AI object management method and device, terminal and network side equipment

Abstract

The invention discloses an AI object management method and device, a terminal and network side equipment, and belongs to the technical field of communication, and the AI object management method comprises the steps that under the condition that the terminal determines to execute first operation, second operation is executed on target configuration; wherein the first operation comprises one of the following items: AI object activation, AI object deactivation, operation of returning to a non-AI object, and AI object switching; the AI object comprises an AI model or an AI function, and the AI object is used for at least one of radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction and handover failure (HOF) prediction; the target configuration is a configuration associated with the AI object, and the second operation is an operation corresponding to the first operation.

Description

Technical Field

[0001] This application belongs to the field of communication technologies, and particularly relates to an AI object management method, apparatus, terminal, and network-side device. Background Art

[0002] Currently, in a mobile communication network, tasks can be performed or services can be provided based on Artificial Intelligence (AI). For example, mobility management-related processes such as radio resource management (RRM) measurement prediction and event prediction are performed based on an AI model or AI function. However, in the related art, there is no corresponding solution for how to manage an AI model or AI function during the mobility management process, thus affecting the effectiveness of the prediction results based on the AI model or AI function. Summary of the Invention

[0003] Embodiments of this application provide an AI object management method, apparatus, terminal, and network-side device, which can perform corresponding operations on the configuration associated with an AI object when it is determined to perform management operations such as activating, deactivating, reverting to non-AI object operations, and switching on the AI object, which helps to ensure the effectiveness of the prediction results based on the AI object.

[0004] In a first aspect, an AI object management method is provided. The method includes:

[0005] When the terminal determines to perform a first operation, it performs a second operation on a target configuration;

[0006] Wherein, the first operation includes one of the following: AI object activation, AI object deactivation, reverting to non-AI object operations, and AI object switching; the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction;

[0007] The target configuration is the configuration associated with the AI object, and the second operation is an operation corresponding to the first operation.

[0008] In a second aspect, an AI object management apparatus is provided. The apparatus includes:

[0009] A first execution module, configured to perform a second operation on a target configuration when it is determined to perform a first operation;

[0010] Wherein, the first operation includes one of the following: activation of the AI object, deactivation of the AI object, fallback to non-AI object operation, and AI object switching; the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction;

[0011] The target configuration is the configuration associated with the AI object, and the second operation is the operation corresponding to the first operation.

[0012] In a third aspect, a method for managing an AI object is provided, and the method includes:

[0013] The network-side device performs a fifth operation, wherein the fifth operation includes at least one of the following:

[0014] Sending a target configuration to the terminal, wherein the target configuration is associated with an AI object, and the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction;

[0015] Receiving first information sent by the terminal, wherein the first information includes at least one of the following:

[0016] Second indication information for indicating a fourth operation performed by the terminal, and the fourth operation includes deactivation of the AI object, or switching of the AI object, or fallback to non-AI object operation;

[0017] RRM measurement prediction accuracy;

[0018] Prediction accuracy of the optimal N cells;

[0019] Prediction accuracy of the optimal M beams;

[0020] Prediction accuracy of measurement events;

[0021] Prediction accuracy of HOF;

[0022] Prediction accuracy of RLF;

[0023] Number or probability of abnormal events occurring within a first time period;

[0024] Handover delay or interruption duration within a second time period;

[0025] Number of handovers per unit time or within a third time period;

[0026] Identity of the AI object after handover.

[0027] Fourthly, an AI object management device is provided, which includes:

[0028] An execution module, configured to execute a fifth operation, where the fifth operation includes at least one of the following:

[0029] Sending a target configuration to a terminal, where the target configuration is associated with an AI object, and the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction;

[0030] Receiving first information sent by the terminal, where the first information includes at least one of the following:

[0031] Second indication information, used to indicate a fourth operation performed by the terminal, and the fourth operation includes AI object deactivation, AI object handover, or fallback to non-AI object operation;

[0032] RRM measurement prediction accuracy;

[0033] Prediction accuracy of the optimal N cells;

[0034] Prediction accuracy of the optimal M beams;

[0035] Prediction accuracy of measurement events;

[0036] Prediction accuracy of HOF;

[0037] Prediction accuracy of RLF;

[0038] Number or probability of abnormal events occurring within a first time period;

[0039] Handover delay or interruption duration within a second time period;

[0040] Number of handovers per unit time or within a third time period;

[0041] Identifier of the AI object after handover.

[0042] Fifthly, a terminal is provided, which includes a processor and a memory. The memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0043] Sixthly, a terminal is provided, which includes a processor and a communication interface. Wherein, the processor is configured to perform a second operation on a target configuration when it is determined to execute a first operation;

[0044] Wherein, the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, AI object switching; the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction;

[0045] The target configuration is the configuration associated with the AI object, and the second operation is the operation corresponding to the first operation.

[0046] In a seventh aspect, a network-side device is provided. The network-side device includes a processor and a memory. The memory stores a program or instructions that can run on the processor. When the program or instructions are executed by the processor, the steps of the method described in the third aspect are implemented.

[0047] In an eighth aspect, a network-side device is provided, including a processor and a communication interface. Wherein, the communication interface is used to perform a fifth operation, and the fifth operation includes at least one of the following:

[0048] Sending a target configuration to a terminal, where the target configuration is associated with an AI object, and the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction;

[0049] Receiving first information sent by the terminal, where the first information includes at least one of the following:

[0050] Second indication information for indicating a fourth operation performed by the terminal, where the fourth operation includes AI object deactivation, AI object switching, or fallback to non-AI object operation;

[0051] RRM measurement prediction accuracy;

[0052] Prediction accuracy of the optimal N cells;

[0053] Prediction accuracy of the optimal M beams;

[0054] Prediction accuracy of measurement events;

[0055] Prediction accuracy of HOF;

[0056] Prediction accuracy of RLF;

[0057] Number or probability of abnormal events occurring within a first time period;

[0058] Handover delay or interruption duration within a second time period;

[0059] The number of handovers within a unit time or a third time period;

[0060] The identifier of the AI object after the handover.

[0061] In a ninth aspect, there is provided an AI object management system, including: a terminal and a network side device. The terminal can be used to execute the steps of the AI object management method described in the first aspect, and the network side device can be used to execute the steps of the AI object management method described in the third aspect.

[0062] In a tenth aspect, there is provided a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements the steps of the method described in the first aspect, or implements the steps of the method described in the third aspect.

[0063] In an eleventh aspect, there is provided a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the method described in the first aspect, or implement the steps of the method described in the third aspect.

[0064] In a twelfth aspect, there is provided a computer program / program product, which includes a computer program or computer instruction. The computer program or computer instruction is executed by at least one processor to implement the steps of the method described in the first aspect, or implement the steps of the method described in the third aspect.

[0065] In the embodiments of the present application, when the terminal determines to execute a first operation, it performs a second operation on a target configuration; wherein, the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, AI object handover; the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction; the target configuration is the configuration associated with the AI object, and the second operation is an operation corresponding to the first operation. That is, the embodiments of the present application can perform corresponding operations on the configuration associated with the AI object when it is determined to perform management operations such as activation, deactivation, fallback to non-AI object operation, and handover on the AI object, which is beneficial to ensuring the effectiveness of the prediction results based on the AI object. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 is a block diagram of a wireless communication system to which the embodiments of the present application can be applied;

[0067] Figure 2aIt is a schematic structural diagram of a neural network provided by an embodiment of the present application;

[0068] Figure 2b It is a schematic structural diagram of a neuron provided by an embodiment of the present application;

[0069] Figure 3 It is a schematic diagram of an AI / ML function architecture provided by an embodiment of the present application;

[0070] Figure 4 It is a flowchart of an AI object management method provided by an embodiment of the present application;

[0071] Figure 5 It is a flowchart of another AI object management method provided by an embodiment of the present application;

[0072] Figure 6 It is a structural diagram of an AI object management device provided by an embodiment of the present application;

[0073] Figure 7 It is a structural diagram of another AI object management device provided by an embodiment of the present application;

[0074] Figure 8 It is a structural diagram of a communication device provided by an embodiment of the present application;

[0075] Figure 9 It is a structural diagram of a terminal provided by an embodiment of the present application;

[0076] Figure 10 It is a structural diagram of a network-side device provided by an embodiment of the present application. Detailed implementation manners

[0077] Next, the technical solutions in the embodiments of the present application will be clearly described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0078] The terms "first", "second", etc. in this application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances, so that the embodiments of this 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 category, and do not limit the number of objects. For example, the first object can be one or multiple. In addition, "or" in this application means at least one of the connected objects. For example, "A or B" covers three scenarios, namely, Scenario 1: including A and not including B; Scenario 2: including B and not including A; Scenario 3: including both A and B. The character " / " generally indicates that the related objects before and after are in an "or" relationship.

[0079] The term "indication" in this application can be either a direct indication (or an explicit indication) or an indirect indication (or an implicit indication). Among them, a direct indication can be understood as that the sender clearly informs the receiver of specific information, operations to be performed, request results, etc. in the sent indication; an indirect indication can be understood as that the receiver determines the corresponding information according to the indication sent by the sender, or makes a judgment and determines the operations to be performed or request results, etc. according to the judgment result.

[0080] It is worth noting that the technology described in the embodiments of this application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, and 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 this application are often used interchangeably, and the described technology can be used not only in the systems and radio technologies mentioned above, but also in other systems and radio technologies. The following description describes the New Radio (NR) system for example purposes, and uses NR terms in most of the following descriptions, but these technologies can also be applied to systems other than the NR system, such as the 6th generation (6 thGeneration, 6G) communication system.

[0081] Figure 1Block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. Among them, the terminal 11 can be a mobile phone, a tablet personal computer, a laptop computer, a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device, a flight vehicle, a vehicle user equipment (VUE), a shipborne device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication functions, such as refrigerators, TVs, washing machines, or furniture, etc.), a game console, a personal computer (PC), a teller machine, or a self-service machine, etc. Wearable devices include: smart watches, smart bracelets, smart earphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart ankle chains, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle user equipment can also be referred to as a vehicle terminal, a vehicle controller, a vehicle module, a vehicle component, a vehicle chip, or a vehicle unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. Among them, the access network device can also be referred to as a radio access network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a wireless local area network (WLAN) access point (AP), or a wireless fidelity (WiFi) node, etc.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, Transmission Reception Point (TRP), or some other suitable term in the art. As long as the same technical effect is achieved, the base station is not limited to specific technical terms. It should be noted that in the embodiments of this application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0082] The core network device may include, but is not limited to, at least one of the following: core network node, core network function, Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (L-NEF), Binding Support Function (BSF), Application Function (AF), etc. It should be noted that in the embodiments of this application, only the core network devices in the NR system are taken as examples for introduction, and the specific types of core network devices are not limited.

[0083] For ease of understanding, some content related to the embodiments of this application is described below:

[0084] I. Artificial Intelligence (AI)

[0085] Artificial intelligence (AI) has currently found extensive applications in various fields. Incorporating artificial intelligence into wireless communication networks to significantly improve technical indicators such as throughput, latency, and user capacity is an important task for future wireless communication networks. There are various implementation methods for the AI module, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. This application takes neural networks as an example for illustration, but does not limit the specific type of the AI module.

[0086] Exemplarily, a neural network can be as Figure 2a shown. A neural network is composed of neurons, and each neuron can be as Figure 2b shown. Among them, a1, a2, …, aK are inputs, w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include Sigmoid, tanh, Rectified Linear Unit (ReLU), and so on.

[0087] The parameters of the neural network are optimized through gradient optimization algorithms. Gradient optimization algorithms are a class of algorithms that minimize or maximize the objective function (also known as the loss function), and the objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we construct a neural network model f(.). After having the model, according to the input x, we can obtain the predicted output f(x), and we can calculate the gap between the predicted value and the true value (f(x) - Y), which is the loss function. The goal is to find the appropriate W and b to minimize the value of the above loss function. Among them, the smaller the loss value, the closer the model is to the real situation.

[0088] Currently, common optimization algorithms are basically based on the error Back Propagation (BP) algorithm. The basic idea of the BP algorithm is that the learning process consists of two processes: the forward propagation of signals and the backward propagation of errors. During forward propagation, the input samples are input 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, it enters the stage of backward propagation of errors. The backward propagation of errors is to reverse the output error through the hidden layer in a certain form layer by layer to the input layer, and distribute the error to all units of each layer, thereby obtaining the error signals of each layer of units. This error signal is used as the basis for correcting the weights of each unit. This process of adjusting the weights of each layer in the forward propagation of signals and the backward propagation of errors is carried out cyclically. The process of continuously adjusting the weights is also the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until a pre-set number of learning times is reached.

[0089] Common optimization algorithms include Gradient Descent, Stochastic Gradient Descent (SGD), mini-batch gradient descent, Momentum, Nesterov (specifically, Stochastic Gradient Descent with Momentum), Adaptive Gradient descent (Adagrad), Adadelta, Root Mean Square Propagation (RMSprop), Adaptive Moment Estimation (Adam), etc.

[0090] When these optimization algorithms perform backpropagation of errors, they all calculate the derivative / partial derivative of the current neuron based on the error / loss obtained from the loss function, and then, considering factors such as the learning rate and the previous gradient / derivative / partial derivative, obtain the gradient, which is then passed to the previous layer.

[0091] II. AI Unit / AI Model

[0092] The AI unit / AI model in the embodiments of this application can also be referred to as a Machine Learning (ML) model, ML unit, AI structure, AI function, AI feature, machine learning model, neural network, neural network function, neural network capability, etc. Or the above AI unit / AI model can also refer to a processing unit that can implement specific algorithms, formulas, processing flows, capabilities, etc. related to AI. Or the AI unit / AI model can be a processing method, algorithm, function, module, or unit for a specific dataset. Or the AI unit / AI model can be a processing method, algorithm, function, module, or unit running on AI / ML-related hardware such as GPUs, NPUs, TPUs, ASICs, etc. The embodiments of this application do not make specific limitations in this regard. Optionally, the specific dataset includes at least one of the input and output of the AI unit / AI model.

[0093] Optionally, the identifier of the AI unit / AI model can be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or the identifier of a specific dataset associated with the AI unit / AI model, or the identifier of a specific scenario, environment, channel characteristic, or device related to AI / ML, or the identifier of a function, feature, capability, or module related to AI / ML. The embodiments of this application do not make specific limitations in this regard.

[0094] AI functionality: That is, an AI algorithm function that can include multiple AI models.

[0095] III. AI / ML Architecture (Framework)

[0096] The air interface AI project of Release 18 studied AI / ML frameworks, such as Figure 3 shown below. The main processes are as follows:

[0097] Data Collection: Responsible for providing input data to Model Training, Management, and Inference;

[0098] Model Training: Responsible for performing AI / ML model training, validation, and testing. Also responsible for data preparation, i.e., data preprocessing, conversion to a specific format, etc.;

[0099] Management: Responsible for model selection / activation / deactivation / switching / rollback, etc.;

[0100] Inference: Responsible for providing the output after applying the AI / ML model or AI / ML function;

[0101] Model Storage: Responsible for saving the trained / updated model

[0102] Model Transfer / Delivery: Responsible for delivering the AI / ML model to the inference function node.

[0103] IV. RRM Measurement Reporting

[0104] The measurement configuration mainly consists of a measurement object, a reporting configuration, and a measurement identifier (ID);

[0105] Measurement Object: That is, the frequency point to be measured

[0106] Report Configuration (ReportConfig): It includes reporting criteria (periodic / event-triggered); reference signal type (Synchronous Signal Block (SSB) / Channel State Information Reference Signal (CSI-RS)), measurement reporting quantities (any combination of Reference Signal Receiving Power (RSRP) / Reference Signal Received Quality (RSRQ) / Signal to Interference Plus Noise Ratio (SINR)); whether to report beam measurement results, the maximum number of beams that can be reported, etc.;

[0107] Measurement Identifier (measId): It is used to associate a measurement object with a reporting configuration. A measurement object can be associated with multiple reporting configurations, and a reporting configuration can be associated with multiple measurement objects.

[0108] Optionally, the three can be associated together in the following way:

[0109]

[0110] The reporting configuration can include event-triggered reporting. The events defined in NR can be seen in Table 1, including the following events:

[0111] Table 1

[0112]

[0113]

[0114] Taking event A3 as an example, the meanings of the parameters for the entry condition and the departure condition are as follows:

[0115] Mn: Neighboring cell measurement result without considering any offset;

[0116] Ofn: Neighboring cell measurement object specific offset;

[0117] Ocn: Neighboring cell specific offset at the cell level;

[0118] Mp: SpCell (Primary Serving Cell) measurement result without considering any offset;

[0119] Ofp: SpCell measurement object specific offset;

[0120] Ocp: SpCell specific offset at the cell level;

[0121] Hys: Hysteresis parameter of the event;

[0122] Off: Offset parameter of the event.

[0123] If the reporting type is event-triggered reporting, in order to avoid frequent reporting or ping-pong handover, the base station configures the trigger time (timeToTrigger) parameter for each event. If the L3 filtered signal quality of one or more candidate cells meets the entry condition of the event within the timeToTrigger time, a measurement report is triggered;

[0124] For conditional handover, the UE uses the cell that meets the condition as the trigger cell and selects one to perform conditional reconfiguration in the trigger cell.

[0125] V. Conditional Handover

[0126] Conditional handover means that the network pre-configures multiple candidate cells for the UE, and the UE evaluates the execution conditions of the candidate cells and switches to the corresponding cell when the conditions are met. The execution conditions may include one or two trigger conditions.

[0127] Taking the parameters in NR as an example:

[0128] condReconfigId indicates the conditional reconfiguration ID; condExecutionCond is used to configure the execution conditions for the change of the Primary Cell (PCell), and condRRCReconfig is used to configure the configuration parameters of the target Master CellGroup (MCG). The three parameters correspond to a group of candidate cell configurations for conditional reconfiguration of a candidate PCell, as follows:

[0129]

[0130] The above execution conditions are the measurement events configured in the reporting configuration associated with MeasId. For conditional handover, the measurement events support conditional handover event A3 (condEventA3), conditional handover event A4 (condEventA4), or conditional handover event A5 (condEventA5), and their judgment conditions are the same as those of A3, A4, and A5 above. If the L3 filtered signal quality of one or more candidate cells meets the entry condition of the event within the timeToTrigger time, the UE uses the cell that meets the condition as the trigger cell and selects one to perform conditional reconfiguration in the trigger cell.

[0131] The following combines the accompanying drawings and details the AI object management method provided by the embodiments of the present application through some embodiments and their application scenarios.

[0132] Please refer to Figure 4 , Figure 4 which is a flowchart of an AI object management method provided by an embodiment of the present application. This method can be executed by a terminal, such as Figure 4 shown, and includes the following steps:

[0133] Step 401: When the terminal determines to perform a first operation, it performs a second operation on a target configuration;

[0134] Wherein, the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, AI object switching; the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction;

[0135] The target configuration is the configuration associated with the AI object, and the second operation is the operation corresponding to the first operation.

[0136] In this embodiment, the above-mentioned AI object activation, that is, activating the AI object. In this case, the terminal starts to use the AI object for prediction.

[0137] The above-mentioned AI object deactivation, that is, deactivating the AI object. In this case, the terminal stops or pauses using the AI object for prediction.

[0138] The above-mentioned fallback to non-AI object operation, that is, stopping or pausing using the AI object for inference or prediction and using the operation of the non-AI object. For example, stopping RRM measurement prediction based on the AI object and performing RRM measurement, or stopping the evaluation of measurement event prediction for triggering measurement reporting based on the AI object and performing the evaluation of the measurement event to determine whether to trigger measurement reporting.

[0139] The above-mentioned AI object switching, that is, switching the AI object. In this case, the terminal stops or pauses using the AI object before switching for inference or prediction and uses the AI object after switching for prediction.

[0140] It should be noted that in the embodiment of the present application, prediction based on the AI object can also be referred to as inference based on the AI object.

[0141] The above target configuration is the configuration associated with the above AI object. Exemplarily, the above target configuration may be a configuration related to mobility management. In some alternative embodiments, the target configuration includes at least one of the following: measurement configuration, measurement identifier (ID), measurement object, and reporting configuration.

[0142] The above second operation is an operation corresponding to the first operation. Exemplarily, if the first operation is the activation of an AI object, the above second operation may be the activation of the target configuration. That is, if the terminal activates the AI object, the terminal activates the configuration associated with the AI object to ensure the effective application of the prediction result of the activated AI object. If the first operation is the deactivation of an AI object, the above second operation may be the deactivation of the target configuration. That is, if the terminal deactivates the AI object, the terminal deactivates the configuration associated with the AI object to avoid processing related to the deactivated AI object. If the first operation is the switching of an AI object, the above second operation may be the switching of the target configuration. For example, if the terminal switches from activating the first AI object to activating the second AI object, the terminal switches to activating the target configuration associated with the second AI object. If the first operation is to fallback to a non-AI object operation, the above second operation may be to deactivate the configuration related to the AI object in the target configuration and activate the configuration unrelated to the AI object in the target configuration. For example, if the terminal determines to fallback to a non-AI object operation, the terminal stops evaluating the prediction event configured in the target configuration and evaluates the measurement event configured in the target configuration to ensure that the terminal can communicate normally without AI.

[0143] In the embodiments of the present application, when the terminal determines to execute the first operation, it performs the second operation on the target configuration. Among them, the first operation includes one of the following: activation of an AI object, deactivation of an AI object, fallback to a non-AI object operation, and switching of an AI object. The AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: prediction of radio resource management (RRM) measurement, prediction of a target cell, prediction of a measurement event, prediction of radio link failure (RLF), and prediction of handover failure (HOF). The target configuration is the configuration associated with the AI object, and the second operation is the operation corresponding to the first operation. That is, the embodiments of the present application can perform corresponding operations on the configuration associated with the AI object when it is determined to perform management operations such as activation, deactivation, fallback to a non-AI object operation, and switching on the AI object, which is beneficial to ensuring the effectiveness of the prediction result based on the AI object.

[0144] Optionally, when the terminal determines to execute the first operation, performing the second operation on the target configuration includes at least one of the following:

[0145] When the terminal determines to activate the AI object, it activates the target configuration;

[0146] When the terminal determines to deactivate the AI object, it deactivates the target configuration;

[0147] When the terminal determines to perform an operation of reverting to a non-AI object, it stops evaluating the prediction event configured for the target configuration and evaluates the measurement event configured for the target configuration;

[0148] When the terminal determines to perform an AI object switch, it carries the prediction result based on the switched AI object in the measurement report associated with the target configuration, where the target configuration is the configuration associated with the switched AI object.

[0149] The following illustrates this embodiment with examples:

[0150] If the terminal determines to activate the AI object, for example, the terminal receives the indication information for activating the AI object sent by the network-side device, the terminal can activate the AI object and activate the measurement configuration, measurement identifier, measurement object, or reporting configuration associated with the AI object. For example, it reports the prediction result of the AI object based on the reporting configuration associated with the AI object, so that the terminal can use the activated AI object for reasoning and report the inferred prediction result to the network-side device according to the reporting configuration associated with the AI object, or perform conditional switching based on the prediction result, etc., to ensure the effective application of the prediction result of the activated AI object.

[0151] If the terminal determines to deactivate the AI object, for example, the terminal receives the indication information for deactivating the AI object sent by the network-side device, the terminal can deactivate the AI object and deactivate the measurement configuration, measurement identifier, measurement object, or reporting configuration associated with the AI object. For example, it stops reporting the prediction result based on the AI object according to the reporting configuration associated with the AI object, or stops evaluating the prediction event configured by the reporting configuration associated with the AI object, so that the terminal can stop using the deactivated AI object for reasoning and stop reporting the prediction result to the network-side device to avoid invalid reporting.

[0152] If the terminal determines to perform an operation to fallback to a non-AI object, for example, if the terminal receives a fallback indication message sent by a network-side device, the terminal deactivates the AI object, stops evaluating the prediction events configured by the measurement configuration, measurement identifier, or reporting configuration associated with the measurement object associated with the AI object, and evaluates the measurement events configured by the measurement configuration, measurement identifier, or reporting configuration associated with the measurement object associated with the AI object; or, the terminal deactivates the AI object, stops evaluating the prediction events configured by the reporting configuration associated with the AI object, and evaluates the measurement events configured by the reporting configuration associated with the AI object, so that the terminal can stop reporting prediction results or perform a handover according to the prediction results, and fallback to the reporting or conditional handover operation of the non-AI object, which can ensure that the terminal can communicate normally without AI.

[0153] If the terminal determines to perform an AI object handover, for example, if the terminal receives an AI object handover indication message sent by a network-side device, the terminal can stop making predictions using the AI object before the handover, make predictions using the AI object after the handover, and carry the prediction results based on the AI object after the handover in the measurement report associated with the measurement configuration, measurement identifier, measurement object, or reporting configuration associated with the AI object after the handover, so that the terminal can perform measurement reporting or conditional handover using the reporting configuration associated with the AI object after the handover, to avoid inconsistent understanding of the prediction result reporting or conditional handover behavior between the network and the terminal.

[0154] It should be noted that for measurement events, the terminal determines whether the measurement events are satisfied according to the measurement results; for prediction events, the terminal determines whether the prediction events are satisfied according to the prediction results. Exemplarily, the above prediction events may include, but are not limited to, at least one of prediction event A1 to prediction event I1. Among them, the definitions of the above prediction events A1 to prediction event I1 can be respectively referred to the definitions of the foregoing event A1 (Event A1) to event I1 (Event I1), which will not be elaborated here.

[0155] Optionally, the activation of the target configuration includes at least one of the following:

[0156] When the periodic reporting condition or reporting trigger event associated with the first reporting configuration is satisfied, at least one of the measurement result and the prediction result is carried in the measurement report associated with the first reporting configuration;

[0157] When the prediction event associated with the first reporting configuration for triggering conditional handover is satisfied, perform conditional handover;

[0158] Wherein, the first reporting configuration is the reporting configuration associated with the target configuration, or the first reporting configuration is the reporting configuration in the target configuration.

[0159] In this embodiment, when the above-mentioned target configuration includes a measurement configuration, a measurement identifier, or a measurement object, the above-mentioned first reporting configuration is the reporting configuration associated with the target configuration; when the above-mentioned target configuration includes a reporting configuration, the first reporting configuration is the reporting configuration in the target configuration. It can be understood that when the target configuration only includes a reporting configuration, the above-mentioned first reporting configuration is the above-mentioned target configuration.

[0160] The above-mentioned reporting trigger event may include a measurement event for triggering a measurement report or a prediction event for triggering a measurement report; for a measurement event for triggering a measurement report, the terminal determines whether the measurement event for triggering a measurement report is satisfied according to the measurement result, and triggers reporting when it is satisfied; for a prediction event for triggering a measurement report, the terminal determines whether the prediction event for triggering a measurement report is satisfied according to the prediction result, and triggers reporting when it is satisfied.

[0161] Exemplarily, the above-mentioned measurement result may include an RRM measurement result. For example, it is a measurement value of the cell signal quality of at least one of the serving cell and neighboring cells; the above-mentioned prediction result may include at least one of an RRM measurement prediction result, a target cell prediction result, a measurement event prediction result, an RLF prediction result, and an HOF prediction result. The above-mentioned RRM measurement prediction result, for example, is a predicted value of the cell signal quality of at least one of the serving cell and neighboring cells.

[0162] In some optional embodiments, the above-mentioned measurement report also carries a measurement identifier, and the above-mentioned measurement result may be the measurement result of the measurement object associated with the measurement identifier.

[0163] For the above-mentioned prediction event for triggering conditional handover, it is evaluated whether the prediction event for triggering conditional handover is satisfied based on the prediction result, and conditional handover is triggered when it is satisfied. Exemplarily, the above-mentioned prediction event for triggering conditional handover may include at least one of a conditional handover prediction event A3, a conditional handover prediction event A4, and a conditional handover prediction event A5. Among them, the definitions of the above-mentioned conditional handover prediction event A3, conditional handover prediction event A4, and conditional handover prediction event A5 may refer to the definitions of the foregoing conditional handover event A3 (condEventA3), conditional handover event A4 (condEventA4), and conditional handover event A5 (condEventA5) respectively, which will not be elaborated here.

[0164] Optionally, deactivating the above-mentioned target configuration includes:

[0165] Stopping the reporting of the measurement report associated with the first reporting configuration;

[0166] Or

[0167] When the periodic reporting condition or reporting trigger event associated with the first reporting configuration is satisfied, only the measurement results are carried in the measurement report associated with the first reporting configuration;

[0168] Or

[0169] When a prediction event is configured in the first reporting configuration, the evaluation of the prediction event is stopped;

[0170] Or

[0171] When a prediction event and a measurement event are configured in the first reporting configuration, the evaluation of the prediction event is stopped, and the evaluation of the measurement event is performed;

[0172] Wherein, the first reporting configuration is the reporting configuration associated with the target configuration, or the first reporting configuration is the reporting configuration in the target configuration.

[0173] In this embodiment, when the above target configuration includes a measurement configuration, a measurement identifier or a measurement object, the above first reporting configuration is the reporting configuration associated with the target configuration; when the above target configuration includes a reporting configuration, the first reporting configuration is the reporting configuration in the target configuration. It can be understood that when the target configuration only includes a reporting configuration, the above first reporting configuration is the above target configuration.

[0174] The above stopping the reporting of the measurement report associated with the first reporting configuration may include stopping triggering the periodic reporting of the measurement report associated with the first reporting configuration, or stopping evaluating the measurement event or prediction event used to trigger the reporting of the measurement report associated with the first reporting configuration.

[0175] Exemplarily, the above measurement results may include RRM measurement results. For example, the measured values of the cell signal quality of at least one of the serving cell and neighboring cells. In some alternative embodiments, the above measurement report also carries a measurement identifier, and the above measurement results may be the measurement results of the measurement object associated with the measurement identifier.

[0176] The above prediction event is used for evaluation based on the prediction result. Among them, the above prediction event may include, but is not limited to, at least one of a prediction event for triggering measurement reporting and a prediction event for triggering conditional handover.

[0177] The above measurement event is used for evaluation based on the measurement result. Among them, the above measurement event may include at least one of a measurement event for triggering measurement reporting and a measurement event for triggering conditional handover.

[0178] When the prediction event and the measurement event are configured in the first reporting configuration, the evaluation of the prediction event is stopped, and the evaluation of the measurement event is performed. For example, if the terminal does not perform the evaluation of the measurement event before deactivating the AI object, the evaluation of the prediction event can be stopped and the evaluation of the measurement event can be started when the terminal deactivates the AI object; or, if the terminal also performs the evaluation of the measurement event before deactivating the AI object, the evaluation of the prediction event can be stopped and the evaluation of the measurement event can be continued when the terminal deactivates the AI object.

[0179] Optionally, the reporting trigger event includes a measurement event for triggering measurement reporting or a prediction event for triggering measurement reporting.

[0180] In this embodiment, for the measurement event for triggering measurement reporting, the terminal determines whether the measurement event for triggering measurement reporting is satisfied according to the measurement result, and triggers reporting when it is satisfied; for the prediction event for triggering measurement reporting, the terminal determines whether the prediction event for triggering measurement reporting is satisfied according to the prediction result, and triggers reporting when it is satisfied.

[0181] Optionally, when it is determined to perform the AI object switch, the method further includes at least one of the following:

[0182] The terminal stops predicting using the AI object before the switch and starts predicting using the AI object after the switch;

[0183] The terminal releases the prediction result based on the AI object before the switch saved by the terminal;

[0184] The terminal performs a third operation using the prediction result based on the AI object after the switch, where the third operation includes at least one of the following: determining whether the prediction event for triggering measurement reporting is satisfied to trigger measurement reporting, determining whether the prediction event for triggering conditional switch is satisfied to trigger conditional switch.

[0185] The above prediction result based on the AI object before the switch, that is, the prediction result obtained by predicting using the AI object before the switch. The above prediction result based on the AI object after the switch, that is, the prediction result obtained by predicting using the AI object after the switch.

[0186] Optionally, the method further includes:

[0187] The terminal receives first indication information sent by the network side device, where the first indication information is used to instruct the terminal to perform the first operation.

[0188] The above first indication information can be used to indicate one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, or AI object switching. Exemplarily, if the network device instructs the terminal to activate the AI object, the terminal activates the AI object; if the network device instructs the terminal to deactivate the AI object, the terminal deactivates the AI object; if the network device instructs the terminal to fallback to non-AI object operation, the terminal deactivates the AI object, stops evaluating the prediction events configured in the reporting configuration associated with the AI object, and evaluates the measurement events configured in the reporting configuration associated with the AI object; if the network device instructs the terminal to perform AI object switching, the terminal stops predicting using the AI object before switching and uses the AI object after switching for prediction.

[0189] Optionally, the method further includes:

[0190] The terminal determines whether to perform a fourth operation according to the monitoring result of the AI object and a first threshold;

[0191] Wherein, the first threshold is configured by the network device or predefined by the protocol, and the fourth operation includes AI object deactivation, AI object switching, or fallback to non-AI object operation.

[0192] In this embodiment, the above monitoring result of the AI object can be understood as the monitoring result obtained by monitoring the AI object. Exemplarily, the AI object can be monitored based on the monitoring metric parameters configured by the network device or predefined by the protocol. Among them, the above monitoring metric parameters include at least one of the RRM measurement prediction accuracy, the prediction accuracy of the optimal cell, the prediction accuracy of the optimal beam, the prediction accuracy of the HOF, the prediction accuracy of the RLF, the prediction accuracy of the measurement event, the number or probability of abnormal events occurring within the first time period, the handover delay or interruption duration within the second time period, the number of handovers per unit time or within the third time period, etc.

[0193] Correspondingly, the monitoring result of the AI object may include at least one of the following: RRM measurement prediction accuracy; the prediction accuracy of the optimal cell; the prediction accuracy of the optimal beam; the prediction accuracy of the HOF; the prediction accuracy of the RLF; the prediction accuracy of the measurement event; the number or probability of abnormal events occurring within the first time period; the handover delay or interruption duration within the second time period; the number of handovers per unit time or within the third time period.

[0194] Exemplarily, the above RRM measurement prediction accuracy may include prediction errors such as reference signal receiving power (RSRP) / reference signal received quality (RSRQ) / signal to interference plus noise ratio (SINR) at the cell level or beam level. Among them, the above prediction errors may include, but are not limited to, mean squared error (MSE), root mean square error (RMSE), normalized mean squared error (NMSE), etc. The prediction of the above measurement event can be understood as predicting whether the measurement event will be satisfied. The above handover delay or interruption duration may include the average handover delay or average interruption duration within the second time period.

[0195] The above first time period, second time period, and third time period can all be configured by the network-side device or predefined by the protocol.

[0196] The determination methods of the above various monitoring results are illustrated by examples as follows:

[0197] I. RRM measurement prediction accuracy: determined according to the RRM measurement prediction result and the error between the RRM measurement result corresponding to the RRM measurement prediction result within the predicted time or time period; among them, the above RRM measurement prediction result can be understood as the result obtained by the terminal based on the AI object for RRM measurement prediction, and the above RRM measurement result can be understood as the result obtained by the terminal for RRM measurement.

[0198] II. The prediction accuracy of the optimal M beams or the optimal N cells is determined according to the following steps:

[0199] Step S11: The terminal predicts the optimal M beams or the optimal N cells at the second moment at the first moment;

[0200] Step S12: The terminal measures the signal quality of m beams or n cells at the second moment, where m >= M and n >= N, and the m beams include the above M beams, or the n cells include the above N cells;

[0201] Step S13: The terminal sorts according to the signal quality from high to low and determines the actual optimal M beams or N cells;

[0202] Step S14: Based on the predicted result of step S11 and the actual result of step S13 at the terminal, determine whether the prediction is accurate.

[0203] III. The prediction accuracy rate of measurement events is determined according to the following steps:

[0204] Step S21: The terminal predicts at the third moment that the measurement event associated with the first cell at the fourth moment will be satisfied;

[0205] Step S22: The terminal determines whether the measurement event at the fourth moment will be satisfied according to the measurement result of the first cell between the third moment and the fourth moment;

[0206] Step S23: The terminal determines whether the measurement event prediction is accurate according to the predicted result and the actual result of the measurement event.

[0207] IV. The HOF prediction accuracy rate is determined according to the following steps:

[0208] Step S31: The terminal predicts at the fifth moment that HOF will occur in the second cell at the sixth moment;

[0209] Step S32: The terminal determines whether HOF will occur at the sixth moment according to the measurement result of the second cell between the fifth moment and the sixth moment. How to determine HOF based on the measurement result can be implemented by the UE or pre-configured by the network. For example, the network can configure a second threshold, and when the average signal quality of the second cell within a given time period is lower than the second threshold, the UE determines that HOF will occur;

[0210] Step S33: The terminal determines whether the HOF prediction is accurate according to the predicted result and the actual result of HOF.

[0211] V. The RLF prediction accuracy rate is determined according to the following steps:

[0212] Step S41: The terminal predicts at the seventh moment that RLF will occur in the third cell at the eighth moment;

[0213] Step S42: The terminal determines whether RLF will occur at the eighth moment according to the measurement result of the third cell between the seventh moment and the eighth moment. The terminal can reuse the existing Radio Link Monitor (RLM) process to determine whether RLF will occur according to the signal quality;

[0214] Step S43: The terminal determines whether the RLF prediction is accurate according to the predicted result and the actual result of RLF.

[0215] VI. The number of occurrences / probability of abnormal events within the first time period: The terminal counts the number of occurrences / probability of abnormal events within the first time period (network-configured or protocol-predefined).

[0216] VII. Handover latency / interruption duration within the second time period, or average handover latency / average interruption duration within the second time period: The terminal counts the handover latency / interruption duration within the second time period, or the terminal counts the average handover latency / average interruption duration within the second time period.

[0217] VIII. Number of handovers within a unit time or within the third time period: The terminal counts the number of handovers within a unit time or within the third time period (configured by the network or predefined by the protocol).

[0218] It should be noted that in the case where the monitoring results of the above AI object include the monitoring results corresponding to at least one monitoring metric parameter, the above first threshold may include the thresholds corresponding to the at least one monitoring metric parameter, where the thresholds corresponding to the at least one monitoring metric parameter may be the same threshold or may be different thresholds.

[0219] It should also be noted that for the handover of the AI object, the network-side device may pre-configure at least one AI object identifier for the handover of the AI object, so that in the case of determining to perform the handover of the AI object, the terminal can switch to the AI object identified by the at least one AI object identifier; for the operation of falling back to a non-AI object, the network-side device may pre-configure the behavior of the terminal after fallback. For example, for conditional handover, the network-side device configures both a measurement event and a prediction event for the same reporting configuration. After fallback, the terminal evaluates whether the execution conditions of the conditional handover are met only based on the measurement event.

[0220] Optionally, the first threshold includes the thresholds corresponding to the respective monitoring metric parameters of the AI object; the terminal determines whether to perform the fourth operation according to the monitoring results of the AI object and the first threshold, including:

[0221] In the case of satisfying at least one of the following, the terminal determines to perform the fourth operation;

[0222] The RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy;

[0223] The prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, where N is a positive integer;

[0224] The prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, where M is a positive integer;

[0225] The prediction accuracy of the measurement event is less than or equal to the threshold corresponding to the measurement event;

[0226] The prediction accuracy of the handover failure HOF is less than or equal to the threshold corresponding to the HOF;

[0227] The prediction accuracy of radio link failure (RLF) is lower than the threshold corresponding to the RLF and less than or equal to it;

[0228] The number of occurrences or probability of abnormal events within the first time period is greater than or equal to the threshold corresponding to the abnormal events;

[0229] The handover delay or interruption duration within the second time period is greater than or equal to the threshold corresponding to the handover delay or interruption duration;

[0230] The number of handovers within a unit time or within a third time period is greater than the threshold corresponding to the number of handovers.

[0231] Optionally, the abnormal events include at least one of the following: ping-pong handover, premature handover, late handover, handover to the wrong cell, handover failure, radio link failure.

[0232] The above premature handover can be understood as the terminal prematurely handing over to the target cell, resulting in radio link failure in the target cell; the above late handover can be understood as the terminal handing over to the target cell too late, resulting in radio link failure in the source cell.

[0233] Optionally, the first threshold is associated with a first object, where the first object includes one of the following: terminal, cell, frequency point, AI object, measurement configuration, measurement identifier, measurement object, reporting configuration.

[0234] Exemplarily, when the first threshold is associated with a terminal, the first threshold can be used for comparison with the monitoring result of the AI object currently activated by the terminal. For example, for the monitoring result of the AI object being the RRM measurement prediction accuracy, the RRM measurement prediction accuracy of the AI object currently activated by the terminal can be compared with the first threshold.

[0235] Exemplarily, when the first threshold is associated with a cell, for example, a special cell (SpCell), the first threshold can be used for comparison with the monitoring result corresponding to the cell. For example, for the monitoring result of the AI object being the RRM measurement prediction accuracy, the RRM measurement prediction accuracy of the cell can be compared with the first threshold.

[0236] Exemplarily, when the first threshold is associated with a frequency point, the first threshold can be used for comparison with the monitoring result corresponding to the cell on that frequency point. For example, for the monitoring result of the AI object being the RRM measurement prediction accuracy, the RRM measurement prediction accuracy of the cell on that frequency point can be compared with the first threshold.

[0237] Exemplarily, in the case where the first threshold is associated with the AI object, the first threshold can be used for comparing the monitoring results of the AI object. For example, for the monitoring result of the AI object being the RRM measurement prediction accuracy, the RRM measurement prediction accuracy of the AI object can be compared with the first threshold.

[0238] Exemplarily, in the case where the first threshold is associated with the measurement configuration / measurement ID / measurement object / reporting configuration, the first threshold can be used for comparing the monitoring results of the AI object associated with the measurement configuration / measurement ID / measurement object / reporting configuration. For example, for the monitoring result of the AI object being the RRM measurement prediction accuracy, the RRM measurement prediction accuracy of the AI object associated with the measurement configuration / measurement ID / measurement object / reporting configuration can be compared with the first threshold.

[0239] Optionally, the method further includes:

[0240] The terminal sends first information to the network-side device;

[0241] Wherein, the first information includes at least one of the following:

[0242] Second indication information, used to indicate the fourth operation performed by the terminal, and the fourth operation includes AI object deactivation or AI object handover or fallback to non-AI object operation;

[0243] RRM measurement prediction accuracy;

[0244] Prediction accuracy of the optimal N cells;

[0245] Prediction accuracy of the optimal M beams;

[0246] Prediction accuracy of RRM measurement events;

[0247] Prediction accuracy of HOF;

[0248] Prediction accuracy of RLF;

[0249] Number or probability of abnormal events occurring within the first time period;

[0250] Handover delay or interruption duration within the second time period;

[0251] Number of handovers per unit time or within the third time period;

[0252] Identity of the AI object after handover.

[0253] The following is an example of this embodiment:

[0254] The terminal sends second indication information to the network-side device, which is used to indicate a fourth operation performed by the terminal, so that the network can determine the current state of the AI object used on the terminal side, thereby avoiding inconsistent understanding between the network and the terminal and affecting terminal communication.

[0255] The terminal sends the monitoring result of the AI object to the network-side device, that is, at least one of the RRM measurement prediction accuracy, the prediction accuracy of the optimal N cells, the prediction accuracy of the optimal M beams, the prediction accuracy of the RRM measurement event, the prediction accuracy of the HOF, the prediction accuracy of the RLF, the number or probability of abnormal events occurring within the first time period, the handover delay or interruption duration within the second time period, and the number of handovers per unit time or within the third time period. Thus, the network-side device can determine the effectiveness of the AI object currently used on the terminal side based on the monitoring result of the AI object, and further determine whether to instruct the terminal to perform operations such as deactivating / switching / rolling back to a non-AI object of the AI object.

[0256] The terminal sends the identifier of the switched AI object to the network-side device, so that the network-side device can determine which AI object the terminal uses after the AI object is switched based on the identifier of the switched AI object, ensuring consistent understanding between the network side and the terminal side and avoiding affecting terminal performance.

[0257] Optionally, the target configuration is associated with at least one of the following: prediction indication, AI object identifier, prediction event.

[0258] In one embodiment, the target configuration is associated with a prediction indication, that is, the target configuration associated with the AI object is indicated by the prediction indication. In this case, the AI object associated with the target configuration can be pre-configured by the network-side device or predefined by the protocol or determined by the AI object identifier associated with the target configuration, etc.

[0259] In another embodiment, the target configuration is associated with an AI object identifier, that is, the target configuration associated with the AI object is indicated by the AI object identifier. In this case, the AI object associated with the target configuration is the AI object identified by the AI object identifier.

[0260] In yet another embodiment, the target configuration is associated with a prediction event, that is, the target configuration associated with the AI object is indicated by the prediction event. In this case, the AI object associated with the target configuration can be pre-configured by the network-side device or predefined by the protocol or determined by the AI object identifier associated with the target configuration, etc.

[0261] It can be understood that the above three embodiments can be combined according to requirements. For example, the above target configuration is associated with a prediction indication and an AI object identifier, or the above target configuration is associated with a prediction event and an AI object identifier, etc.

[0262] Optionally, the prediction indication is used to indicate that the measurement report associated with the target configuration needs to carry a prediction result;

[0263] Or,

[0264] When the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering conditional handover, the prediction indication is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers conditional handover when the first measurement event is satisfied;

[0265] Or,

[0266] The prediction indication is used to indicate a prediction type, and the prediction type includes at least one of the following: cell prediction, beam prediction, RRM measurement prediction, measurement event prediction.

[0267] It should be noted that when the prediction indication is used to indicate the prediction type, the AI object corresponding to the above prediction type can be indicated by the network-side device, predefined by the protocol, determined by the AI object identifier associated with the target configuration, etc.

[0268] Optionally, the AI object identifier is used to indicate that the measurement report associated with the target configuration needs to carry a prediction result;

[0269] Or,

[0270] When the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering conditional handover, the AI object identifier is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers conditional handover when the first measurement event is satisfied;

[0271] Or,

[0272] The AI object identifier is used to indicate that the terminal uses the AI object corresponding to the AI object identifier to obtain a prediction result, and carries the prediction result in the measurement report associated with the target configuration when the reporting condition is satisfied.

[0273] In this embodiment, the above-mentioned satisfaction of the reporting condition may include satisfying the periodic reporting condition or satisfying the reporting trigger event, where the above-mentioned reporting trigger event may include a measurement event for triggering measurement reporting or a prediction event for triggering measurement reporting.

[0274] Exemplarily, when the target configuration is associated with an AI object identifier, the terminal may perform at least one of the following:

[0275] The measurement report associated with the target configuration carries a prediction result, and the prediction result may include a prediction result based on the AI object corresponding to the AI object identifier;

[0276] When the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering a condition switch, the terminal evaluates whether the first measurement event is satisfied based on a prediction result, and triggers the condition switch when the first measurement event is satisfied. The prediction result may include a prediction result of an AI object corresponding to the AI object identifier;

[0277] Use the AI object corresponding to the AI object identifier to make a prediction to obtain a prediction result, and carry the prediction result in the measurement report associated with the target configuration when the reporting condition is satisfied.

[0278] Optionally, the prediction event includes at least one of the following: a first prediction event for triggering a measurement report, a second prediction event for triggering a condition switch;

[0279] Among them, the first prediction event evaluates whether to trigger a measurement report according to a prediction result of at least one of a serving cell and a neighboring cell, and the second prediction event evaluates whether to trigger a condition switch according to a prediction result of at least one of a serving cell and a neighboring cell.

[0280] Exemplarily, for the measured EventA3, if the measurement result of the neighboring cell is always higher than a certain threshold than the measurement result of the serving cell within the triggering time (Time to Trigger, TTT), then the A3 measurement event is satisfied; for the predicted Event A3, if the predicted result of the neighboring cell is always higher than a certain threshold than the predicted result of the serving cell within the TTT time, then the A3 prediction event is satisfied.

[0281] Optionally, the target configuration is a reporting configuration;

[0282] When the reporting configuration is associated with the first prediction event, the first prediction event is used to instruct the terminal to evaluate whether the first prediction event is satisfied according to a prediction result of at least one of a serving cell and a neighboring cell, and trigger a measurement report when the first prediction event is satisfied;

[0283] Or,

[0284] When the reporting configuration is associated with a second prediction event for triggering a condition switch, the second prediction event is used to instruct the terminal to evaluate whether the second prediction event is satisfied according to a prediction result of at least one of a serving cell and a neighboring cell, and trigger a condition switch when the second prediction event is satisfied.

[0285] Exemplarily, when the reporting configuration is associated with a first prediction event, the terminal evaluates whether the first prediction event is satisfied according to the prediction results of at least one of the serving cell and neighboring cells, and triggers a measurement report when the first prediction event is satisfied; when the reporting configuration is associated with a second prediction event, the terminal evaluates whether the second prediction event is satisfied according to the prediction results of at least one of the serving cell and neighboring cells, and triggers a conditional handover when the second prediction event is satisfied.

[0286] Please refer to Figure 5 , Figure 5 is a flowchart of an AI object management method provided by an embodiment of the present application. This method can be executed by a network-side device, such as Figure 5 shown, and includes the following steps:

[0287] Step 501, the network-side device performs a fifth operation, where the fifth operation includes at least one of the following:

[0288] Sending a target configuration to the terminal, where the target configuration is associated with an AI object, and the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction;

[0289] Receiving first information sent by the terminal, where the first information includes at least one of the following:

[0290] Second indication information for indicating a fourth operation performed by the terminal, where the fourth operation includes AI object deactivation, AI object handover, or fallback to a non-AI object operation;

[0291] RRM measurement prediction accuracy;

[0292] Prediction accuracy of the optimal N cells;

[0293] Prediction accuracy of the optimal M beams;

[0294] Prediction accuracy of measurement events;

[0295] Prediction accuracy of HOF;

[0296] Prediction accuracy of RLF;

[0297] Number or probability of abnormal events occurring within a first time period;

[0298] Handover delay or interruption duration within a second time period;

[0299] Number of handovers per unit time or within a third time period;

[0300] Identifier of the AI object after switching.

[0301] Optionally, the target configuration includes at least one of the following: measurement configuration, measurement identifier, measurement object, reporting configuration.

[0302] Optionally, the target configuration is associated with at least one of the following: prediction indication, AI object identifier, prediction event.

[0303] Optionally, the prediction indication is used to indicate that the measurement report associated with the target configuration needs to carry a prediction result;

[0304] Or,

[0305] In the case where the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering conditional switching, the prediction indication is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers conditional switching when the first measurement event is satisfied;

[0306] Or,

[0307] The prediction indication is used to indicate a prediction type, and the prediction type includes at least one of the following: cell prediction, beam prediction, RRM measurement prediction, measurement event prediction.

[0308] Optionally, the AI object identifier is used to indicate that the measurement report associated with the target configuration needs to carry a prediction result;

[0309] Or,

[0310] In the case where the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering conditional switching, the AI object identifier is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers conditional switching when the first measurement event is satisfied;

[0311] Or,

[0312] The AI object identifier is used to indicate that the terminal uses the AI object corresponding to the AI object identifier to obtain a prediction result, and carries the prediction result in the measurement report associated with the target configuration when the reporting condition is satisfied.

[0313] Optionally, the prediction event includes at least one of the following: a first prediction event for triggering measurement reporting, a second prediction event for triggering conditional switching;

[0314] Among them, the first prediction event evaluates whether to trigger a measurement report according to the prediction result of at least one of the serving cell and neighboring cells, and the second prediction event evaluates whether to trigger a conditional handover according to the prediction result of at least one of the serving cell and neighboring cells.

[0315] Optionally, the target is a reporting configuration;

[0316] When the reporting configuration is associated with the first prediction event, the first prediction event is used to instruct the terminal to evaluate whether the first prediction event is satisfied according to the prediction result, and trigger a measurement report when the first prediction event is satisfied;

[0317] Or,

[0318] When the reporting configuration is associated with the second prediction event, the second prediction event is used to instruct the terminal to evaluate whether the second prediction event is satisfied according to the prediction result, and trigger a conditional handover when the second prediction event is satisfied.

[0319] Optionally, the method further includes:

[0320] The network-side device sends first indication information to the terminal, where the first indication information is used to instruct the terminal to perform a first operation, and the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, AI object handover.

[0321] Optionally, the method further includes:

[0322] The network-side device sends a first threshold to the terminal;

[0323] Among them, the first threshold is used for the terminal to determine whether to perform a fourth operation, and the fourth operation includes AI object deactivation or AI object handover or fallback to non-AI object operation.

[0324] Optionally, the first threshold includes thresholds corresponding to each monitoring index parameter of the AI object;

[0325] Among them, the monitoring index parameters of the AI object include at least one of the following:

[0326] RRM measurement prediction accuracy;

[0327] Prediction accuracy of the optimal N cells, where N is a positive integer;

[0328] Prediction accuracy of the optimal M beams, where M is a positive integer;

[0329] Prediction accuracy of handover failure HOF;

[0330] Prediction accuracy of radio link failure (RLF);

[0331] Prediction accuracy of measurement events;

[0332] Number or probability of abnormal events occurring within the first time period;

[0333] Handover latency or interruption duration within the second time period;

[0334] Number of handovers per unit time or within the third time period.

[0335] It should be noted that the implementation method of this embodiment can refer to Figure 4 the relevant description of the embodiments shown, which will not be elaborated here.

[0336] It should also be noted that the conditional handover in the embodiments of this application can include conditional primary-secondary cell addition / modification (Conditional PSCell addition / change) or conditional LTM (i.e., Condition L1 / L2-triggered mobility).

[0337] It should further be noted that for the AI object management method provided in the embodiments of this application, the execution entity can be an AI object management device, or a control module in the AI object management device for executing the AI object management method. In the embodiments of this application, taking the AI object management device executing the AI object management method as an example, the AI object management device provided in the embodiments of this application is described.

[0338] Please refer to Figure 6 , Figure 6 which is a structural diagram of an AI object management device provided in the embodiments of this application. As Figure 6 shown, the AI object management device 600 includes:

[0339] A first execution module 601, configured to perform a second operation on a target configuration when it is determined to execute a first operation;

[0340] Wherein, the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, AI object handover; the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, RLF prediction, and handover failure (HOF) prediction;

[0341] The target configuration is the configuration associated with the AI object, and the second operation is an operation corresponding to the first operation.

[0342] Optionally, the target configuration includes at least one of the following: measurement configuration, measurement identifier, measurement object, reporting configuration.

[0343] Optionally, the first execution module is specifically configured to perform at least one of the following:

[0344] When it is determined that the AI object is activated, activate the target configuration;

[0345] When it is determined that the AI object is deactivated, deactivate the target configuration;

[0346] When it is determined that the operation is to be rolled back to a non-AI object operation, stop evaluating the prediction event configured for the target configuration, and evaluate the measurement event configured for the target configuration;

[0347] When it is determined that an AI object switch is to be performed, carry the prediction result based on the switched AI object in the measurement report associated with the target configuration, where the target configuration is the configuration associated with the switched AI object.

[0348] Optionally, the activation of the target configuration includes at least one of the following:

[0349] When the periodic reporting condition or reporting trigger event associated with the first reporting configuration is met, carry at least one of the measurement result and the prediction result in the measurement report associated with the first reporting configuration;

[0350] When the prediction event associated with the first reporting configuration for triggering condition switching is met, perform condition switching;

[0351] wherein the first reporting configuration is the reporting configuration associated with the target configuration, or the first reporting configuration is the reporting configuration in the target configuration

[0352] Optionally, the deactivation of the target configuration includes:

[0353] Stop reporting the measurement report associated with the first reporting configuration;

[0354] Or,

[0355] When the periodic reporting condition or reporting trigger event associated with the first reporting configuration is met, only carry the measurement result in the measurement report associated with the first reporting configuration;

[0356] Or,

[0357] When a prediction event is configured in the first reporting configuration, stop evaluating the prediction event;

[0358] Or,

[0359] When a prediction event and a measurement event are configured in the first reporting configuration, the evaluation of the prediction event is stopped, and the evaluation of the measurement event is performed;

[0360] Wherein, the first reporting configuration is the reporting configuration associated with the target configuration, or the first reporting configuration is the reporting configuration in the target configuration.

[0361] Optionally, the reporting trigger event includes a measurement event for triggering measurement reporting or a prediction event for triggering measurement reporting.

[0362] Optionally, when it is determined to perform an AI object switch, the device further includes a second execution module, which is specifically used for at least one of the following:

[0363] Stop making predictions using the AI object before the switch, and use the AI object after the switch to make predictions;

[0364] Release the prediction results based on the AI object before the switch saved by the terminal;

[0365] Execute a third operation using the prediction results based on the AI object after the switch, where the third operation includes at least one of the following: determining whether a prediction event for triggering measurement reporting is satisfied to trigger measurement reporting, and determining whether a prediction event for triggering conditional switching is satisfied to trigger conditional switching.

[0366] Optionally, the device further includes:

[0367] A receiving module, configured to receive first indication information sent by a network-side device, where the first indication information is used to instruct the terminal to execute the first operation.

[0368] Optionally, the device further includes:

[0369] A determination module, configured to determine whether to execute a fourth operation according to the monitoring result of the AI object and a first threshold;

[0370] Wherein, the first threshold is configured by a network-side device or predefined by a protocol, and the fourth operation includes AI object deactivation, AI object switching, or fallback to non-AI object operation.

[0371] Optionally, the first threshold includes thresholds corresponding to respective monitoring metric parameters of the AI object; the determination module is specifically configured to:

[0372] Determine to execute the fourth operation when at least one of the following is satisfied;

[0373] The RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy;

[0374] The prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, where N is a positive integer;

[0375] The prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, where M is a positive integer;

[0376] The prediction accuracy of the measurement event is less than or equal to the threshold corresponding to the measurement event;

[0377] The prediction accuracy of handover failure HOF is less than or equal to the threshold corresponding to the HOF;

[0378] The prediction accuracy of radio link failure RLF is less than or equal to the threshold corresponding to the RLF;

[0379] The number of occurrences or probability of an abnormal event within the first time period is greater than or equal to the threshold corresponding to the abnormal event;

[0380] The handover delay or interruption duration within the second time period is greater than or equal to the threshold corresponding to the handover delay or interruption duration;

[0381] The number of handovers within a unit time or the third time period is greater than the threshold corresponding to the number of handovers.

[0382] Optionally, the abnormal event includes at least one of the following: ping-pong handover, premature handover, late handover, handover to the wrong cell, handover failure, radio link failure.

[0383] Optionally, the first threshold is associated with a first object, where the first object includes one of the following: terminal, cell, frequency point, AI object, measurement configuration, measurement identifier, measurement object, reporting configuration.

[0384] Optionally, the device further includes:

[0385] A sending module, configured to send first information to a network-side device;

[0386] Wherein, the first information includes at least one of the following:

[0387] Second indication information, configured to indicate a fourth operation performed by the terminal, where the fourth operation includes deactivating an AI object or switching an AI object or falling back to a non-AI object operation;

[0388] RRM measurement prediction accuracy;

[0389] The prediction accuracy of the optimal N cells;

[0390] The prediction accuracy of the optimal M beams;

[0391] The prediction accuracy of the RRM measurement event;

[0392] Prediction accuracy of HOF;

[0393] Prediction accuracy of RLF;

[0394] Number or probability of abnormal events occurring within the first time period;

[0395] Handover delay or interruption duration within the second time period;

[0396] Number of handovers within a unit time or the third time period;

[0397] Identifier of the AI object after handover.

[0398] Optionally, the target configuration is associated with at least one of the following: prediction indication, AI object identifier, prediction event.

[0399] Optionally, the prediction indication is used to indicate that the measurement report associated with the target configuration needs to carry the prediction result;

[0400] Or,

[0401] In the case where the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering conditional handover, the prediction indication is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers conditional handover when the first measurement event is satisfied;

[0402] Or,

[0403] The prediction indication is used to indicate the prediction type, and the prediction type includes at least one of the following: cell prediction, beam prediction, RRM measurement prediction, measurement event prediction.

[0404] Optionally, the AI object identifier is used to indicate that the measurement report associated with the target configuration needs to carry the prediction result;

[0405] Or,

[0406] In the case where the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering conditional handover, the AI object identifier is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers conditional handover when the first measurement event is satisfied;

[0407] Or,

[0408] The AI object identifier is used to indicate that the terminal uses the AI object corresponding to the AI object identifier to obtain the prediction result, and carries the prediction result in the measurement report associated with the target configuration when the reporting condition is satisfied.

[0409] Optionally, the prediction event includes at least one of the following: a first prediction event for triggering measurement reporting, and a second prediction event for triggering conditional handover;

[0410] Wherein, the first prediction event evaluates whether to trigger measurement reporting according to the prediction result of at least one of the serving cell and neighboring cells, and the second prediction event evaluates whether to trigger conditional handover according to the prediction result of at least one of the serving cell and neighboring cells.

[0411] Optionally, the target is a reporting configuration;

[0412] When the reporting configuration is associated with the first prediction event, the first prediction event is used to instruct the terminal to evaluate whether the first prediction event is satisfied according to the prediction result of at least one of the serving cell and neighboring cells, and trigger measurement reporting when the first prediction event is satisfied;

[0413] Or,

[0414] When the reporting configuration is associated with a second prediction event for triggering conditional handover, the second prediction event is used to instruct the terminal to evaluate whether the second prediction event is satisfied according to the prediction result of at least one of the serving cell and neighboring cells, and trigger conditional handover when the second prediction event is satisfied.

[0415] The AI object management device in the embodiments of the present application may 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 a chip. The electronic device may be a terminal or other devices other than the terminal. Exemplarily, the terminal may include, but is not limited to, the types of the above-mentioned terminal 11, and other devices may be a server, a Network Attached Storage (NAS), etc., which are not specifically limited in the embodiments of the present application.

[0416] The AI object management device provided in the embodiments of the present application can implement Figure 4 each process implemented by the method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein again.

[0417] Please refer to Figure 7 , Figure 7 which is a structural diagram of an AI object management device provided in the embodiments of the present application. As Figure 7 shown, the AI object management device 700 includes:

[0418] An execution module 701, configured to execute a fifth operation, wherein the fifth operation includes at least one of the following:

[0419] Send a target configuration to a terminal, where the target configuration is associated with an AI object, and the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction;

[0420] Receive first information sent by the terminal, where the first information includes at least one of the following:

[0421] Second indication information for indicating a fourth operation performed by the terminal, and the fourth operation includes deactivating the AI object, switching the AI object, or falling back to a non-AI object operation;

[0422] RRM measurement prediction accuracy;

[0423] Prediction accuracy of the optimal N cells;

[0424] Prediction accuracy of the optimal M beams;

[0425] Prediction accuracy of the measurement event;

[0426] Prediction accuracy of the HOF;

[0427] Prediction accuracy of the RLF;

[0428] Number or probability of abnormal events occurring within a first time period;

[0429] Handover delay or interruption duration within a second time period;

[0430] Number of handovers per unit time or within a third time period;

[0431] Identifier of the AI object after handover.

[0432] Optionally, the target configuration includes at least one of the following: measurement configuration, measurement identifier, measurement object, and reporting configuration.

[0433] Optionally, the target configuration is associated with at least one of the following: prediction indication, AI object identifier, and prediction event.

[0434] Optionally, the prediction indication is used to indicate that the measurement report associated with the target configuration needs to carry a prediction result;

[0435] Or,

[0436] When the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering a conditional handover, the prediction indication is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers a conditional handover when the first measurement event is satisfied;

[0437] Alternatively,

[0438] The prediction indication is used to indicate a prediction type, which includes at least one of the following: cell prediction, beam prediction, RRM measurement prediction, and measurement event prediction.

[0439] Optionally, the AI object identifier is used to indicate that the measurement report associated with the target configuration needs to carry a prediction result;

[0440] Alternatively,

[0441] In the case where the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering conditional handover, the AI object identifier is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result and triggers conditional handover when the first measurement event is satisfied;

[0442] Alternatively,

[0443] The AI object identifier is used to indicate that the terminal obtains a prediction result using the AI object corresponding to the AI object identifier and carries the prediction result in the measurement report associated with the target configuration when the reporting condition is satisfied.

[0444] Optionally, the prediction event includes at least one of the following: a first prediction event for triggering measurement reporting and a second prediction event for triggering conditional handover;

[0445] Wherein, the first prediction event evaluates whether to trigger measurement reporting based on the prediction result of at least one of the serving cell and neighboring cells, and the second prediction event evaluates whether to trigger conditional handover based on the prediction result of at least one of the serving cell and neighboring cells.

[0446] Optionally, the target configuration is a reporting configuration;

[0447] In the case where the reporting configuration is associated with the first prediction event, the first prediction event is used to indicate that the terminal evaluates whether the first prediction event is satisfied based on the prediction result and triggers measurement reporting when the first prediction event is satisfied;

[0448] Alternatively,

[0449] In the case where the reporting configuration is associated with the second prediction event, the second prediction event is used to indicate that the terminal evaluates whether the second prediction event is satisfied based on the prediction result and triggers conditional handover when the second prediction event is satisfied.

[0450] Optionally, the apparatus further includes:

[0451] A first sending module, configured to send first indication information to the terminal, where the first indication information is used to instruct the terminal to perform a first operation, and the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, AI object switching.

[0452] Optionally, the apparatus further includes:

[0453] A second sending module, configured to send a first threshold to the terminal;

[0454] where the first threshold is used for the terminal to determine whether to perform a fourth operation, and the fourth operation includes AI object deactivation, AI object switching, or fallback to non-AI object operation.

[0455] Optionally, the first threshold includes thresholds corresponding to respective monitoring metric parameters of the AI object;

[0456] where the monitoring metric parameters of the AI object include at least one of the following:

[0457] RRM measurement prediction accuracy;

[0458] Prediction accuracy of the optimal N cells, where N is a positive integer;

[0459] Prediction accuracy of the optimal M beams, where M is a positive integer;

[0460] Prediction accuracy of handover failure HOF;

[0461] Prediction accuracy of radio link failure RLF;

[0462] Prediction accuracy of measurement events;

[0463] Number or probability of abnormal events occurring within a first time period;

[0464] Handover delay or interruption duration within a second time period;

[0465] Number of handovers per unit time or within a third time period.

[0466] The AI object management device in the embodiments of the present application may 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 a chip. The electronic device may be a network-side device or other devices other than network-side devices. Exemplarily, the network-side device may include, but is not limited to, the types of network-side devices 12 listed above, and other devices may be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiments of the present application.

[0467] The AI object management device provided by the embodiments of this application can implement Figure 5 each process implemented by the method embodiments of

[0468] Optionally, as Figure 8 shown, the embodiments of this application also provide a communication device 800, including a processor 801 and a memory 802. A program or instruction that can run on the processor 801 is stored on the memory 802. For example, when the communication device 800 is a terminal, when the program or instruction is executed by the processor 801, each step of the above AI object management method embodiment is implemented, and the same technical effect can be achieved. When the communication device 800 is a network-side device, when the program or instruction is executed by the processor 801, each step of the above AI object management method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, details are not described herein again.

[0469] The embodiments of this application also provide a terminal, including a processor and a communication interface. The processor is used to perform a second operation on a target configuration when it is determined to perform a first operation. Among them, the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, and AI object switching. The AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction. The target configuration is the configuration associated with the AI object, and the second operation is an operation corresponding to the first operation. This terminal embodiment corresponds to the above terminal-side method embodiments. Each implementation process and implementation manner of the above method embodiments can be applied to this terminal embodiment, and the same technical effect can be achieved. Specifically, Figure 9 FIG. is a schematic hardware structure diagram of a terminal for implementing the embodiments of this application.

[0470] The terminal 900 includes, but is not limited to, at least some components such as a radio frequency unit 901, a network module 902, an audio output unit 903, an input unit 904, a sensor 905, a display unit 906, a user input unit 907, an interface unit 908, a memory 909, and a processor 910.

[0471] Those skilled in the art can understand that the terminal 900 may further include a power source (such as a battery) for supplying power to each component. The power source can be logically connected to the processor 910 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. Figure 9The terminal structure shown does not constitute a limitation on 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 elaborated here.

[0472] It should be understood that in the embodiments of the present application, the input unit 904 may include a Graphics Processing Unit (GPU) 9041 and a microphone 9042. The graphics processor 9041 processes the image data of static pictures or videos obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 906 may include a display panel 9061, and the display panel 9061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 907 includes at least one of a touch panel 9071 and other input devices 9072. The touch panel 9071 is also called a touch screen. The touch panel 9071 may include two parts: a touch detection device and a touch controller. The other input devices 9072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, which will not be elaborated here.

[0473] In the embodiments of the present application, after receiving downlink data from a network-side device, the radio frequency unit 901 may transmit it to the processor 910 for processing; in addition, the radio frequency unit 901 may send uplink data to the network-side device. Generally, the radio frequency unit 901 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0474] The memory 909 can be used to store software programs or instructions as well as various data. The memory 909 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area may store an operating system, application programs or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 909 may include volatile memory or 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 (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synch link dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM). The memory 909 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0475] The processor 910 may include one or more processing units; optionally, the processor 910 integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above modem processor may not be integrated into the processor 910 either.

[0476] Among them, the processor 910 is used to perform a second operation on a target configuration when it is determined to execute a first operation;

[0477] Among them, the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, AI object switching; the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction;

[0478] The target configuration is the configuration associated with the AI object, and the second operation is the operation corresponding to the first operation.

[0479] It can be understood that the implementation processes of the implementation manners mentioned in this embodiment can refer to the relevant descriptions of the foregoing method embodiments and achieve the same or corresponding technical effects. To avoid repetition, they will not be elaborated here.

[0480] The embodiment of the present application further provides a network-side device, including a processor and a communication interface. The communication interface is used to perform a fifth operation. Among them, the fifth operation includes at least one of the following: sending a target configuration to a terminal, where the target configuration is associated with an AI object, and the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction; receiving first information sent by the terminal, where the first information includes at least one of the following: second indication information for indicating a fourth operation performed by the terminal, and the fourth operation includes AI object deactivation, AI object switching, or fallback to non-AI object operation; RRM measurement prediction accuracy; prediction accuracy of the optimal N cells; prediction accuracy of the optimal M beams; prediction accuracy of measurement events; prediction accuracy of HOF; prediction accuracy of RLF; number or probability of abnormal events occurring within a first time period; handover delay or interruption duration within a second time period; number of handovers per unit time or within a third time period; identifier of the AI object after handover. This embodiment of the network-side device corresponds to the above-mentioned method embodiment of the network-side device. Each implementation process and implementation manner of the above method embodiment can be applied to this embodiment of the network-side device and can achieve the same technical effect.

[0481] Specifically, the embodiment of the present application further provides a network-side device. As Figure 10As shown in the figure, the network-side device 1000 includes: an antenna 1001, a radio frequency device 1002, a baseband device 1003, a processor 1004, and a memory 1005. The antenna 1001 is connected to the radio frequency device 1002. In the uplink direction, the radio frequency device 1002 receives information through the antenna 1001 and sends the received information to the baseband device 1003 for processing. In the downlink direction, the baseband device 1003 processes the information to be sent and sends it to the radio frequency device 1002. After processing the received information, the radio frequency device 1002 sends it out through the antenna 1001.

[0482] In the above embodiments, the method executed by the network-side device can be implemented in the baseband device 1003, and the baseband device 1003 includes a baseband processor.

[0483] The baseband device 1003 may include, for example, at least one baseband board, and a plurality of chips are arranged on the baseband board, such as Figure 10 As shown in the figure, one of the chips is, for example, a baseband processor, which is connected to the memory 1005 through a bus interface to call the program in the memory 1005 and execute the operations of the network device shown in the above method embodiments.

[0484] The network-side device may further include a network interface 1006, and the interface is, for example, a Common Public Radio Interface (CPRI).

[0485] Specifically, the network-side device 1000 in the embodiments of the present application further includes: instructions or programs stored on the memory 1005 and executable on the processor 1004. The processor 1004 calls the instructions or programs in the memory 1005 to execute Figure 7 the methods executed by the modules shown in the figure and achieve the same technical effects. To avoid repetition, they are not described here in detail.

[0486] The embodiments of the present application further provide a readable storage medium. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the various processes of the above method embodiments of the AI object management method are implemented, and the same technical effects can be achieved. To avoid repetition, they are not described here again.

[0487] Wherein, the processor is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disks, or optical discs, etc. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0488] Another embodiment of the present application further provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is configured to run programs or instructions to implement each process of the above-mentioned embodiment of the AI object management method, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0489] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip.

[0490] Another embodiment of the present application further provides a computer program / program product, which includes a computer program or computer instructions. The computer program or computer instructions are executed by at least one processor to implement each process of the above-mentioned embodiment of the AI object management method, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0491] The embodiments of the present application further provide an AI object management system, including: a terminal and a network-side device. The terminal is configured to execute as Figure 4 and each process of the above-mentioned method embodiments. The network-side device is configured to execute as Figure 5 and each process of the above-mentioned method embodiments, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0492] It should be noted that in this document, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device including such element. In addition, it should be pointed out that the methods and devices in the embodiments of the present application are not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0493] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of computer software products plus the necessary general hardware platforms, and of course, they can also be implemented by hardware. The computer software products are stored in storage media (such as ROM, RAM, magnetic disks, optical disks, etc.) and include several instructions for causing a terminal or a network-side device to execute the methods described in various embodiments of the present application.

[0494] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms of embodiments without departing from the purpose of the present application and the scope protected by the claims. These embodiments are all within the protection scope of the present application.

Claims

1. An AI object management method, characterized in that, Including: When the terminal determines to perform a first operation, it performs a second operation on a target configuration; Wherein, the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, AI object switching; the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction; The target configuration is the configuration associated with the AI object, and the second operation is the operation corresponding to the first operation.

2. The method according to claim 1, wherein The target configuration includes at least one of the following: measurement configuration, measurement identifier, measurement object, reporting configuration.

3. The method according to claim 1 or 2, characterized in that, When the terminal determines to perform a first operation, performing a second operation on a target configuration includes at least one of the following: When the terminal determines to activate the AI object, it activates the target configuration; When the terminal determines to deactivate the AI object, it deactivates the target configuration; When the terminal determines to perform a fallback to non-AI object operation, it stops evaluating the predicted events configured for the target configuration and evaluates the measurement events configured for the target configuration; When the terminal determines to perform an AI object switch, it includes the prediction result based on the switched AI object in the measurement report associated with the target configuration, and the target configuration is the configuration associated with the switched AI object.

4. The method according to claim 3, characterized in that, Activating the target configuration includes at least one of the following: When meeting the periodic reporting condition or reporting trigger event associated with the first reporting configuration, carrying at least one of the measurement result and the prediction result in the measurement report associated with the first reporting configuration; When meeting the predicted event for triggering a conditional handover associated with the first reporting configuration, performing a conditional handover; Wherein, the first reporting configuration is the reporting configuration associated with the target configuration, or the first reporting configuration is the reporting configuration in the target configuration.

5. The method according to claim 3, characterized in that, Deactivating the target configuration includes: Stopping the reporting of the measurement report associated with the first reporting configuration; Or, When meeting the periodic reporting condition or reporting trigger event associated with the first reporting configuration, only carrying the measurement result in the measurement report associated with the first reporting configuration; Or, When a predicted event is configured in the first reporting configuration, stopping the evaluation of the predicted event; Or, When a predicted event and a measurement event are configured in the first reporting configuration, stopping the evaluation of the predicted event and evaluating the measurement event; Wherein, the first reporting configuration is the reporting configuration associated with the target configuration, or the first reporting configuration is the reporting configuration in the target configuration.

6. The method according to claim 4 or 5, characterized in that, The reporting trigger event includes a measurement event for triggering measurement reporting or a predicted event for triggering measurement reporting.

7. The method according to claim 3, wherein When determining to perform an AI object switch, the method further includes at least one of the following: The terminal stops predicting using the AI object before the switch and uses the switched AI object for prediction; The terminal releases the prediction result of the AI object based on before handover saved by the terminal; The terminal performs a third operation using the prediction result of the AI object based on after handover, where the third operation includes at least one of the following: determining whether a prediction event for triggering measurement reporting is satisfied to trigger measurement reporting, determining whether a prediction event for triggering conditional handover is satisfied to trigger conditional handover.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: The terminal receives first indication information sent by a network side device, where the first indication information is used to instruct the terminal to perform the first operation.

9. The method according to any one of claims 1 to 8, characterized in that The method further includes: The terminal determines whether to perform a fourth operation according to the monitoring result of the AI object and a first threshold; Wherein, the first threshold is configured by the network side device or predefined by the protocol, and the fourth operation includes AI object deactivation or AI object handover or fallback to non-AI object operation.

10. The method according to claim 9, wherein The first threshold includes thresholds corresponding to respective monitoring metric parameters of the AI object; the terminal determining whether to perform the fourth operation according to the monitoring result of the AI object and the first threshold includes: In case at least one of the following is satisfied, the terminal determines to perform the fourth operation; The RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy; The prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, where N is a positive integer; The prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, where M is a positive integer; The prediction accuracy of a measurement event is less than or equal to the threshold corresponding to the measurement event; The prediction accuracy of handover failure HOF is less than or equal to the threshold corresponding to the HOF; The prediction accuracy of radio link failure RLF is less than or equal to the threshold corresponding to the RLF; The number of occurrences or probability of abnormal events within a first time period is greater than or equal to the threshold corresponding to the abnormal events; The handover delay or interruption duration within a second time period is greater than or equal to the threshold corresponding to the handover delay or interruption duration; The number of handovers within a unit time or a third time period is greater than the threshold corresponding to the number of handovers.

11. The method according to claim 10, wherein The abnormal events include at least one of the following: ping-pong handover, premature handover, late handover, handover to a wrong cell, handover failure, radio link failure.

12. The method according to any one of claims 9 to 11, characterized in that, The first threshold is associated with a first object, where the first object includes one of the following: terminal, cell, frequency point, AI object, measurement configuration, measurement identifier, measurement object, reporting configuration.

13. The method according to any one of claims 10 to 12, characterized in that, The method further includes: The terminal sends first information to the network side device; Wherein, the first information includes at least one of the following: Second indication information for indicating the fourth operation performed by the terminal, where the fourth operation includes AI object deactivation or AI object handover or fallback to non-AI object operation; The RRM measurement prediction accuracy; The prediction accuracy of the optimal N cells; The prediction accuracy of the optimal M beams; The prediction accuracy of the RRM measurement event; The prediction accuracy of HOF; The prediction accuracy of RLF; The number of occurrences or probability of abnormal events within a first time period; The handover latency or interruption duration within the second time period; The number of handovers within a unit time or the third time period; The identifier of the AI object after handover.

14. The method according to any one of claims 1 to 13, characterized in that, The target configuration is associated with at least one of the following: a prediction indication, an AI object identifier, a prediction event.

15. The method according to claim 14, characterized in that, The prediction indication is used to indicate that the measurement report associated with the target configuration needs to carry a prediction result; Or, When the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering a conditional handover, the prediction indication is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers a conditional handover when the first measurement event is satisfied; Or, The prediction indication is used to indicate a prediction type, and the prediction type includes at least one of the following: cell prediction, beam prediction, RRM measurement prediction, measurement event prediction.

16. The method according to claim 14 or 15, characterized in that, The AI object identifier is used to indicate that the measurement report associated with the target configuration needs to carry a prediction result; Or, When the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering a conditional handover, the AI object identifier is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers a conditional handover when the first measurement event is satisfied; Or, The AI object identifier is used to indicate that the terminal uses the AI object corresponding to the AI object identifier to obtain a prediction result, and carries the prediction result in the measurement report associated with the target configuration when the reporting condition is satisfied.

17. The method according to any one of claims 14 to 16, characterized in that, The prediction event includes at least one of the following: a first prediction event for triggering a measurement report, a second prediction event for triggering a conditional handover; Wherein, the first prediction event evaluates whether to trigger a measurement report according to the prediction result of at least one of the serving cell and the neighboring cell, and the second prediction event evaluates whether to trigger a conditional handover according to the prediction result of at least one of the serving cell and the neighboring cell.

18. The method according to claim 17, wherein The target configuration is a reporting configuration; When the reporting configuration is associated with the first prediction event, the first prediction event is used to indicate that the terminal evaluates whether the first prediction event is satisfied according to the prediction result of at least one of the serving cell and the neighboring cell, and triggers a measurement report when the first prediction event is satisfied; Or, When the reporting configuration is associated with a second prediction event for triggering a conditional handover, the second prediction event is used to indicate that the terminal evaluates whether the second prediction event is satisfied according to the prediction result of at least one of the serving cell and the neighboring cell, and triggers a conditional handover when the second prediction event is satisfied.

19. An AI object management method, characterized in that, Including: The network-side device performs a fifth operation, where the fifth operation includes at least one of the following: Sending a target configuration to the terminal, where the target configuration is associated with an AI object, and the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management (RRM) measurement prediction, target cell prediction, measurement event prediction, radio link failure (RLF) prediction, and handover failure (HOF) prediction; Receive the first information sent by the receiving terminal, where the first information includes at least one of the following: The second indication information, which is used to indicate the fourth operation performed by the terminal, and the fourth operation includes AI object deactivation, AI object switching, or fallback to non-AI object operation; RRM measurement prediction accuracy; Prediction accuracy of the optimal N cells; Prediction accuracy of the optimal M beams; Prediction accuracy of measurement events; Prediction accuracy of HOF; Prediction accuracy of RLF; The number of occurrences or probability of abnormal events within the first time period; The handover delay or interruption duration within the second time period; The number of handovers per unit time or within the third time period; The identifier of the AI object after handover.

20. The method according to claim 19, wherein The target configuration includes at least one of the following: measurement configuration, measurement identifier, measurement object, reporting configuration.

21. The method according to claim 19 or 20, characterized in that, The target configuration is associated with at least one of the following: prediction indication, AI object identifier, prediction event.

22. The method according to claim 21, wherein The prediction indication is used to indicate that the measurement report associated with the target configuration needs to carry a prediction result; Or, When the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering conditional handover, the prediction indication is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers conditional handover when the first measurement event is satisfied; Or, The prediction indication is used to indicate the prediction type, and the prediction type includes at least one of the following: cell prediction, beam prediction, RRM measurement prediction, measurement event prediction.

23. The method according to claim 21 or 22, characterized in that, The AI object identifier is used to indicate that the measurement report associated with the target configuration needs to carry a prediction result; Or, When the target configuration is a reporting configuration and the reporting configuration is associated with a first measurement event for triggering conditional handover, the AI object identifier is used to indicate that the terminal evaluates whether the first measurement event is satisfied based on the prediction result, and triggers conditional handover when the first measurement event is satisfied; Or, The AI object identifier is used to indicate that the terminal uses the AI object corresponding to the AI object identifier to obtain a prediction result, and carries the prediction result in the measurement report associated with the target configuration when the reporting condition is met.

24. The method according to any one of claims 21 to 23, characterized in that, The prediction event includes at least one of the following: a first prediction event for triggering measurement reporting, a second prediction event for triggering conditional handover; Wherein, the first prediction event evaluates whether to trigger measurement reporting according to the prediction result of at least one of the serving cell and neighboring cells, and the second prediction event evaluates whether to trigger conditional handover according to the prediction result of at least one of the serving cell and neighboring cells.

25. The method according to claim 24, wherein The target configuration is a reporting configuration; When the reporting configuration is associated with the first prediction event, the first prediction event is used to indicate that the terminal evaluates whether the first prediction event is satisfied according to the prediction result, and triggers measurement reporting when the first prediction event is satisfied; Or, When the reporting configuration is associated with the second prediction event, the second prediction event is used to instruct the terminal to evaluate whether the second prediction event is satisfied according to the prediction result, and trigger a conditional handover when the second prediction event is satisfied.

26. The method according to any one of claims 19 to 25, characterized in that The method further includes: The network side device sends first indication information to the terminal, where the first indication information is used to instruct the terminal to perform a first operation, and the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, AI object handover.

27. The method according to any one of claims 19 to 25, characterized in that, The method further includes: The network side device sends a first threshold to the terminal; wherein, the first threshold is used for the terminal to determine whether to perform a fourth operation, and the fourth operation includes AI object deactivation or AI object handover or fallback to non-AI object operation.

28. The method according to claim 27, wherein The first threshold includes thresholds corresponding to each monitoring metric parameter of the AI object; wherein, the monitoring metric parameters of the AI object include at least one of the following: RRM measurement prediction accuracy; Prediction accuracy of the optimal N cells, where N is a positive integer; Prediction accuracy of the optimal M beams, where M is a positive integer; Prediction accuracy of handover failure HOF; Prediction accuracy of radio link failure RLF; Prediction accuracy of measurement events; Number or probability of abnormal events occurring within a first time period; Handover delay or interruption duration within a second time period; Number of handovers per unit time or within a third time period.

29. An AI object management device, characterized in that, Includes: A first execution module, configured to perform a second operation on a target configuration when it is determined to perform the first operation; wherein, the first operation includes one of the following: AI object activation, AI object deactivation, fallback to non-AI object operation, AI object handover; the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management RRM measurement prediction, target cell prediction, measurement event prediction, RLF prediction, and HOF prediction; The target configuration is the configuration associated with the AI object, and the second operation is the operation corresponding to the first operation.

30. An AI object management device, characterized in that, Includes: An execution module, configured to perform a fifth operation, where the fifth operation includes at least one of the following: Send a target configuration to the terminal, where the target configuration is associated with an AI object, and the AI object includes an AI model or an AI function, and the AI object is used for at least one of the following: radio resource management RRM measurement prediction, target cell prediction, measurement event prediction, radio link failure RLF prediction, and handover failure HOF prediction; Receive first information sent by the terminal, where the first information includes at least one of the following: Second indication information, used to indicate the fourth operation performed by the terminal, and the fourth operation includes AI object deactivation or AI object handover or fallback to non-AI object operation; RRM measurement prediction accuracy; Prediction accuracy of the optimal N cells; Prediction accuracy of the optimal M beams; Prediction accuracy of measurement events; Prediction accuracy of HOF; Prediction accuracy of RLF; Number or probability of abnormal events occurring within a first time period; The handover latency or interruption duration within the second time period; The number of handovers within a unit time or the third time period; The identifier of the AI object after handover.

31. A terminal, characterized in that, It includes a processor and a memory. The memory stores programs or instructions that can run on the processor. When the programs or instructions are executed by the processor, the steps of the AI object management method according to any one of claims 1 to 18 are implemented.

32. A network-side device, characterized in that, It includes a processor and a memory. The memory stores programs or instructions that can run on the processor. When the programs or instructions are executed by the processor, the steps of the AI object management method according to any one of claims 19 to 28 are implemented.

33. A readable storage medium, characterized in that, Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the steps of the AI object management method according to any one of claims 1 to 18 are implemented, or the steps of the AI object management method according to any one of claims 19 to 28 are implemented.

34. A computer program product, characterized in that, The computer program product includes a computer program or computer instructions. The computer program or computer instructions are executed by at least one processor to implement the steps of the AI object management method according to any one of claims 1 to 18, or to implement the steps of the AI object management method according to any one of claims 19 to 28.

Images