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

Abstract

The invention discloses an AI object monitoring method and device, a terminal and network side equipment, and belongs to the technical field of communication, and the AI object monitoring method comprises the steps that the terminal executes a first operation according to a first parameter, or the terminal sends a first measurement report to the network side equipment; wherein the first operation comprises at least one of AI object monitoring and AI object monitoring result reporting, and the first parameter comprises at least one of the following items: a monitoring index parameter of the AI object and a reporting parameter of the AI object monitoring result; the first measurement report is used for the network side equipment to monitor the AI object, the first measurement report comprises a first prediction result based on the AI object, and the first prediction result comprises at least one of a radio resource management (RRM) measurement prediction result and an event prediction result; the AI object comprises an AI model or an AI function, and the AI object is an AI object used for mobility management.

Description

Technical Field

[0001] This application belongs to the field of communication technologies, and particularly relates to an AI object monitoring 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 related technologies, there is no corresponding solution for how to monitor an AI model or AI function in mobility management to ensure the reliability of prediction results, thus affecting the reliability of the prediction results of the AI model or AI function. Summary of the Invention

[0003] Embodiments of this application provide an AI object monitoring method, apparatus, terminal, and network-side device, which can monitor an AI model or AI function during the mobility management process to improve the reliability of the prediction results of the AI model or AI function.

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

[0005] The terminal performs a first operation according to a first parameter, or the terminal sends a first measurement report to a network-side device;

[0006] wherein the first operation includes at least one of AI object monitoring and reporting of the monitoring result of the AI object, and the first parameter includes at least one of the following: the monitoring metric parameter of the AI object, the reporting parameter of the monitoring result of the AI object;

[0007] The first measurement report is used for the network-side device to monitor the AI object. The first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result;

[0008] The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0009] In a second aspect, an AI object monitoring apparatus is provided. The apparatus includes:

[0010] A first execution module, configured to perform a first operation according to a first parameter, or send a first measurement report to a network-side device;

[0011] Among them, the first operation includes at least one of AI object monitoring and reporting of the monitoring result of the AI object, and the first parameter includes at least one of the following: the monitoring metric parameter of the AI object, the reporting parameter of the monitoring result of the AI object;

[0012] The first measurement report is used for the network side device to monitor the AI object. The first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result;

[0013] The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0014] In a third aspect, an AI object monitoring method is provided. The method includes:

[0015] The network side device sends a first parameter to the terminal, or the network side device receives a first measurement report sent by the terminal;

[0016] Among them, the first parameter is used for the terminal to perform a first operation. The first operation includes at least one of AI object monitoring and reporting of the monitoring result of the AI object, and the first parameter includes at least one of the following: the monitoring metric parameter of the AI object, the reporting parameter of the monitoring result of the AI object;

[0017] The first measurement report is used for the network side device to monitor the AI object. The first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result;

[0018] The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0019] In a fourth aspect, an AI object monitoring device is provided. The device includes:

[0020] A transmission module, configured to send a first parameter to the terminal, or the network side device receives a first measurement report sent by the terminal;

[0021] Among them, the first parameter is used for the terminal to perform a first operation. The first operation includes at least one of AI object monitoring and reporting of the monitoring result of the AI object, and the first parameter includes at least one of the following: the monitoring metric parameter of the AI object, the reporting parameter of the monitoring result of the AI object;

[0022] The first measurement report is used by the network-side device to monitor the AI object. The first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result;

[0023] The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0024] In a fifth aspect, a terminal is provided. The terminal includes a processor and a memory. The memory stores a program or instruction that can run on the processor. When the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0025] In a sixth aspect, a terminal is provided, including a processor and a communication interface. Wherein, the processor is configured to perform a first operation according to a first parameter, or the communication interface is configured to send a first measurement report to the network-side device;

[0026] Wherein, the first operation includes at least one of AI object monitoring and reporting of the monitoring result of the AI object, and the first parameter includes at least one of the following: a monitoring metric parameter of the AI object, a reporting parameter of the monitoring result of the AI object;

[0027] The first measurement report is used by the network-side device to monitor the AI object. The first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result;

[0028] The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0029] 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 instruction that can run on the processor. When the program or instruction is executed by the processor, the steps of the method described in the third aspect are implemented.

[0030] In an eighth aspect, a network-side device is provided, including a processor and a communication interface. Wherein, the communication interface is configured to send a first parameter to the terminal, or receive the first measurement report sent by the terminal;

[0031] Wherein, the first parameter is used for the terminal to perform a first operation. The first operation includes at least one of AI object monitoring and reporting of the monitoring result of the AI object, and the first parameter includes at least one of the following: a monitoring metric parameter of the AI object, a reporting parameter of the monitoring result of the AI object;

[0032] The first measurement report is used by the network-side device to monitor the AI object. The first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result.

[0033] The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0034] In a ninth aspect, an AI object monitoring system is provided, including: a terminal and a network-side device. The terminal can be used to execute the steps of the AI object monitoring method described in the first aspect, and the network-side device can be used to execute the steps of the AI object monitoring method described in the third aspect.

[0035] In a tenth aspect, a readable storage medium is provided. A program or instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the third aspect are implemented.

[0036] In an eleventh aspect, a chip is provided. The chip 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 to implement the steps of the method described in the third aspect.

[0037] In a twelfth aspect, a computer program / program product is provided. The computer program / program product includes a computer program or computer instruction, and 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 to implement the steps of the method described in the third aspect.

[0038] In an embodiment of the present application, the terminal performs a first operation according to a first parameter, or the terminal sends a first measurement report to a network-side device; wherein, the first operation includes at least one of AI object monitoring and reporting of monitoring results of the AI object, and the first parameter includes at least one of the following: monitoring metric parameters of the AI object, reporting parameters of the monitoring results of the AI object; the first measurement report is used for the network-side device to monitor the AI object, and the first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result; the AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management, that is, in an embodiment of the present application, the terminal can perform at least one of AI object monitoring and reporting of monitoring results of the AI object according to the first parameter, or the terminal reports a prediction result based on the AI object to the network-side device, so that the network-side device monitors the AI object based on the prediction result of the AI object, realizing the monitoring of the AI model or AI function in the process of mobility management, and thus facilitating the improvement of the reliability of the prediction result of the AI model or AI function. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a block diagram of a wireless communication system to which an embodiment of the present application can be applied;

[0040] Figure 2a is a schematic structural diagram of a neural network provided by an embodiment of the present application;

[0041] Figure 2b is a schematic structural diagram of a neuron provided by an embodiment of the present application;

[0042] Figure 3 is a schematic diagram of an AI / ML functional architecture provided by an embodiment of the present application;

[0043] Figure 4 is a flowchart of an AI object monitoring method provided by an embodiment of the present application;

[0044] Figure 5 is a flowchart of another AI object monitoring method provided by an embodiment of the present application;

[0045] Figure 6 is a structural diagram of an AI object monitoring device provided by an embodiment of the present application;

[0046] Figure 7 is a structural diagram of another AI object monitoring device provided by an embodiment of the present application;

[0047] Figure 8 is a structural diagram of a communication device provided by an embodiment of the present application;

[0048] Figure 9 is a structural diagram of the terminal provided by an embodiment of the present application;

[0049] Figure 10 is a structural diagram of the network-side device provided by an embodiment of the present application. Specific embodiments

[0050] 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 of 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.

[0051] The terms "first", "second", etc. in the present 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 the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are usually of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "or" in the present 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 an "or" relationship between the associated objects before and after.

[0052] The term "indicate" in the present 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 recipient of specific information, operations to be performed, or request results, etc. in the sent indication; an indirect indication can be understood as that the recipient 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.

[0053] It should be noted that the technology described in the embodiments of this application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in the embodiments of this application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, as well as in other systems and radio technologies. The following description describes the New Radio (NR) system for example purposes, and the NR term is used 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 th Generation, 6G) communication system.

[0054] Figure 1The block diagram of a wireless communication system to which embodiments of the present application can be applied is shown. 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 devices 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 may 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.

[0055] 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.

[0056] For ease of understanding, some content related to the embodiments of this application is described below:

[0057] I. Artificial Intelligence (AI)

[0058] 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.

[0059] 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.

[0060] 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, based on 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.

[0061] 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 layer by layer through the hidden layer to the input layer in a certain form, 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.

[0062] 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 Prop (RMSprop), Adaptive Moment Estimation (Adam), etc.

[0063] 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 add the learning rate, previous gradients / derivatives / partial derivatives, etc. to obtain the gradient, which is then passed to the previous layer.

[0064] II. AI Unit / AI Model

[0065] 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. Alternatively, 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 data set, 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 data set includes at least one of the input and output of the AI unit / AI model.

[0066] 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 data set associated with the AI unit / AI model, or the identifier of a specific scenario, environment, channel feature, 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.

[0067] AI functionality: That is, an AI algorithm function, which can include multiple AI models.

[0068] III. AI / ML Architecture (Framework)

[0069] The air interface AI project of Release 18 studied the AI / ML framework, such as Figure 3 shown below, and the main processes are as follows:

[0070] Data Collection: Responsible for providing input data for Model Training, Management, and Inference;

[0071] Model Training: Responsible for performing AI / ML model training, verification, and testing. Also responsible for data preparation, i.e., data preprocessing, conversion into a specific format, etc.;

[0072] Management: Responsible for model selection / activation / deactivation / switching / rollback, etc.;

[0073] Inference: Responsible for providing the output after applying the AI / ML model or AI / ML function;

[0074] Model Storage: Responsible for saving the trained / updated model

[0075] Model Transfer / Delivery: Responsible for delivering the AI / ML model to the inference function node.

[0076] IV. RRM Measurement Report

[0077] The measurement configuration mainly consists of a measurement object, a reporting configuration, and a measurement identifier (ID);

[0078] Measurement Object: That is, the frequency point to be measured

[0079] Report Configuration (ReportConfig): It includes reporting criteria (periodic / event-triggered); reference signal types (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 reportable beams, etc.;

[0080] Measurement Identity (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.

[0081] Optionally, the above three are associated together in the following way:

[0082]

[0083] The reporting configuration can include event-triggered reporting. The events defined in NR can be seen in Table 1, including the following events:

[0084] Table 1

[0085]

[0086]

[0087] Taking event A3 as an example, the meanings of the parameters for the entry condition and the departure condition are as follows:

[0088] Mn: Neighboring cell measurement result without considering any offset;

[0089] Ofn: Neighboring cell measurement object specific offset;

[0090] Ocn: Neighboring cell specific offset at the cell level;

[0091] Mp: Serving cell (SpCell) measurement result without considering any offset;

[0092] Ofp: SpCell measurement object specific offset;

[0093] Ocp: SpCell specific offset at the cell level;

[0094] Hys: Hysteresis parameter of the event;

[0095] Off: Offset parameter of the event.

[0096] 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 conditions of the event within the timeToTrigger time, a measurement report is triggered;

[0097] For conditional handover, the UE uses the cell that meets the conditions as the trigger cell and selects one to perform conditional reconfiguration in the trigger cell.

[0098] V. Conditional Handover

[0099] 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.

[0100] Taking the parameters in NR as an example:

[0101] 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 set of candidate cell configurations for conditional reconfiguration of a candidate PCell, as follows:

[0102]

[0103] 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 conditions of the event within the timeToTrigger time, the UE uses the cell that meets the conditions as the trigger cell and selects one to perform conditional reconfiguration in the trigger cell.

[0104] The following combines the accompanying drawings and details the AI object monitoring method provided by the embodiments of the present application through some embodiments and their application scenarios.

[0105] Please refer to Figure 4 , Figure 4 which is a flowchart of an AI object monitoring 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:

[0106] Step 401, the terminal performs a first operation according to a first parameter, or the terminal sends a first measurement report to a network-side device;

[0107] Among them, the first operation includes at least one of AI object monitoring and reporting of monitoring results of the AI object, and the first parameter includes at least one of the following: monitoring index parameters of the AI object, reporting parameters of the monitoring results of the AI object;

[0108] The first measurement report is used for the network-side device to monitor the AI object. The first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result;

[0109] The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0110] In this embodiment, the above first parameter can be configured by the network-side device or can be predefined by the protocol. Among them, the above first parameter includes at least one of the monitoring index parameters of the AI object and the reporting parameters of the monitoring results of the AI object.

[0111] Exemplarily, the monitoring index parameters of the above AI object may include, but are not limited to, RRM measurement prediction accuracy, prediction accuracy of the optimal cell / beam, prediction accuracy of measurement events, etc.

[0112] The monitoring result of the above AI object can be understood as the result obtained by monitoring the AI object based on the monitoring index parameters of the AI object. Exemplarily, if the monitoring index parameter includes RRM measurement prediction accuracy, the monitoring result of the above AI object may include the value of the RRM measurement prediction accuracy. If the monitoring index parameter includes the prediction accuracy of the measurement event, the monitoring result of the above AI object may include the value of the prediction accuracy of the measurement event.

[0113] Exemplarily, the reporting parameters of the monitoring results of the above AI object may include, but are not limited to, at least one of the reporting period, reporting event, reporting threshold, etc. of the monitoring results of the above AI object.

[0114] Exemplarily, when the first parameter includes the monitoring metric parameter of the AI object, the terminal can monitor the AI object according to the monitoring metric parameter of the AI object; when the first parameter includes the reporting parameter of the monitoring result of the AI object, the terminal can report the monitoring result of the AI object according to the reporting parameter of the monitoring result of the AI object; when the first parameter includes the monitoring metric parameter of the AI object and the reporting parameter of the monitoring result of the AI object, the terminal can monitor the AI object according to the monitoring metric parameter of the AI object and report the monitoring result of the AI object according to the reporting parameter of the monitoring result of the AI object.

[0115] The above first measurement report may include a prediction result based on the AI object, that is, a first prediction result, and the first prediction result includes at least one of an RRM measurement prediction result and an event prediction result. Exemplarily, the above RRM measurement prediction result may be understood as a result obtained by predicting the RRM measurement amount based on the AI object. For example, it is a prediction result of the cell signal quality of at least one of the serving cell, neighboring cell signal, candidate cell, and target cell; the above event prediction result may be understood as a result obtained by predicting an event based on the AI object. For example, it is at least one of a prediction result of a measurement event, a prediction result of a handover failure (HOF), a radio link failure (RLF), etc.

[0116] It can be understood that the terminal sends the first measurement report to the network-side device. In this case, when the network-side device receives the first measurement report, it can monitor the AI object based on the first prediction result to obtain the monitoring result of the AI object. For example, if the terminal sends the prediction result of HOF to the network-side device, the network-side device can monitor the AI object used for HOF prediction based on the prediction result of HOF and the actual result of HOF (that is, whether HOF actually occurs) to obtain the prediction accuracy of the AI object for HOF; if the terminal sends the prediction result of RLF to the network-side device, the network-side device can monitor the AI object used for RLF prediction based on the prediction result of RLF and the actual result of RLF (that is, whether RLF actually occurs) to obtain the prediction accuracy of the AI object for RLF; if the terminal sends the RRM measurement prediction result to the network-side device, the network-side device can monitor the AI object used for RRM measurement prediction based on the RRM measurement prediction result and the actual result of the RRM measurement (that is, the RRM measurement result obtained by the terminal's RRM measurement) to obtain the RRM measurement prediction accuracy of the AI object.

[0117] It should be noted that the above AI objects for mobility management may include at least one AI object. Exemplarily, the above AI objects for mobility management may include at least one of an AI object for RRM measurement prediction, an AI object for measurement event prediction, an AI object for HOF prediction, an AI object for RLF prediction, etc.

[0118] In the embodiment of the present application, the terminal performs a first operation according to a first parameter, or the terminal sends a first measurement report to the network-side device; wherein, the first operation includes at least one of AI object monitoring and reporting of the monitoring result of the AI object, and the first parameter includes at least one of the following: the monitoring metric parameter of the AI object, the reporting parameter of the monitoring result of the AI object; the first measurement report is used for the network-side device to monitor the AI object, the first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result; the AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management, that is, in the embodiment of the present application, the terminal can perform at least one of AI object monitoring and reporting of the monitoring result of the AI object according to the first parameter, or the terminal reports a prediction result based on the AI object to the network-side device, so that the network-side device monitors the AI object based on the prediction result of the AI object, realizing the monitoring of the AI model or the AI function in the process of mobility management, and thus facilitating the improvement of the reliability of the prediction result of the AI model or the AI function.

[0119] Optionally, the monitoring metric parameter of the AI object includes at least one of the following:

[0120] RRM measurement prediction accuracy;

[0121] Prediction accuracy of the optimal N cells, where N is a positive integer;

[0122] Prediction accuracy of the optimal M beams, where M is a positive integer;

[0123] Prediction accuracy of handover failure (HOF);

[0124] Prediction accuracy of radio link failure (RLF);

[0125] Prediction accuracy of measurement events;

[0126] Number or probability of abnormal events occurring within the first time period;

[0127] Handover delay or interruption duration within the second time period;

[0128] Number of handovers per unit time or within the third time period.

[0129] Exemplarily, the above RRM measurement prediction accuracy may include prediction errors such as RSRP / RSRQ / 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.

[0130] The prediction of the above measurement event can be understood as predicting whether the measurement event will be satisfied.

[0131] Exemplarily, the above handover delay or interruption duration may include the average handover delay or average interruption duration within the second time period.

[0132] The above N and M may be values predefined by the protocol or values configured by the network-side device.

[0133] The above first time period, second time period, and third time period may all be configured by the network-side device or predefined by the protocol.

[0134] The determination methods of the above various monitoring index parameters are respectively illustrated by examples as follows:

[0135] I. RRM measurement prediction accuracy: It is determined according to the RRM measurement prediction result and the error between the RRM measurement result corresponding to the RRM measurement prediction result and the RRM measurement result within the prediction 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.

[0136] II. The prediction accuracy of the optimal M beams or the optimal N cells is determined according to the following steps:

[0137] Step S11: The terminal predicts the optimal M beams or the optimal N cells at the second moment at the first moment;

[0138] Step S12: The terminal measures the signal quality of m beams or n cells at the second moment, where m >= M and n >= N. The m beams include the above M beams, or the n cells include the above N cells;

[0139] Step S13: The terminal sorts according to the signal quality from high to low and determines the actual optimal M beams or N cells;

[0140] Step S14: The terminal compares the prediction result of step S11 with the actual result of step S13 to determine whether the prediction is accurate.

[0141] III. The prediction accuracy rate of measurement events is determined according to the following steps:

[0142] 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;

[0143] 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;

[0144] Step S23: The terminal determines whether the measurement event prediction is accurate according to the prediction result and the actual result of the measurement event.

[0145] IV. The HOF prediction accuracy rate is determined according to the following steps:

[0146] Step S31: The terminal predicts at the fifth moment that HOF will occur in the second cell at the sixth moment;

[0147] 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 according to the measurement result can be implemented based on 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;

[0148] Step S33: The terminal determines whether the HOF prediction is accurate according to the prediction result and the actual result of HOF.

[0149] V. The RLF prediction accuracy rate is determined according to the following steps:

[0150] Step S41: The terminal predicts at the seventh moment that RLF will occur in the third cell at the eighth moment;

[0151] 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;

[0152] Step S43: The terminal determines whether the RLF prediction is accurate according to the prediction result and the actual result of RLF.

[0153] 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 pre-defined by the protocol).

[0154] VII. Handover latency / interruption duration during the second time period, or average handover latency / average interruption duration during the second time period: The terminal counts the handover latency / interruption duration during the second time period, or the terminal counts the average handover latency / average interruption duration during the second time period.

[0155] VIII. Number of handovers per unit time or during the third time period: The terminal counts the number of handovers within a unit time or during the third time period (configured by the network or predefined by the protocol).

[0156] In this embodiment, when monitoring the AI object based on at least one of the RRM measurement prediction accuracy, prediction accuracy of the optimal N cells, prediction accuracy of the optimal M beams, prediction accuracy of HOF, prediction accuracy of RLF, and prediction accuracy of measurement events, it is beneficial to ensure the accuracy of the prediction result of the AI object; when monitoring the AI object based on at least one of the number of abnormal events or probability within the first time period, handover latency or interruption duration during the second time period, and number of handovers per unit time or during the third time period, it is beneficial to ensure that the prediction result based on the AI object can meet the system performance requirements.

[0157] 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.

[0158] In this embodiment, the above premature handover can be understood as the terminal prematurely handing over to the target cell, resulting in a 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 a radio link failure in the source cell.

[0159] Optionally, the reporting parameters of the monitoring result include at least one of the following: reporting period, reporting trigger event, reporting threshold.

[0160] The above reporting period can be predefined by the protocol or configured by the network-side device. Exemplarily, the terminal can receive the reporting period configured by the network-side device and periodically report the monitoring result of the AI object according to the configured reporting period.

[0161] The above reporting trigger event can be understood as the time for triggering the reporting of the monitoring result of the AI object, which can be predefined by the protocol or configured by the network-side device. Exemplarily, the terminal can receive the reporting trigger event configured by the network-side device and trigger the reporting of the monitoring result of the AI object when the above reporting trigger event is satisfied.

[0162] The above reporting threshold can be used to compare with the value of the above monitoring metric parameter to determine whether to trigger the reporting of the monitoring result of the AI object, and can be predefined by the protocol or configured by the network-side device. Exemplarily, the terminal can receive the reporting threshold configured by the network-side device, and trigger the reporting of the monitoring result of the AI object when the value of the monitoring metric parameter meets the above reporting threshold.

[0163] Optionally, the reporting parameter of the monitoring result includes the reporting threshold, and the reporting threshold includes the thresholds corresponding to the respective monitoring metric parameters of the AI object; the terminal performs a first operation according to a first parameter, including at least one of the following:

[0164] When the RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy, the terminal reports the monitoring result of the AI object;

[0165] When the prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, the terminal reports the monitoring result of the AI object;

[0166] When the prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, the terminal reports the monitoring result of the AI object;

[0167] When the prediction accuracy of the measurement event is less than or equal to the threshold corresponding to the measurement event, the terminal reports the monitoring result of the AI object;

[0168] When 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, the terminal reports the monitoring result of the AI object;

[0169] When 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, the terminal reports the monitoring result of the AI object;

[0170] When the number of handovers within a unit time or the third time period is greater than or equal to the threshold corresponding to the number of handovers, the terminal reports the monitoring result of the AI object.

[0171] In this embodiment, the terminal determines whether to report the monitoring result of the AI object according to the comparison result between the value of each monitoring metric parameter and the corresponding threshold, which is beneficial to reducing some unnecessary reporting of monitoring results and saving system resources while ensuring the accuracy of the prediction result of the AI object.

[0172] Optionally, the reporting trigger event includes at least one of the following:

[0173] The first event occurs continuously for K1 times, or the first event occurs K1 times within the fourth time period, where the first event is that the RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy, and K1 is a positive integer;

[0174] The second event occurs continuously for K2 times, or the second event occurs K2 times within the fifth time period, where the second event is that the prediction of the optimal N cells is incorrect, or the prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, and K2 is a positive integer;

[0175] The third event occurs continuously for K3 times, or the third event occurs K3 times within the sixth time period, where the third event is that the prediction of the optimal M beams is incorrect, or the prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, and K3 is a positive integer;

[0176] The fourth event occurs continuously for K4 times, or the fourth event occurs K4 times within the seventh time period, where the fourth event is that the prediction of the measurement event is incorrect, or the prediction accuracy of the measurement event is less than or equal to the threshold corresponding to the measurement event, and K4 is a positive integer;

[0177] The abnormal event occurs continuously for K5 times, or the abnormal event occurs K5 times within the eighth time period, and K5 is a positive integer;

[0178] The fifth event occurs continuously for K6 times, or the fifth event occurs K6 times within the ninth time period, where the fifth event is that the handover delay or interruption duration is greater than or equal to the threshold corresponding to the handover delay or interruption duration, and K6 is a positive integer;

[0179] The handover occurs continuously for K7 times, or the handover occurs K7 times within the ninth time period, and K7 is a positive integer.

[0180] The above K1 to K7 can be predefined by the protocol, configured by the network-side device, or determined by the terminal.

[0181] The above fifth to ninth time periods can be predefined by the protocol, configured by the network-side device, or determined by the terminal.

[0182] Optionally, the reporting parameter 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.

[0183] Exemplarily, in the case where the above reporting parameter is associated with a terminal, the above reporting parameter can be used to report the monitoring results of each AI object of the terminal. For example, the terminal can periodically report the RRM measurement prediction accuracy of the AI object currently activated for RRM measurement prediction of the terminal based on the above reporting period, or the terminal can trigger the reporting of the RRM measurement prediction accuracy of the AI object currently activated for RRM measurement prediction of the terminal based on the above reporting trigger event.

[0184] Exemplarily, in the case where the above reporting parameter is associated with a cell, for example, a special cell (SpCell), then the above reporting parameter can be used to report the monitoring results corresponding to the cell. For example, the terminal can periodically report the RRM measurement prediction accuracy of the SpCell based on the above reporting period, or the terminal can trigger the reporting of the RRM measurement prediction accuracy of the SpCell based on the above reporting trigger event.

[0185] Exemplarily, in the case where the above reporting parameter is associated with a frequency point, then the above reporting parameter can be used to report the monitoring results corresponding to the cell on the frequency point. For example, the terminal can periodically report the RRM measurement prediction accuracy of the cell on the frequency point based on the above reporting period, or the terminal can trigger the reporting of the RRM measurement prediction accuracy of the cell on the frequency point based on the above reporting trigger event.

[0186] Exemplarily, in the case where the above reporting parameter is associated with an AI object, then the above reporting parameter can be used to report the monitoring results of the AI object. For example, the terminal can periodically report the RRM measurement prediction accuracy of the AI object based on the above reporting period, or the terminal can trigger the reporting of the RRM measurement prediction accuracy of the AI object based on the above reporting trigger event.

[0187] Exemplarily, in the case where the above reporting parameter is associated with a measurement configuration / measurement ID / measurement object / reporting configuration, then the above reporting parameter can be used to report the monitoring results of the AI object associated with the measurement configuration / measurement ID / measurement object / reporting configuration. For example, the terminal can periodically report the RRM measurement prediction accuracy of the AI object associated with the measurement configuration / measurement ID / measurement object / reporting configuration based on the above reporting period, or the terminal can trigger the reporting of the RRM measurement prediction accuracy of the AI object associated with the measurement configuration / measurement ID / measurement object / reporting configuration based on the above reporting trigger event.

[0188] Optionally, the method further includes:

[0189] The terminal sends a second measurement report to the network-side device;

[0190] Wherein, the second measurement report includes the actual result within the prediction time or prediction time period corresponding to the first prediction result.

[0191] For the prediction time or prediction time period corresponding to the above first prediction result, for example, if the terminal predicts the cell signal quality within at least one future time or at least one time period based on the AI object, then the above at least one time or at least one time period is the prediction time or prediction time period corresponding to the predicted cell signal quality.

[0192] The above actual result may include but is not limited to RRM measurement results, whether a measurement event actually occurs, whether RLF / HOF actually occurs, etc.

[0193] In this embodiment, the terminal sends the actual result within the prediction time or prediction time period corresponding to the first prediction result to the network-side device, so that the network-side device can more conveniently monitor the AI object based on the first prediction result and the actual result within its corresponding prediction time or prediction time period.

[0194] Optionally, the method further includes:

[0195] The terminal receives the second information sent by the network-side device;

[0196] Wherein, the second information is used to determine the correlation between the reporting time of the first measurement report and the reporting time of the second measurement report.

[0197] Exemplarily, the above second information may include the time interval between the reporting time of the first measurement report and the reporting time of the second measurement report.

[0198] In this embodiment, the above second information is used to determine the correlation between the reporting time of the first measurement report and the reporting time of the second measurement report, and then the terminal can control the reporting time of the first measurement report and the reporting time of the second measurement report based on the above second information.

[0199] Optionally, the second information includes the configuration information of a first timer; the terminal sending the second measurement report to the network-side device includes:

[0200] The terminal starts the first timer when sending the first measurement report to the network-side device;

[0201] The terminal sends the second measurement report to the network-side device when the first timer expires.

[0202] The above configuration information of the first timer may include the duration of the first timer.

[0203] Taking the RRM measurement prediction as an example, assume that the duration of the first timer is 1 s. The first measurement report carries the RRM measurement prediction result of cell 1 after 1 s. After the first measurement report is reported, the first timer is started. After the first timer expires, the terminal reports a second measurement report, which contains the RRM measurement result of cell 1 at the current moment, that is, the actual result. That is to say, by setting the first timer, it can be more accurately ensured that the second measurement report carries the actual result at the prediction moment corresponding to the RRM measurement prediction result.

[0204] Taking the event prediction as an example, assume that the duration of the first timer is 1 s. The first measurement report carries the prediction result that event A3 will be satisfied after 1 s. After the first measurement report is reported, the first timer is started. After the first timer expires, the terminal reports a second measurement report, which contains the actual result of whether event A3 is satisfied at the current moment. That is to say, by setting the first timer, it can be more accurately ensured that the second measurement report carries the actual result at the prediction moment corresponding to the prediction result that event A3 will be satisfied.

[0205] In this embodiment, when the terminal sends the first measurement report to the network-side device, it starts the first timer configured according to the configuration information of the first timer above. When the first timer expires, it sends the second measurement report. This is conducive to ensuring that the second measurement report carries the actual result at the prediction moment or prediction time period corresponding to the prediction result carried by the first measurement report.

[0206] Optionally, the first measurement report includes the first prediction results within T prediction moments or T prediction time periods. The first timer includes T timers. The T timers respectively correspond to the T prediction moments or T prediction time periods, and the durations of the T timers are different, where T is an integer greater than 1;

[0207] When the terminal starts the first timer when sending the first measurement report to the network-side device, it includes:

[0208] When the terminal sends the first measurement report to the network-side device, it starts the T timers;

[0209] When the terminal sends the second measurement report to the network-side device when the first timer expires, it includes:

[0210] When each of the T timers expires, the terminal respectively sends the second measurement report corresponding to each timer to the network-side device. Among them, the second measurement report corresponding to each timer respectively includes the actual result within the prediction moment or prediction time period corresponding to each timer.

[0211] In this embodiment, if the terminal carries prediction results of at least two prediction moments or prediction time periods in the first measurement report, after the terminal triggers the reporting of the first measurement report, it can start at least two timers with different durations simultaneously, and after each timer times out, it triggers the reporting of a measurement report carrying the actual result within the corresponding prediction moment or prediction time period.

[0212] Optionally, the first measurement report includes a first identifier, and the second measurement report includes the first identifier.

[0213] The above first identifier can be any identifier. For example, it can be any number, letter, or a combination of numbers and letters, etc.

[0214] In this embodiment, by carrying the same identifier, that is, the first identifier, in the first measurement report and the second measurement report, the network-side device can identify the second measurement report corresponding to the first measurement report based on the first identifier.

[0215] Optionally, the method further includes:

[0216] When a first condition is met, the terminal does not report the second measurement report or the actual result within the prediction moment or prediction time period corresponding to the first prediction result, and the second measurement report includes the actual result within the prediction moment or prediction time period corresponding to the first prediction result;

[0217] Wherein, the first condition includes any one of the following:

[0218] A handover, reconstruction, or redirection occurs;

[0219] The first prediction result is the same as the actual result within the prediction moment or prediction time period corresponding to the first prediction result, or the difference between the first prediction result and the actual result within the prediction moment or prediction time period corresponding to the first prediction result is less than or equal to a first threshold;

[0220] The measurement object associated with the first measurement report is deleted;

[0221] An RLF, HOF, or radio resource control (RRC) state transition occurs.

[0222] Exemplarily, after the terminal reports the first measurement report, if the first condition is met, the terminal does not report the second measurement report or the actual result within the prediction moment or prediction time period corresponding to the first prediction result; if the first condition is not met, the terminal can report the second measurement report or the actual result within the prediction moment or prediction time period corresponding to the first prediction result.

[0223] In some optional embodiments, when the first condition includes handover, reconstruction, or redirection, the terminal does not report the second measurement report to the source cell or the actual result during the prediction time or prediction time period corresponding to the first prediction result.

[0224] In this embodiment, when the first condition is satisfied, the terminal does not report the second measurement report or the actual result during the prediction time or prediction time period corresponding to the first prediction result, which can save resources.

[0225] Optionally, the method further includes:

[0226] When handover, reconstruction, or redirection occurs, the terminal performs a second operation;

[0227] Wherein, the second operation includes any one of the following:

[0228] When the AI object associated with the first measurement report is in an active state, report the second measurement report to the target cell;

[0229] When the AI object associated with the first measurement report is in an inactive state or has been released, do not report the second measurement report to the target cell;

[0230] Wherein, the second measurement report includes the actual result during the prediction time or prediction time period corresponding to the first prediction result.

[0231] The AI object associated with the above first measurement report can be understood as that the prediction result carried by the first measurement report includes the prediction result based on this AI object.

[0232] In this embodiment, when handover, reconstruction, or redirection occurs, if the AI object associated with the first measurement report is in an active state, the terminal can report the second measurement report to the target cell after the handover is completed, which is convenient for the target cell to monitor the AI object; if the AI object associated with the first measurement report is in an inactive state or has been released, the terminal has no need to monitor the AI object associated with the first measurement report. In this case, the terminal does not report the second measurement report to the target cell to save resources.

[0233] Optionally, the event prediction result includes at least one of the prediction result of the measurement event, the prediction result of the RLF, and the prediction result of the HOF.

[0234] Optionally, when the first prediction result includes the prediction result of the HOF, the method further includes:

[0235] The terminal starts a second timer after sending the first measurement report to the network-side device;

[0236] When the second timer expires, the terminal reports the actual result of the first predicted cell during the operation of the second timer;

[0237] Or,

[0238] When a HOF or RRC state transition occurs during the operation of the second timer, the terminal does not report the actual result of the first predicted cell during the operation of the second timer.

[0239] In this embodiment, the above first predicted cell can be understood as the cell targeted by the prediction result of the above HOF, that is, the prediction result of the HOF is the prediction result obtained by performing HOF prediction on the first predicted cell.

[0240] The duration of the above second timer can be predefined by the protocol or configured by the network-side device or determined by the terminal.

[0241] In some optional embodiments, when a HOF or RRC state transition occurs during the operation interval of the second timer, the terminal can stop the operation of the second timer and does not report the actual result of the first predicted cell during the operation of the second timer.

[0242] Optionally, when the first prediction result includes the prediction result of the RLF, the method further includes:

[0243] The terminal starts a third timer after sending a first measurement report to the network-side device;

[0244] When the third timer expires, the terminal reports the actual result of the second predicted cell during the operation of the third timer;

[0245] Or,

[0246] When an RLF or RRC state transition occurs during the operation of the third timer, the terminal does not report the actual result of the second predicted cell during the operation of the third timer.

[0247] In this embodiment, the above second predicted cell can be understood as the cell targeted by the prediction result of the above RLF, that is, the prediction result of the RLF is the prediction result obtained by performing RLF prediction on the second predicted cell.

[0248] The duration of the above third timer can be predefined by the protocol or configured by the network-side device or determined by the terminal.

[0249] In some optional embodiments, when RLF or RRC state transition occurs during the running period of the third timer, the terminal may stop the running of the third timer and does not report the actual result of the second predicted cell during the running period of the third timer.

[0250] The following is an example of the AI object monitoring for the network-side device to perform RLF or HOF prediction:

[0251] I. For HOF prediction, the terminal reports the measurement result of the target cell to the network-side device for the network-side device to monitor the AI object for HOF prediction. The specific steps are as follows:

[0252] At the ninth moment, the terminal predicts that HOF will occur in the fourth cell (for example, the target cell), and the terminal reports the prediction result of HOF to the network-side device;

[0253] The terminal starts the first timer. After the second timer expires, the terminal reports the measurement result or average measurement result of the fourth cell during the running period of the second timer.

[0254] Optionally, the terminal reports the prediction result of HOF at the tenth moment and reports the measurement result of the fourth cell within the first time period (i.e., during the running period of the second timer) at the eleventh moment;

[0255] Among them, if HOF occurs to the terminal before reporting the measurement result of the fourth cell within the first time period, the measurement result of the fourth cell within the first time period is not reported; if RRC state transition occurs before reporting the measurement result of the fourth cell within the first time period, the measurement result of the fourth cell within the first time period is not reported.

[0256] II. For RLF prediction, the terminal reports the measurement result of the source cell to the network for the network to monitor the AI object for RLF prediction. The specific steps are as follows:

[0257] At the twelfth moment, the terminal predicts that RLF will occur in the fifth cell (for example, the source cell), and the terminal reports the prediction result of RLF to the network-side device;

[0258] The terminal starts the third timer. After the third timer expires, the terminal reports the measurement result or average measurement result of the fifth cell within the third timer.

[0259] Optionally, the terminal reports the prediction result of HOF at the thirteenth moment and reports the measurement result of the fifth cell within the second time period (i.e., during the running period of the third timer) at the fourteenth moment;

[0260] Wherein, if the terminal experiences RLF before reporting the measurement results of the fifth cell in the second time period, the measurement results of the fifth cell in the second time period are not reported; if an RRC state transition occurs before reporting the measurement results of the fifth cell in the second time period, the measurement results of the fifth cell in the second time period are not reported.

[0261] Please refer to Figure 5 , Figure 5 is a flowchart of an AI object monitoring 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:

[0262] Step 501, the network-side device sends a first parameter to the terminal, or the network-side device receives a first measurement report sent by the terminal;

[0263] Wherein, the first parameter is used for the terminal to perform a first operation, and the first operation includes at least one of AI object monitoring and reporting of monitoring results of the AI object. The first parameter includes at least one of the following: monitoring index parameters of the AI object, reporting parameters of monitoring results of the AI object;

[0264] The first measurement report is used for the network-side device to monitor the AI object. The first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result;

[0265] The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0266] Optionally, the monitoring index parameters of the AI object include at least one of the following:

[0267] RRM measurement prediction accuracy;

[0268] Prediction accuracy of the optimal N cells, where N is a positive integer;

[0269] Prediction accuracy of the optimal M beams, where M is a positive integer;

[0270] Prediction accuracy of handover failure (HOF);

[0271] Prediction accuracy of radio link failure (RLF);

[0272] Prediction accuracy of measurement events;

[0273] Number or probability of abnormal events occurring within the first time period;

[0274] Handover delay or interruption duration within the second time period;

[0275] The number of handovers within a unit time or a third time period.

[0276] 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.

[0277] Optionally, the reporting parameters of the monitoring result include at least one of the following: reporting period, reporting trigger event, reporting threshold.

[0278] Optionally, the reporting threshold includes the thresholds corresponding to the respective monitoring metric parameters of the AI object.

[0279] Optionally, the reporting trigger event includes at least one of the following:

[0280] The first event occurs continuously K1 times, or the first event occurs K1 times within a fourth time period, where the first event is that the RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy, and K1 is a positive integer;

[0281] The second event occurs continuously K2 times, or the second event occurs K2 times within a fifth time period, where the second event is that the prediction of the optimal N cells is incorrect, or the prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, and K2 is a positive integer;

[0282] The third event occurs continuously K3 times, or the third event occurs K3 times within a sixth time period, where the third event is that the prediction of the optimal M beams is incorrect, or the prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, and K3 is a positive integer;

[0283] The fourth event occurs continuously K4 times, or the fourth event occurs K4 times within a seventh time period, where the fourth event is that the prediction of the measurement event is incorrect, or the prediction accuracy of the measurement event is less than or equal to the threshold corresponding to the measurement event, and K4 is a positive integer;

[0284] The abnormal event occurs continuously K5 times, or the abnormal event occurs K5 times within an eighth time period, and K5 is a positive integer;

[0285] The fifth event occurs continuously K6 times, or the fifth event occurs K6 times within a ninth time period, where the fifth event is that the handover delay or interruption duration is greater than or equal to the threshold corresponding to the handover delay or interruption duration, and K6 is a positive integer;

[0286] The handover occurs continuously K7 times, or the handover occurs K7 times within a ninth time period, and K7 is a positive integer.

[0287] Optionally, the reporting parameter is associated with a first object, where the first object includes one of the following: a terminal, a cell, a frequency point, an AI object, a measurement configuration, a measurement identifier, a measurement object, and a reporting configuration.

[0288] Optionally, the method further includes:

[0289] The network device receives a second measurement report sent by the terminal;

[0290] Wherein, the second measurement report includes the actual result within the prediction time or prediction time period corresponding to the first prediction result.

[0291] Optionally, the method further includes:

[0292] The network device sends second information to the terminal;

[0293] Wherein, the second information is used to determine the association relationship between the reporting time of the first measurement report and the reporting time of the second measurement report.

[0294] Optionally, the second information includes configuration information of a first timer, and the first timer is used to control the reporting time of the second measurement report.

[0295] Optionally, the first measurement report includes first prediction results within T prediction times or T prediction time periods, the first timer includes T timers, the T timers respectively correspond to the T prediction times or T prediction time periods, and the durations of the T timers are different, where T is an integer greater than 1.

[0296] Optionally, the first measurement report includes a first identifier, and the second measurement report includes the first identifier.

[0297] Optionally, the event prediction result includes at least one of a prediction result of a measurement event, a prediction result of RLF, and a prediction result of HOF.

[0298] It should be noted that the implementation manner of this embodiment can refer to the relevant description of the embodiment shown in Figure 4 and will not be elaborated here.

[0299] It should also be noted that the conditional handover in the embodiments of the present application may include conditional primary-secondary cell addition / modification (Conditional PSCell addition / change) or conditional LTM (i.e., Condition L1 / L2-triggered mobility).

[0300] It should also be noted that for the AI object monitoring method provided in the embodiments of the present application, the execution entity may be an AI object monitoring device, or a control module in the AI object monitoring device for executing the AI object monitoring method. In the embodiments of the present application, the case where the AI object monitoring device executes the AI object monitoring method is taken as an example to illustrate the AI object monitoring device provided in the embodiments of the present application.

[0301] Please refer to Figure 6 , Figure 6 which is a structural diagram of an AI object monitoring device provided in the embodiments of the present application. As Figure 6 shown, the AI object monitoring device 600 includes:

[0302] A first execution module 601, configured to execute a first operation according to a first parameter, or send a first measurement report to a network-side device;

[0303] Wherein, the first operation includes at least one of AI object monitoring and reporting of the monitoring result of the AI object, and the first parameter includes at least one of the following: the monitoring index parameter of the AI object, the reporting parameter of the monitoring result of the AI object;

[0304] The first measurement report is used for the network-side device to monitor the AI object, and the first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result;

[0305] The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0306] Optionally, the monitoring index parameter of the AI object includes at least one of the following:

[0307] RRM measurement prediction accuracy;

[0308] Prediction accuracy of the optimal N cells, where N is a positive integer;

[0309] Prediction accuracy of the optimal M beams, where M is a positive integer;

[0310] Prediction accuracy of handover failure (HOF);

[0311] Prediction accuracy of radio link failure (RLF);

[0312] Prediction accuracy of measurement events;

[0313] Number or probability of abnormal events occurring within a first time period;

[0314] Handover delay or interruption duration within a second time period;

[0315] The number of handovers within a unit time or a third time period.

[0316] Optionally, the abnormal event includes at least one of the following: ping-pong handover, premature handover, late handover, handover to a wrong cell, handover failure, radio link failure.

[0317] Optionally, the reporting parameters of the monitoring result include at least one of the following: reporting period, reporting trigger event, reporting threshold.

[0318] Optionally, the reporting parameters of the monitoring result include the reporting threshold, and the reporting threshold includes the thresholds corresponding to the monitoring metric parameters of the AI object; the terminal performs a first operation according to a first parameter, including at least one of the following:

[0319] When the RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy, the terminal reports the monitoring result of the AI object;

[0320] When the prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, the terminal reports the monitoring result of the AI object;

[0321] When the prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, the terminal reports the monitoring result of the AI object;

[0322] When the prediction accuracy of the measurement event is less than or equal to the threshold corresponding to the measurement event, the terminal reports the monitoring result of the AI object;

[0323] When the number of occurrences or probability of the abnormal event within the first time period is greater than or equal to the threshold corresponding to the abnormal event, the terminal reports the monitoring result of the AI object;

[0324] When 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, the terminal reports the monitoring result of the AI object;

[0325] When the number of handovers within a unit time or a third time period is greater than or equal to the threshold corresponding to the number of handovers, the terminal reports the monitoring result of the AI object.

[0326] Optionally, the reporting trigger event includes at least one of the following:

[0327] The first event occurs continuously for K1 times, or occurs K1 times within the fourth time period, where the first event is that the RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy, and K1 is a positive integer;

[0328] The second event occurs continuously for K2 times, or occurs K2 times within the fifth time period, where the second event is that the prediction of the optimal N cells is incorrect, or the prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, and K2 is a positive integer;

[0329] The third event occurs continuously for K3 times, or occurs K3 times within the sixth time period, where the third event is that the prediction of the optimal M beams is incorrect, or the prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, and K3 is a positive integer;

[0330] The fourth event occurs continuously for K4 times, or occurs K4 times within the seventh time period, where the fourth event is that the prediction of the measurement event is incorrect, or the prediction accuracy of the measurement event is less than or equal to the threshold corresponding to the measurement event, and K4 is a positive integer;

[0331] The abnormal event occurs continuously for K5 times, or occurs K5 times within the eighth time period, and K5 is a positive integer;

[0332] The fifth event occurs continuously for K6 times, or occurs K6 times within the ninth time period, where the fifth event is that the handover delay or interruption duration is greater than or equal to the threshold corresponding to the handover delay or interruption duration, and K6 is a positive integer;

[0333] The handover occurs continuously for K7 times, or occurs K7 times within the ninth time period, and K7 is a positive integer.

[0334] Optionally, the reporting parameter 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.

[0335] Optionally, the device further includes:

[0336] A first sending module, configured to send a second measurement report to the network-side device;

[0337] Wherein, the second measurement report includes the actual result within the prediction moment or prediction time period corresponding to the first prediction result.

[0338] Optionally, the device further includes:

[0339] A first receiving module, configured to receive second information sent by the network-side device;

[0340] Wherein, the second information is used to determine the correlation between the reporting time of the first measurement report and the reporting time of the second measurement report.

[0341] Optionally, the second information includes configuration information of a first timer; the first sending module includes:

[0342] A starting unit, configured to start the first timer when sending the first measurement report to the network-side device;

[0343] A sending unit, configured to send a second measurement report to the network-side device when the first timer expires.

[0344] Optionally, the first measurement report includes first prediction results within T prediction moments or T prediction time periods, the first timer includes T timers, the T timers respectively correspond to the T prediction moments or T prediction time periods, and the durations of the T timers are different, where T is an integer greater than 1;

[0345] The starting unit is specifically configured to:

[0346] Start the T timers when sending the first measurement report to the network-side device;

[0347] The sending unit is specifically configured to:

[0348] When each of the T timers expires, send a second measurement report corresponding to each timer to the network-side device respectively, where the second measurement report corresponding to each timer respectively includes the actual result within the prediction moment or prediction time period corresponding to each timer.

[0349] Optionally, the first measurement report includes a first identifier, and the second measurement report includes the first identifier.

[0350] Optionally, when a first condition is met, the second measurement report or the actual result within the prediction moment or prediction time period corresponding to the first prediction result is not reported, and the second measurement report includes the actual result within the prediction moment or prediction time period corresponding to the first prediction result;

[0351] Wherein, the first condition includes any one of the following:

[0352] A handover, reconstruction or redirection occurs;

[0353] The first prediction result is the same as the actual result during the prediction time or prediction time period corresponding to the first prediction result, or the difference between the first prediction result and the actual result during the prediction time or prediction time period corresponding to the first prediction result is less than or equal to a first threshold;

[0354] The measurement object associated with the first measurement report is deleted;

[0355] RLF, HOF or radio resource control (RRC) state transition occurs.

[0356] Optionally, the device further includes:

[0357] A second execution module, configured to perform a second operation when a handover, reconstruction or redirection occurs;

[0358] Wherein, the second operation includes any one of the following:

[0359] When the AI object associated with the first measurement report is in an active state, report a second measurement report to the target cell;

[0360] When the AI object associated with the first measurement report is in an inactive state or has been released, do not report a second measurement report to the target cell;

[0361] Wherein, the second measurement report includes the actual result during the prediction time or prediction time period corresponding to the first prediction result.

[0362] Optionally, the event prediction result includes at least one of a prediction result of a measurement event, a prediction result of RLF, and a prediction result of HOF.

[0363] Optionally, when the first prediction result includes the prediction result of HOF, the device further includes:

[0364] A first start module, configured to start a second timer after sending the first measurement report to the network side device;

[0365] A first reporting module, configured to report the actual result of the first predicted cell during the running period of the second timer when the second timer expires; or, when a HOF or RRC state transition occurs during the running period of the second timer, do not report the actual result of the first predicted cell during the running period of the second timer.

[0366] Optionally, when the first prediction result includes the prediction result of RLF, the device further includes:

[0367] A second start module, configured to start a third timer after sending the first measurement report to the network side device;

[0368] A second reporting module, configured to report the actual result of the second predicted cell during the operation of the third timer when the third timer times out; or, not report the actual result of the second predicted cell during the operation of the third timer when RLF or RRC state transition occurs during the operation of the third timer.

[0369] The AI object monitoring 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 terminal 11 listed above, 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.

[0370] The AI object monitoring 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.

[0371] Please refer to Figure 7 , Figure 7 which is a structural diagram of an AI object monitoring device provided in the embodiments of the present application. As shown in Figure 7 , the AI object monitoring device 700 includes:

[0372] A transmission module 701, configured to send a first parameter to the terminal, or receive a first measurement report sent by the terminal;

[0373] Wherein, the first parameter is used for the terminal to perform a first operation, and the first operation includes at least one of AI object monitoring and reporting of the monitoring result of the AI object. The first parameter includes at least one of the following: the monitoring index parameter of the AI object, the reporting parameter of the monitoring result of the AI object;

[0374] The first measurement report is used for the network side device to monitor the AI object. The first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result;

[0375] The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0376] Optionally, the monitoring index parameter of the AI object includes at least one of the following:

[0377] RRM measurement prediction accuracy;

[0378] Prediction accuracy of the optimal N cells, where N is a positive integer;

[0379] Prediction accuracy of the optimal M beams, where M is a positive integer;

[0380] Prediction accuracy of handover failure HOF;

[0381] Prediction accuracy of radio link failure RLF;

[0382] Prediction accuracy of measurement events;

[0383] Number or probability of abnormal events occurring within the first time period;

[0384] Handover delay or interruption duration within the second time period;

[0385] Number of handovers per unit time or within the third time period.

[0386] 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.

[0387] Optionally, the reporting parameters of the monitoring results include at least one of the following: reporting period, reporting trigger event, reporting threshold.

[0388] Optionally, the reporting threshold includes the thresholds corresponding to the respective monitoring metric parameters of the AI object.

[0389] Optionally, the reporting trigger event includes at least one of the following:

[0390] The first event occurs continuously K1 times, or the first event occurs K1 times within the fourth time period, where the first event is that the RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy, and K1 is a positive integer;

[0391] The second event occurs continuously K2 times, or the second event occurs K2 times within the fifth time period, where the second event is that the prediction of the optimal N cells is incorrect, or the prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, and K2 is a positive integer;

[0392] The third event occurs continuously K3 times, or the third event occurs K3 times within the sixth time period, where the third event is that the prediction of the optimal M beams is incorrect, or the prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, and K3 is a positive integer;

[0393] The fourth event occurs continuously K4 times, or the fourth event occurs K4 times within the seventh time period, where the fourth event is an incorrect prediction of a measurement event, or the prediction accuracy rate of the measurement event is less than or equal to the threshold corresponding to the measurement event, and K4 is a positive integer;

[0394] The abnormal event occurs continuously K5 times, or the abnormal event occurs K5 times within the eighth time period, and K5 is a positive integer;

[0395] The fifth event occurs continuously K6 times, or the fifth event occurs K6 times within the ninth time period, where the fifth event is that the handover delay or interruption duration is greater than or equal to the threshold corresponding to the handover delay or interruption duration, and K6 is a positive integer;

[0396] The handover occurs continuously K7 times, or the handover occurs K7 times within the ninth time period, and K7 is a positive integer.

[0397] Optionally, the reporting parameter 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.

[0398] Optionally, the method further includes:

[0399] A receiving module, configured to receive a second measurement report sent by the terminal;

[0400] Wherein, the second measurement report includes the actual result within the prediction moment or prediction time period corresponding to the first prediction result.

[0401] Optionally, the method further includes:

[0402] A sending module, configured to send second information to the terminal;

[0403] Wherein, the second information is used to determine the association relationship between the reporting time of the first measurement report and the reporting time of the second measurement report.

[0404] Optionally, the second information includes configuration information of a first timer, and the first timer is used to control the reporting time of the second measurement report.

[0405] Optionally, the first measurement report includes first prediction results within T prediction moments or T prediction time periods, the first timer includes T timers, the T timers respectively correspond to the T prediction moments or T prediction time periods, and the durations of the T timers are different, and T is an integer greater than 1.

[0406] Optionally, the first measurement report includes a first identifier, and the second measurement report includes the first identifier.

[0407] Optionally, the event prediction result includes at least one of a prediction result of a measurement event, a prediction result of RLF, and a prediction result of HOF.

[0408] The AI object monitoring 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 the network-side device. Exemplarily, the network-side device may include, but is not limited to, the types of the network-side device 12 listed above, 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.

[0409] The AI object monitoring device provided in the embodiments of the present application can implement Figure 5 each process implemented by the method embodiment, and achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0410] Optionally, as Figure 8 shown, the embodiments of the present application further 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 AI object monitoring method embodiment on the terminal side 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 AI object monitoring method embodiment on the network-side device side is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be elaborated here.

[0411] An embodiment of the present application further provides a terminal, including a processor and a communication interface. The processor is configured to perform a first operation according to a first parameter, or the communication interface is configured to send a first measurement report to a network-side device. Wherein, the first operation includes at least one of AI object monitoring and reporting of monitoring results of the AI object, and the first parameter includes at least one of the following: monitoring metric parameters of the AI object, reporting parameters of the monitoring results of the AI object; the first measurement report is used for the network-side device to monitor the AI object, and the first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result; the AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management. This terminal embodiment corresponds to the above terminal-side method embodiment, and each implementation process and implementation manner of the above method embodiment can be applied to this terminal embodiment and can achieve the same technical effect. Specifically, Figure 9 FIG. is a schematic diagram of the hardware structure of a terminal according to an embodiment of the present application.

[0412] 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.

[0413] 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 may 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 9 The terminal structure shown in 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.

[0414] 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 the video capture mode or the 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, for example, 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 referred to as 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, and a joystick, which will not be elaborated here.

[0415] 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.

[0416] The memory 909 can be used to store software programs or instructions and 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 can 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 can include volatile memory or non-volatile memory. Among them, the non-volatile memory can 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 can 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 synchronous 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.

[0417] 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.

[0418] Among them, the processor 910 is configured to perform a first operation according to a first parameter, or the radio frequency unit 901 is configured to send a first measurement report to a network-side device; wherein, the first operation includes at least one of AI object monitoring and reporting of monitoring results of the AI object, and the first parameter includes at least one of the following: monitoring metric parameters of the AI object, reporting parameters of the monitoring results of the AI object; the first measurement report is used for the network-side device to monitor the AI object, and the first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result; the AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

[0419] It can be understood that the implementation processes of the various implementation manners mentioned in this embodiment may 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.

[0420] The embodiment of the present application further provides a network-side device, including a processor and a communication interface. The communication interface is configured to send a first parameter to a terminal, or receive the first measurement report sent by the terminal; wherein, the first parameter is used for the terminal to perform a first operation, and the first operation includes at least one of AI object monitoring and reporting of monitoring results of the AI object, and the first parameter includes at least one of the following: monitoring metric parameters of the AI object, reporting parameters of the monitoring results of the AI object; the first measurement report is used for the network-side device to monitor the AI object, and the first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result; the AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management. This embodiment of the network-side device corresponds to the foregoing method embodiment of the network-side device. Each implementation process and implementation manner of the foregoing method embodiment can be applied to this embodiment of the network-side device and can achieve the same technical effect.

[0421] 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.

[0422] 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.

[0423] 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, 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.

[0424] The network-side device may further include a network interface 1006, and the interface is, for example, a Common Public Radio Interface (CPRI).

[0425] 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, and achieves the same technical effects. To avoid repetition, it will not be elaborated here.

[0426] 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-mentioned AI object monitoring method embodiments are implemented, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0427] 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.

[0428] 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 monitoring method, and can achieve the same technical effects. To avoid repetition, details are not described herein again.

[0429] 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.

[0430] Another embodiment of the present application further provides a computer program / program product, which includes computer programs or computer instructions. The computer programs or computer instructions are executed by at least one processor to implement each process of the above-mentioned embodiment of the AI object monitoring method, and can achieve the same technical effects. To avoid repetition, details are not described herein again.

[0431] The embodiments of the present application further provide an AI object monitoring 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, and 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, details are not described herein again.

[0432] It should be noted that in this article, the term "including", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so 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 also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the 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. In addition, the features described with reference to certain examples may be combined in other examples.

[0433] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment 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 discs, 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.

[0434] 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 all fall within the protection scope of the present application.

Claims

1. An AI object monitoring method, characterized in that, Including: The terminal performs a first operation according to a first parameter, or the terminal sends a first measurement report to a network-side device; Wherein, the first operation includes at least one of AI object monitoring and reporting of monitoring results of the AI object, and the first parameter includes at least one of the following: monitoring metric parameters of the AI object, reporting parameters of the monitoring results of the AI object; The first measurement report is used to monitor the AI object, and the first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result; The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

2. The method according to claim 1, 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.

3. The method according to claim 2, wherein 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.

4. The method according to any one of claims 1 to 3, characterized in that, The reporting parameters of the monitoring results include at least one of the following: reporting period, reporting trigger event, reporting threshold.

5. The method according to claim 4, characterized in that The reporting parameters of the monitoring results include the reporting threshold, and the reporting threshold includes thresholds corresponding to the respective monitoring metric parameters of the AI object; the terminal performing the first operation according to the first parameter includes at least one of the following: When the RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy, the terminal reports the monitoring results of the AI object; When the prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, the terminal reports the monitoring results of the AI object; When the prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, the terminal reports the monitoring results of the AI object; When the prediction accuracy of measurement events is less than or equal to the threshold corresponding to the measurement events, the terminal reports the monitoring results of the AI object; When the number or probability of abnormal events occurring within the first time period is greater than or equal to the threshold corresponding to the abnormal events, the terminal reports the monitoring results of the AI object; When 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, the terminal reports the monitoring results of the AI object; When the number of handovers per unit time or within the third time period is greater than or equal to the threshold corresponding to the number of handovers, the terminal reports the monitoring results of the AI object.

6. The method according to claim 4, characterized in that The reporting trigger event includes at least one of the following: The first event occurs continuously for K1 times, or the first event occurs K1 times within the fourth time period. The first event is that the RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy, and K1 is a positive integer; The second event occurs continuously for K2 times, or the second event occurs K2 times within the fifth time period. The second event is that the prediction of the optimal N cells is incorrect, or the prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, and K2 is a positive integer; The third event occurs continuously for K3 times, or the third event occurs K3 times within the sixth time period. The third event is that the prediction of the optimal M beams is incorrect, or the prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, and K3 is a positive integer; The fourth event occurs continuously for K4 times, or the fourth event occurs K4 times within the seventh time period. The fourth event is that the prediction of the measurement event is incorrect, or the prediction accuracy of the measurement event is less than or equal to the threshold corresponding to the measurement event, and K4 is a positive integer; The abnormal event occurs continuously for K5 times, or the abnormal event occurs K5 times within the eighth time period, and K5 is a positive integer; The fifth event occurs continuously for K6 times, or the fifth event occurs K6 times within the ninth time period. The fifth event is that the handover delay or interruption duration is greater than or equal to the threshold corresponding to the handover delay or interruption duration, and K6 is a positive integer; The handover occurs continuously for K7 times, or the handover occurs K7 times within the ninth time period, and K7 is a positive integer.

7. The method according to any one of claims 1 to 6, characterized in that, The reported parameter is associated with the 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.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: The terminal sends a second measurement report to the network side device; Wherein, the second measurement report includes the actual result within the prediction time or prediction time period corresponding to the first prediction result.

9. The method according to claim 8, wherein The method further includes: The terminal receives the second information sent by the network side device; Wherein, the second information is used to determine the association relationship between the reporting time of the first measurement report and the reporting time of the second measurement report.

10. The method according to claim 9, wherein The second information includes the configuration information of the first timer; the terminal sending the second measurement report to the network side device includes: The terminal starts the first timer when sending the first measurement report to the network side device; The terminal sends the second measurement report to the network side device when the first timer times out.

11. The method according to claim 10, wherein The first measurement report includes the first prediction results within T prediction times or T prediction time periods. The first timer includes T timers, and the T timers respectively correspond to the T prediction times or T prediction time periods, and the durations of the T timers are different, and T is an integer greater than 1; The terminal starts the first timer when sending the first measurement report to the network side device, including: When the terminal sends the first measurement report to the network - side device, it starts the T timers; When the first timer expires, the terminal sends a second measurement report to the network - side device, including: When each of the T timers expires, the terminal sends a second measurement report corresponding to each timer to the network - side device respectively, where the second measurement report corresponding to each timer respectively includes the actual result within the predicted moment or predicted time period corresponding to each timer.

12. The method according to any one of claims 8 to 11, characterized in that The first measurement report includes a first identifier, and the second measurement report includes the first identifier.

13. The method according to any one of claims 1 to 12, characterized in that: When a first condition is met, the terminal does not report the second measurement report or the actual result within the predicted moment or predicted time period corresponding to the first prediction result, and the second measurement report includes the actual result within the predicted moment or predicted time period corresponding to the first prediction result; Wherein, the first condition includes any one of the following: A handover, reconstruction or redirection occurs; The first prediction result is the same as the actual result within the predicted moment or predicted time period corresponding to the first prediction result, or the difference between the first prediction result and the actual result within the predicted moment or predicted time period corresponding to the first prediction result is less than or equal to a first threshold; The measurement object associated with the first measurement report is deleted; An RLF, HOF or radio resource control (RRC) state transition occurs.

14. The method according to any one of claims 1 to 13, characterized in that, The method further includes: When a handover, reconstruction or redirection occurs, the terminal performs a second operation; Wherein, the second operation includes any one of the following: When the AI object associated with the first measurement report is in an active state, report a second measurement report to the target cell; When the AI object associated with the first measurement report is in an inactive state or has been released, do not report a second measurement report to the target cell; Wherein, the second measurement report includes the actual result within the predicted moment or predicted time period corresponding to the first prediction result.

15. The method according to any one of claims 1 to 14, characterized in that, The event prediction result includes at least one of the prediction result of a measurement event, the prediction result of an RLF, and the prediction result of an HOF.

16. The method according to claim 15, wherein When the first prediction result includes the prediction result of an HOF, the method further includes: The terminal starts a second timer after sending the first measurement report to the network - side device; When the second timer expires, the terminal reports the actual result of the first predicted cell during the running of the second timer; Or, When an HOF or an RRC state transition occurs during the running of the second timer, the terminal does not report the actual result of the first predicted cell during the running of the second timer.

17. The method according to claim 15, wherein When the first prediction result includes the prediction result of an RLF, the method further includes: The terminal starts a third timer after sending the first measurement report to the network - side device; When the third timer expires, the terminal reports the actual result of the second predicted cell during the operation of the third timer; Or, When RLF or RRC state transition occurs during the operation of the third timer, the terminal does not report the actual result of the second predicted cell during the operation of the third timer.

18. An AI object monitoring method, characterized in that, Including: The network-side device sends a first parameter to the terminal, or the network-side device receives a first measurement report sent by the terminal; Wherein, the first parameter includes at least one of the following: the monitoring metric parameter of the AI object, the reporting parameter of the monitoring result of the AI object; The first measurement report is used for the network-side device to monitor the AI object, and the first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result; The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

19. The method according to claim 18, wherein The monitoring metric parameter of the AI object includes 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.

20. The method according to claim 19, characterized in that 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.

21. The method according to any one of claims 18 to 20, characterized in that, The reporting parameter of the monitoring result includes at least one of the following: reporting period, reporting trigger event, reporting threshold.

22. The method according to claim 21, wherein The reporting threshold includes the thresholds corresponding to the respective monitoring metric parameters of the AI object.

23. The method according to claim 21, wherein, The reporting trigger event includes at least one of the following: The first event occurs continuously K1 times, or the first event occurs K1 times within a fourth time period, where the first event is that the RRM measurement prediction accuracy is less than or equal to the threshold corresponding to the RRM measurement prediction accuracy, and K1 is a positive integer; The second event occurs continuously K2 times, or the second event occurs K2 times within a fifth time period, where the second event is that the prediction of the optimal N cells is incorrect, or the prediction accuracy of the optimal N cells is less than or equal to the threshold corresponding to the optimal N cells, and K2 is a positive integer; The third event occurs continuously K3 times, or the third event occurs K3 times within a sixth time period, where the third event is that the prediction of the optimal M beams is incorrect, or the prediction accuracy of the optimal M beams is less than or equal to the threshold corresponding to the optimal M beams, and K3 is a positive integer; The fourth event occurs continuously K4 times, or the fourth event occurs K4 times within a seventh time period, where the fourth event is that the prediction of the measurement event is incorrect, or the prediction accuracy of the measurement event is less than or equal to the threshold corresponding to the measurement event, and K4 is a positive integer; An abnormal event occurs continuously K5 times, or K5 abnormal events occur within the eighth time period, where K5 is a positive integer; The fifth event occurs continuously K6 times, or K6 fifth events occur within the ninth time period, where the fifth event is that the handover delay or interruption duration is greater than or equal to the threshold corresponding to the handover delay or interruption duration, and K6 is a positive integer; A handover occurs continuously K7 times, or K7 handovers occur within the ninth time period, where K7 is a positive integer.

24. The method according to any one of claims 18 to 23, characterized in that, The reported parameter is associated with a first object, where the first object includes one of the following: a terminal, a cell, a frequency point, an AI object, a measurement configuration, a measurement identifier, a measurement object, a reporting configuration.

25. The method according to any one of claims 18 to 24, characterized in that, The method further includes: The network-side device receives a second measurement report sent by the terminal; Wherein, the second measurement report includes the actual result within the prediction moment or prediction time period corresponding to the first prediction result.

26. The method according to claim 25, wherein The method further includes: The network-side device sends second information to the terminal; Wherein, the second information is used to determine the association relationship between the reporting time of the first measurement report and the reporting time of the second measurement report.

27. The method according to claim 26, wherein The second information includes configuration information of a first timer, and the first timer is used to control the reporting time of the second measurement report.

28. The method according to claim 27, wherein The first measurement report includes first prediction results within T prediction moments or T prediction time periods, the first timer includes T timers, the T timers respectively correspond to the T prediction moments or T prediction time periods, and the durations of the T timers are different, where T is an integer greater than 1.

29. The method according to any one of claims 25 to 28, characterized in that, The first measurement report includes a first identifier, and the second measurement report includes the first identifier.

30. The method according to any one of claims 18 to 29, characterized in that, The event prediction result includes at least one of the prediction result of a measurement event, the prediction result of RLF, and the prediction result of HOF.

31. An AI object monitoring device, characterized in that, Includes: A first execution module, configured to perform a first operation according to a first parameter, or send a first measurement report to a network-side device; Wherein, the first operation includes at least one of AI object monitoring and reporting of the monitoring result of the AI object, and the first parameter includes at least one of the following: the monitoring metric parameter of the AI object, the reported parameter of the monitoring result of the AI object; The first measurement report is used to monitor the AI object, the first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result; The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

32. An AI object monitoring device, characterized in that, Includes: A transmission module, configured to send a first parameter to a terminal, or receive a first measurement report sent by the terminal; Wherein, the first parameter includes at least one of the following: the monitoring metric parameter of the AI object, the reported parameter of the monitoring result of the AI object; The first measurement report is used by a network-side device to monitor the AI object. The first measurement report includes a first prediction result based on the AI object, and the first prediction result includes at least one of a radio resource management (RRM) measurement prediction result and an event prediction result. The AI object includes an AI model or an AI function, and the AI object is an AI object for mobility management.

33. A terminal, characterized in that, It 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 AI object monitoring method according to any one of claims 1 to 17 are implemented.

34. A network-side device, characterized in that, It 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 AI object monitoring method according to any one of claims 18 to 30 are implemented.

35. A readable storage medium, characterized in that, The program or instructions are stored on the readable storage medium. When the program or instructions are executed by a processor, the steps of the AI object monitoring method according to any one of claims 1 to 17 are implemented, or the steps of the AI object monitoring method according to any one of claims 18 to 30 are implemented.

36. 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 monitoring method according to any one of claims 1 to 17, or to implement the steps of the AI object monitoring method according to any one of claims 18 to 30.

Images