the third threshold value, a model with improved capability is reselected.

[0307] In some embodiments, the execution unit 320 is specifically configured to:

[0308] When the monitoring result of the first indicator is less than or equal to the second threshold value, determining to monitor the resources of the terminal;

[0309] When the monitoring result of the second indicator is greater than the third threshold value, performing at least one of the following: deactivating the first model, deactivating the first function, or reselecting a function with a lower capability; or

[0310] When the monitoring result of the second indicator is less than or equal to the third threshold value, a model with improved capability is reselected.

[0311] In some embodiments, the execution unit 320 is specifically configured to:

[0312] When the first model is the model with the highest capability under the first function and the monitoring result of the second indicator is less than or equal to the third threshold value, function reselection with higher capability is performed.

[0313] In some embodiments, the apparatus 300 further includes a second communication unit configured to:

[0314] In the case of at least one of deactivating the first model, deactivating the first function, and reselecting a function with a lowered capability, sending a second request to the network side device, where the second request is used to request to reduce the capability;

[0315] A response to the second request is received from the network-side device, where the response to the second request includes an activation indication of a second function, and a capability of the second function is less than a capability of the first function.

[0316] In some embodiments, after sending the second request to the network-side device, the second communication unit is further configured to:

[0317] Monitoring the resources of the terminal to obtain a second resource monitoring result;

[0318] The second resource monitoring result is sent to the network side device, where the second resource monitoring result is used by the network side device to determine the model configuration of the second model under the second function.

[0319] In some embodiments, the apparatus 300 further includes a third communication unit configured to:

[0320] In the case of reselecting a function with an upward capability, sending a third request to the network-side device, wherein the third request is used to request an upgrade function;

[0321] A response to the third request is received from the network-side device, where the response to the third request includes an activation indication of a third function, and a capability of the third function is greater than a capability of the first function.

[0322] In some embodiments, the apparatus 300 further includes a fourth communication unit configured to:

[0323] Before the model activation time of the first model expires, if the terminal does not reselect the model activated by the terminal, sending a fourth request to the network side device, where the fourth request is used to request to extend the activation time of the first model;

[0324] A response to the fourth request is received from the network device, the response to the fourth request including a duration of the first model.

[0325] It should be understood that the wireless communication device 300 provided in the embodiment of the present application may correspond to the terminal in the method embodiment of the present application, and the above-mentioned (or other) operations or functions of each unit in the wireless communication device 300 are respectively for implementing the corresponding processes executed by the terminal in the method embodiment of Figure 6 or Figure 7. For the sake of brevity, they will not be repeated here.

[0326] FIG12 shows a schematic block diagram of a wireless communication device 400 according to an embodiment of the present application.

[0327] As shown in FIG12 , the wireless communication device 400 includes:

[0328] The communication unit 410 is configured to send a model configuration of the first model to the terminal;

[0329] The model configuration of the first model includes at least one of the following:

[0330] an activation indication of the first model;

[0331] an instruction to monitor at least one of performance of the first model and resources of the terminal;

[0332] At least one of a first threshold value and a second threshold value corresponding to a first indicator for characterizing model performance, the first threshold value being greater than the second threshold value;

[0333] a third threshold value corresponding to a second indicator used to characterize a resource situation of the terminal;

[0334] The activation time of the first model.

[0335] In some embodiments, before sending the model configuration of the first model to the terminal, the communication unit 410 is further configured to:

[0336] Sending basic monitoring configuration to the terminal;

[0337] The basic monitoring configuration includes at least one of the following:

[0338] Window time or counter;

[0339] Basic remaining resource threshold.

[0340] In some embodiments, before sending the model configuration of the first model to the terminal, the communication unit 410 is further configured to:

[0341] receiving a first request from the terminal, where the first request is used to request activation of a first function or request the network device to determine the first function;

[0342] sending a response to the first request to the terminal, where the response to the first request includes an activation indication of the first function;

[0343] A first resource monitoring result is received from the terminal, where the first resource monitoring result is used by the network-side device to determine a model configuration of the first model.

[0344] In some embodiments, the communication unit 410 is further configured to:

[0345] receiving a second request from the terminal, the second request being for requesting to reduce a function;

[0346] A response to the second request is sent to the terminal, where the response to the second request includes an activation indication of a second function, and a capability of the second function is less than a capability of the first function.

[0347] In some embodiments, the communication unit 410 is further configured to:

[0348] receiving a third request from the terminal, wherein the third request is used to request an upgrade function;

[0349] A response to the third request is sent to the terminal, where the response to the third request includes an activation indication of a third function, and a capability of the third function is greater than a capability of the first function.

[0350] In some embodiments, the communication unit 410 is further configured to:

[0351] receiving a fourth request from the terminal, the fourth request being used to request extension of activation time of the first model;

[0352] A response to the fourth request is sent to the terminal, where the response to the fourth request includes the duration of the first model.

[0353] It should be understood that the wireless communication device 400 provided in the embodiment of the present application may correspond to the network side device in the method embodiment of the present application, and the above-mentioned (or other) operations or functions of each unit in the wireless communication device 400 are respectively for implementing the corresponding processes of the network side device in the method embodiment of Figure 7. For the sake of brevity, they will not be repeated here.

[0354] The wireless communication device in the embodiments of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal or a network-side device. For example, the terminal can include but is not limited to the types of terminal 11 listed above, and the network-side device can include but is not limited to the types of network-side device 12 listed above. Other devices can be servers, network attached storage (NAS), etc., and are not specifically limited in the embodiments of the present application.

[0355] The wireless communication device provided in the embodiment of the present application can implement the various processes involved in the method embodiment of Figure 6 or Figure 7 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0356] FIG13 is an example of a communication device 500 provided in an embodiment of the present application.

[0357] As shown in Figure 13, the communication device 500 includes a processor 501 and a memory 502. The memory 502 stores a program or instruction that can be run on the processor 501. When the program or instruction is executed by the processor 501, it implements the various steps of the embodiment of the above-mentioned wireless communication method. For example, when the communication device 500 is a terminal, when the program or instruction is executed by the processor 501, it implements the various steps performed by the terminal in the embodiment of the above-mentioned wireless communication method, and can achieve the same technical effect. When the communication device 500 is a network-side device, when the program or instruction is executed by the processor 501, it implements the various steps performed by the network-side device in the embodiment of the above-mentioned wireless communication method, and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0358] The present application also provides a terminal including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps in the method embodiment shown in Figures 6 or 7. This terminal embodiment corresponds to the method embodiment on the terminal side, and each implementation process and implementation method of the aforementioned method embodiment are applicable to this terminal embodiment and can achieve the same technical effects.

[0359] The present application also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in FIG7 . This network-side device embodiment corresponds to the method embodiment on the network-side device side, and each implementation process and implementation method of the aforementioned method embodiment are applicable to this network-side device embodiment and can achieve the same technical effects.

[0360] FIG14 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

[0361] As shown in Figure 14, the terminal 600 includes but is not limited to: a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, a display unit 606, a user input unit 607, an interface unit 606, a memory 609 and at least some of the components of the processor 610.

[0362] Those skilled in the art will appreciate that the terminal 600 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 610 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system. The terminal structure shown in FIG14 does not constitute a limitation of the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be described in detail here.

[0363] It should be understood that in an embodiment of the present application, the input unit 604 may include a graphics processing unit (GPU) 6041 and a microphone 6042, and the graphics processor 6041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 606 may include a display panel 6061, and the display panel 6061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 607 includes a touch panel 6071 and at least one of other input devices 6072. The touch panel 6071 is also called a touch screen. The touch panel 6071 may include two parts: a touch detection device and a touch controller. Other input devices 6072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0364] In the embodiment of the present application, after receiving downlink data from a network-side device, the radio frequency unit 601 may transmit the data to the processor 610 for processing. Furthermore, the radio frequency unit 601 may send uplink data to the network-side device. Typically, the radio frequency unit 601 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.

[0365] The memory 609 can be used to store software programs or instructions and various data. The memory 609 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 609 may include a volatile memory or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct memory bus random access memory (DRRAM). The memory 609 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0366] Processor 610 may include one or at least two processing units. Optionally, processor 610 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 610.

[0367] The processor 610 is configured to:

[0368] Activate the first model under the first function;

[0369] performing a first operation based on a monitoring result of at least one of performance of the first model and resources of the terminal within an activation time of the first model;

[0370] The first operation includes at least one of the following:

[0371] Continue to run the first model, reselect the model, deactivate the first model, deactivate the first function, and reselect the function.

[0372] In this embodiment, when the first function or the first model is not compatible with the resources of the terminal, the terminal can avoid the problem of the inherent performance of the terminal (such as encoding, decoding, measurement, etc.) being reduced or the resource utilization of the terminal being too low due to the terminal continuing to run the first model by executing the first operation, thereby ensuring the performance of the terminal. In addition, the performance of the function or model running on the terminal can also be guaranteed, thereby ensuring network performance. In addition, through the first operation, a dynamic balance can be achieved as much as possible between the performance of the model running on the terminal and the resources of the terminal, that is, without interfering with the inherent performance of the terminal (such as encoding, decoding, measurement, etc.), the gain of the function or model running on the terminal on network performance can be maximized, thereby further improving network performance. Therefore, the wireless communication method provided in the embodiment of the present application can improve network performance on the basis of ensuring terminal performance.

[0373] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the method embodiment and achieve the same or corresponding technical effects. To avoid repetition, it will not be described here.

[0374] FIG15 is an example of a network-side device 700 provided in an embodiment of the present application.

[0375] As shown in Figure 15 , network-side device 700 includes an antenna 71, a radio frequency device 72, a baseband device 73, a processor 74, and a memory 75. Antenna 71 is connected to radio frequency device 72. In the uplink direction, radio frequency device 72 receives information via antenna 71 and sends the received information to baseband device 73 for processing. In the downlink direction, baseband device 73 processes the information to be transmitted and sends it to radio frequency device 72. Radio frequency device 72 processes the received information and then sends it through antenna 71.

[0376] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 73 , which includes a baseband processor.

[0377] The baseband device 73 may include, for example, at least one baseband board, on which at least two chips are provided, as shown in FIG9 , one of the chips being, for example, a baseband processor, which is connected to the memory 75 through a bus interface to call the program in the memory 75 and execute the corresponding process of the network side device in the above method embodiment.

[0378] The network side device may further include a network interface 76, which is, for example, a Common Public Radio Interface (CPRI).

[0379] Specifically, the network side device 700 of the embodiment of the present application also includes: instructions or programs stored in the memory 75 and executable on the processor 74. The processor 74 calls the instructions or programs in the memory 75 to execute the steps performed by each unit in the wireless communication device shown in Figure 12 and achieve the same technical effect. To avoid repetition, it will not be described here.

[0380] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned wireless communication method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0381] The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0382] An embodiment of the present application also provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned wireless communication method embodiment and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0383] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0384] An embodiment of the present application also provides a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the above-mentioned wireless communication method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0385] An embodiment of the present application also provides a communication system, including: a terminal and a network side device, wherein the terminal can be used to execute the steps performed by the terminal in the wireless communication method described above, and the network side device can be used to execute the steps performed by the network side device in the wireless communication method described above.

[0386] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0387] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned method-related embodiments can be implemented by means of a computer software product plus a necessary general-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for causing a terminal or network-side device to execute the methods described in each embodiment of the present application.

[0388] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. A wireless communication method, wherein, Including: The terminal activates a first model under a first function; During the activation time of the first model, the terminal performs a first operation based on at least one of the performance of the first model and the resources of the terminal; Wherein, the first operation includes at least one of the following: Continuing to run the first model, performing model reselection, deactivating the first model, deactivating the first function, performing function reselection.

2. The method according to claim 1, wherein, Before the terminal activates the first model under the first function, the method further includes: The terminal receives a basic monitoring configuration from a network-side device; Wherein, the basic monitoring configuration includes at least one of the following: Window time or counter; Basic remaining resource threshold.

3. The method according to claim 1 or 2, wherein, Before the terminal activates the first model under the first function, the method further includes: The terminal sends a first request to the network-side device, and the first request is used to request activation of the first function or request the network device to determine the first function; The terminal receives a response to the first request from the network-side device, and the response to the first request includes an activation indication of the first function; The terminal monitors the resources of the terminal to obtain a first resource monitoring result; The terminal sends the first resource monitoring result to the network-side device, and the first resource monitoring result is used for the network-side device to determine the model configuration of the first model.

4. The method according to any one of claims 1 to 3, wherein Before the terminal activates the first model under the first function, the method further includes: The terminal receives the model configuration of the first model; Wherein, the model configuration of the first model includes at least one of the following: An activation indication of the first model; An indication to monitor at least one of the performance of the first model and the resources of the terminal; At least one of a first threshold value and a second threshold value corresponding to a first metric for characterizing model performance, the first threshold value being greater than the second threshold value; A third threshold value corresponding to a second metric for characterizing the resource situation of the terminal; The activation time of the first model.

5. The method according to claim 4, wherein The terminal performs the first operation based on at least one of the performance of the first model and the resources of the terminal, including: The terminal performs the first operation based on any one of the first threshold value and the second threshold value, the first metric, the second metric, and the third threshold value.

6. The method according to claim 5, wherein The terminal performs the first operation based on any one of the first threshold value and the second threshold value, the first metric, the second metric, and the third threshold value, including: When the monitoring result of the first metric is greater than or equal to the first threshold value and the monitoring result of the second metric is less than or equal to the third threshold value, the terminal continues to run the first model; or When the monitoring result of the first metric is greater than or equal to the first threshold value and the monitoring result of the second metric is greater than the third threshold value, the terminal performs model reselection with reduced capabilities; or When the monitoring result of the first indicator is less than the first threshold value and the monitoring result of the second indicator is greater than the third threshold value, the terminal performs a model reselection with reduced capabilities; or When the monitoring result of the first indicator is less than the first threshold value and the monitoring result of the second indicator is less than or equal to the third threshold value, the terminal performs a model reselection with increased capabilities; or When the monitoring result of the first indicator is less than or equal to the second threshold value and the monitoring result of the second indicator is less than or equal to the third threshold value, the terminal performs a model reselection with increased capabilities; or When the monitoring result of the first indicator is less than or equal to the second threshold value and the monitoring result of the second indicator is greater than the third threshold value, the terminal performs at least one of the following: deactivating the first model, deactivating the first function, and performing a function reselection with reduced capabilities.

7. The method according to claim 4, wherein The terminal performs a first operation based on the monitoring result of at least one of the performance of the first model and the resources of the terminal, including: The terminal determines whether to monitor the resources of the terminal based on either the first threshold value or the second threshold value and the monitoring result of the first indicator; When monitoring the resources of the terminal, the terminal performs the first operation based on the monitoring result of the second indicator and the third threshold value; When not monitoring the resources of the terminal, the first model continues to run.

8. The method according to claim 7, wherein The terminal determines whether to monitor the resources of the terminal based on either the first threshold value or the second threshold value and the monitoring result of the first indicator, including: When the monitoring result of the first indicator is greater than the first threshold value, the terminal determines not to monitor the resources of the terminal.

9. The method according to claim 7 or 8, wherein The terminal determines whether to monitor the resources of the terminal based on either the first threshold value or the second threshold value and the monitoring result of the first indicator, including: When the monitoring result of the first indicator is less than or equal to the first threshold value, the terminal determines to monitor the resources of the terminal; Wherein, the terminal performs the first operation based on the monitoring result of the second indicator and the third threshold value, including: When the monitoring result of the second indicator is greater than the third threshold value, the terminal performs a model reselection with reduced capabilities; or When the detection result of the second indicator is less than or equal to the third threshold value, the terminal performs a model reselection with increased capabilities.

10. The method according to any one of claims 7 to 9, wherein The terminal determines whether to monitor the resources of the terminal based on either the first threshold value or the second threshold value and the monitoring result of the first indicator, including: When the monitoring result of the first indicator is less than or equal to the second threshold value, the terminal determines to monitor the resources of the terminal; Wherein, the terminal performs the first operation based on the monitoring result of the second indicator and the third threshold value, including: When the monitoring result of the second indicator is greater than the third threshold, the terminal performs at least one of the following: deactivating the first model, deactivating the first function, performing a function reselection with a lower capability; or When the monitoring result of the second indicator is less than or equal to the third threshold, the terminal performs a model reselection with a higher capability.

11. The method according to claim 4, wherein, The terminal performs a first operation based on the monitoring result of at least one of the performance of the first model and the resources of the terminal, including: When the first model is the model with the maximum capability under the first function and the monitoring result of the second indicator is less than or equal to the third threshold, perform a function reselection with a higher capability.

12. The method according to any one of claims 1 to 11, wherein, The method further includes: When at least one of deactivating the first model, deactivating the first function, and performing a function reselection with a lower capability is performed, the terminal sends a second request to the network-side device, and the second request is used to request a reduction in function; The terminal receives a response to the second request from the network-side device, and the response to the second request includes an activation indication of a second function, and the capability of the second function is less than the capability of the first function.

13. The method according to claim 12, wherein, After the terminal sends the second request to the network-side device, the method further includes: The terminal monitors the resources of the terminal to obtain a second resource monitoring result; The terminal sends the second resource monitoring result to the network-side device, and the second resource monitoring result is used for the network-side device to determine the model configuration of the second model under the second function.

14. The method according to any one of claims 1 to 11, wherein The method further includes: When performing a function reselection with a higher capability, the terminal sends a third request to the network-side device, and the third request is used to request an upgrade in function; The terminal receives a response to the third request from the network-side device, and the response to the third request includes an activation indication of a third function, and the capability of the third function is greater than the capability of the first function.

15. The method according to any one of claims 1 to 11, wherein The method further includes: Before the model activation time of the first model expires, when the terminal does not reselect the model activated by the terminal, the terminal sends a fourth request to the network-side device, and the fourth request is used to request an extension of the activation time of the first model; The terminal receives a response to the fourth request from the network device, and the response to the fourth request includes the duration of the first model.

16. A wireless communication method, wherein, Including: The network-side device sends the model configuration of the first model to the terminal; Wherein, the model configuration of the first model includes at least one of the following: The activation indication of the first model; An indication to monitor at least one of the performance of the first model and the resources of the terminal; At least one of a first threshold and a second threshold corresponding to a first indicator for characterizing model performance, and the first threshold is greater than the second threshold; A third threshold corresponding to a second indicator for characterizing the resource situation of the terminal; The activation time of the first model.

17. The method according to claim 16, wherein, Before the network-side device sends the model configuration of the first model to the terminal, the method further includes: The network-side device sends a basic monitoring configuration to the terminal; Wherein, the basic monitoring configuration includes at least one of the following: Window time or counter; Basic remaining resource threshold.

18. The method according to claim 16 or 17, wherein Before the network-side device sends the model configuration of the first model to the terminal, the method further includes: The network-side device receives a first request from the terminal, where the first request is used to request activation of the first function or request the network device to determine the first function; The network-side device sends a response to the first request to the terminal, and the response to the first request includes an activation indication of the first function; The network-side device receives a first resource monitoring result from the terminal, and the first resource monitoring result is used for the network-side device to determine the model configuration of the first model.

19. The method according to claim 18, wherein, The method further includes: The network-side device receives a second request from the terminal, where the second request is used to request reduction of a function; The network-side device sends a response to the second request to the terminal, and the response to the second request includes an activation indication of a second function, and the capability of the second function is less than the capability of the first function.

20. The method according to claim 18, wherein The method further includes: The network-side device receives a third request from the terminal, where the third request is used to request upgrade of a function; The network-side device sends a response to the third request to the terminal, and the response to the third request includes an activation indication of a third function, and the capability of the third function is greater than the capability of the first function.

21. The method according to any one of claims 16 to 18, wherein, The method further includes: The network-side device receives a fourth request from the terminal, where the fourth request is used to request extension of the activation time of the first model; The network-side device sends a response to the fourth request to the terminal, and the response to the fourth request includes the duration of the first model.

22. A wireless communication device, wherein, Includes: An activation unit, configured to activate a first model under a first function; An execution unit, configured to perform a first operation based on a monitoring result of at least one of the performance of the first model and the resources of the terminal during the activation time of the first model; Wherein, the first operation includes at least one of the following: Continuing to run the first model, performing model reselection, deactivating the first model, deactivating the first function, performing function reselection.

23. The device according to claim 22, wherein, The apparatus further includes a first receiving unit. Before the activation unit activates the first model under the first function, the first receiving unit is configured to: Receive a basic monitoring configuration from a network-side device; Wherein, the basic monitoring configuration includes at least one of the following: Window time or counter; Basic remaining resource threshold.

24. The apparatus according to claim 22 or 23, wherein, The apparatus further includes a first communication unit. Before the activation unit activates the first model, the first communication unit is configured to: Send a first request to a network-side device, where the first request is used to request activation of the first function or request the network device to determine the first function; Receive a response to the first request from the network-side device, and the response to the first request includes an activation indication of the first function; Monitor the resources of the terminal to obtain a first resource monitoring result; Send the first resource monitoring result to the network-side device, and the first resource monitoring result is used for the network-side device to determine the model configuration of the first model.

25. The apparatus according to any one of claims 22 to 24, wherein The device further includes a second receiving unit, and before the terminal activates the first model, the second receiving unit is configured to: Receive the model configuration of the first model; Wherein, the model configuration of the first model includes at least one of the following: The activation indication of the first model; An indication for monitoring at least one of the performance of the first model and the resources of the terminal; At least one of a first threshold and a second threshold corresponding to a first metric for characterizing model performance, where the first threshold is greater than the second threshold; A third threshold corresponding to a second metric for characterizing the resource situation of the terminal; The activation time of the first model.

26. The apparatus according to claim 25, wherein, The execution unit is specifically configured to: Execute the first operation based on any one of the first threshold and the second threshold, the first metric, the second metric, and the third threshold.

27. The device according to claim 25, wherein, The execution unit is specifically configured to: Determine whether to monitor the resources of the terminal based on any one of the first threshold and the second threshold and the monitoring result of the first metric; In the case of monitoring the resources of the terminal, execute the first operation based on the monitoring result of the second metric and the third threshold.

28. A wireless communication device, wherein, Includes: A communication unit, configured to send the model configuration of the first model to the terminal; Wherein, the model configuration of the first model includes at least one of the following: The activation indication of the first model; An indication for monitoring at least one of the performance of the first model and the resources of the terminal; At least one of a first threshold and a second threshold corresponding to a first metric for characterizing model performance, where the first threshold is greater than the second threshold; A third threshold corresponding to a second metric for characterizing the resource situation of the terminal; The activation time of the first model.

29. The device according to claim 28, wherein, Before the communication unit sends the model configuration of the first model to the terminal, it is further configured to: Send a basic monitoring configuration to the terminal; Wherein, the basic monitoring configuration includes at least one of the following: Window time or counter; Basic remaining resource threshold.

30. The device according to claim 28 or 29, wherein, Before the communication unit sends the model configuration of the first model to the terminal, it is further configured to: Receive a first request from the terminal, where the first request is used to request to activate a first function or request the network device to determine the first function; Send a response to the first request to the terminal, and the response to the first request includes the activation indication of the first function; Receive a first resource monitoring result from the terminal, where the first resource monitoring result is used for the network-side device to determine the model configuration of the first model.

31. A terminal, wherein, Includes a transceiver, a processor, and a memory, where the memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, it implements the wireless communication method according to any one of claims 1 to 15.

32. A network-side device, wherein, Includes a transceiver, a processor, and a memory, where the memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, it implements the wireless communication method according to any one of claims 16 to 21.

33. A readable storage medium, wherein, The program or instruction is stored on the readable storage medium, and when the program or instruction is executed by the processor, it implements the wireless communication method according to any one of claims 1 to 15, or implements the wireless communication method according to any one of claims 16 to 21.

Images