Event prediction method and apparatus, terminal, and network side device

Abstract

The present application relates to the technical field of wireless communications, and discloses an event prediction method and apparatus, a terminal, and a network side device. The event prediction method in the embodiments of the present application comprises: a terminal acquires a first parameter; the terminal acquires a predicted measurement result; and on the basis of the first parameter and the predicted measurement result, the terminal determines whether a trigger condition for a target event is satisfied.

Description

Event prediction methods, devices, terminals and network-side equipment

[0001] Cross-reference of related applications

[0002] This application claims priority to Chinese Patent Application No. 202510058114.X, filed on January 14, 2025, entitled “Event Prediction Method, Apparatus, Terminal and Network Side Device”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of wireless communication technology, specifically relating to an event prediction method, apparatus, terminal, and network-side equipment. Background Technology

[0004] In related technologies, in indirect measurement event prediction, the prediction results of Radio Resource Management (RRM) measurements from the serving cell and neighboring cells are compared to determine whether the event entry conditions will continue to be met within the time-to-trigger period, thus predicting whether the event will occur. However, in practical applications, the prediction results of the two cells performing event prediction may be obtained based on different AI models, or the RRM measurement results of the two cells performing event prediction may be obtained by measurement and prediction, respectively. In such cases, prediction errors introduced by the AI ​​model may lead to inaccurate event predictions, and incorrect reporting of measurement events may result in problems such as handover failures. Summary of the Invention

[0005] This application provides an event prediction method, apparatus, terminal, and network-side device that can solve the problem of inaccurate event prediction.

[0006] In a first aspect, an event prediction method is provided, comprising: a terminal acquiring a first parameter; the terminal acquiring a prediction measurement result; and the terminal determining whether the triggering conditions of a target event are met based on the first parameter and the prediction measurement result.

[0007] Secondly, an event prediction method is provided, comprising: a network-side device sending configuration information to a terminal, wherein the configuration information includes a first parameter, and the configuration information is used to instruct the terminal to determine whether the triggering conditions of a target event are met based on the prediction measurement results and the first parameter.

[0008] Thirdly, an event prediction device is provided, comprising: a processing module, configured to: acquire a first parameter; acquire a prediction measurement result; and determine whether the triggering conditions of a target event are met based on the first parameter and the prediction measurement result.

[0009] Fourthly, an event prediction device is provided, comprising: a sending module for sending configuration information to a terminal, wherein the configuration information includes a first parameter, and the configuration information is used to instruct the terminal to determine whether the triggering conditions of a target event are met based on the prediction measurement result and the first parameter.

[0010] Fifthly, an event prediction apparatus is provided, the apparatus being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0011] In a sixth aspect, a terminal is provided, the terminal including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.

[0012] In a seventh aspect, a terminal is provided, including a processor and a communication interface, wherein the processor is used to perform the steps of the method described in the first aspect, and the communication interface is used to couple with the processor.

[0013] Eighthly, a network-side device is provided, the network-side device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the second aspect.

[0014] In a ninth aspect, a network-side device is provided, including a processor and a communication interface, wherein the processor is configured to perform the steps of the method described in the second aspect, and the communication interface is configured to be coupled to the processor.

[0015] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the second aspect.

[0016] Eleventhly, a wireless communication system is provided, comprising: a terminal and a network-side device, wherein the terminal can be used to perform the steps of the method as described in the first aspect, and the network-side device can be used to perform the steps of the method as described in the second aspect.

[0017] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run a program or instructions to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0018] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method as described in the first aspect, or to implement the steps of the method as described in the second aspect.

[0019] In this embodiment, the terminal obtains a first parameter and a predicted measurement result. The terminal determines whether the triggering conditions of the target event are met based on the first parameter and the predicted measurement result. Thus, the prediction error brought by the AI ​​model when obtaining the predicted measurement result can be calibrated through the first parameter, thereby improving the accuracy of the target event prediction and avoiding the problem of misjudgment of the measurement event trigger due to the prediction result error of RRM measurement. Attached Figure Description

[0020] Figure 1 shows a block diagram of a wireless communication system that can be applied to an embodiment of this application;

[0021] Figure 2 shows a schematic diagram of a neural network;

[0022] Figure 3 shows a flowchart of an event prediction method provided in an embodiment of this application;

[0023] Figure 4 shows another flowchart of an event prediction method provided in an embodiment of this application;

[0024] Figure 5 shows another flowchart of an event prediction method provided in an embodiment of this application;

[0025] Figure 6 shows another flowchart of an event prediction method provided in an embodiment of this application;

[0026] Figure 7 shows another flowchart of an event prediction method provided in an embodiment of this application;

[0027] Figure 8 shows another schematic flowchart of an event prediction method provided in an embodiment of this application;

[0028] Figure 9 shows another flowchart of an event prediction method provided in an embodiment of this application;

[0029] Figure 10 shows a flowchart of another event prediction method provided in an embodiment of this application;

[0030] Figure 11 shows a schematic diagram of an event prediction device provided in an embodiment of this application;

[0031] Figure 12 shows a schematic diagram of another event prediction device provided in an embodiment of this application;

[0032] Figure 13 shows a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0033] Figure 14 shows a schematic diagram of the hardware structure of a terminal provided in an embodiment of this application;

[0034] Figure 15 shows a schematic diagram of the hardware structure of a network-side device provided in an embodiment of this application. Detailed Implementation

[0035] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0036] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0037] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as the sender explicitly informing the receiver of specific information, the required operation, or the requested result in the instruction sent. An indirect instruction can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the required operation or requested result based on the judgment result.

[0038] It is worth noting that the technologies described in this application are 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 this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0039] Figure 1 shows a block diagram of a wireless communication system applicable to an embodiment of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can also be referred to as User Equipment (UE), and can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM, or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (APs), or Wireless Fidelity (WiFi) nodes, etc.Among them, base stations can be referred to as Node B (NB), Evolved Node B (eNB), 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, Transmit / Receive Point (TRP), Non-Terrestrial Network (NTN) equipment (such as satellite or high altitude platform stations). The term "base station" can be any suitable term in the field, such as "station" or any other appropriate term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to any specific technical term. It should be noted that the embodiments of this application only use the base station in the NR system as an example for introduction, and do not limit the specific type of base station.

[0040] Artificial intelligence (AI) has been widely applied in various fields. Integrating AI 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. AI modules can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application uses neural networks as an example for illustration, but it does not limit the specific type of AI module.

[0041] Figure 2 is a schematic diagram of a neural network, which is composed of neurons. The schematic diagram of a neuron is shown below. Where a1, a2, ... a K The input is w, where w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include Sigmoid, tanh, and ReLU (Rectified Linear Unit).

[0042] The parameters of a neural network are optimized using gradient optimization algorithms. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (sometimes called a loss function), which is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, a neural network model f(.) can be built. With the model, the predicted output f(x) can be obtained from the input x, and the difference between the predicted value and the true value (f(x)-Y) can be calculated; this is the loss function. The purpose of building the model is to find suitable w and b to minimize the value of the above loss function. The smaller the loss value, the closer our model is to the reality.

[0043] One optimization algorithm for AI models is the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two processes: forward propagation of the signal and backward propagation of the error. During forward propagation, the input sample is introduced from the input layer, processed layer by layer by the hidden layers, and then propagated to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to the error back propagation stage. Error back propagation involves propagating the output error back to the input layer layer by layer through the hidden layers in a certain form, distributing the error to all units in each layer, thereby obtaining the error signal of each unit. This error signal serves as the basis for adjusting the weights of each unit. This process of adjusting the weights of each layer through forward and backward propagation is repeated continuously. This continuous adjustment of weights is 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 the predetermined number of learning iterations is reached.

[0044] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (named after the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square prop (RMSprop), and adaptive momentum estimation (Adam).

[0045] During error backpropagation, these optimization algorithms calculate the gradient based on the error / loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients / derivatives / partial derivatives, etc., and then pass the gradient to the previous layer.

[0046] The AI ​​model (also referred to as AI unit, AI structure, AI function, AI characteristic, machine learning (ML) model, machine learning unit, neural network, neural network function, neural network capability, etc.) in the embodiments of this application can refer to a processing unit capable of implementing specific algorithms, formulas, processing flows, capabilities, etc. related to AI; or an AI unit can be a processing method, algorithm, function, module, or unit for a specific dataset; or an AI unit can be a processing method, algorithm, function, module, or unit running on AI / machine learning (ML) related hardware such as a graphics processing unit (GPU), neural processing unit (NPU), tensor processing unit (TPU), or application-specific integrated circuit (ASIC), etc., and this application does not specifically limit this. Optionally, the aforementioned specific dataset includes the input or output of the AI ​​unit.

[0047] Optionally, the identifier of the AI ​​unit or AI model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific dataset associated with the AI ​​unit / AI model, or an identifier of a specific scenario, environment, region, cell, channel characteristics, or device related to the AI / ML, or an identifier of a function, characteristic, capability, or module related to the AI / ML. This application embodiment does not specifically limit this.

[0048] In the embodiments of this application, an AI function can be an AI algorithm function, and the AI ​​function may include multiple AI models.

[0049] AI-based mobility enhancements can include RRM measurement prediction, measurement event prediction, and radio link failure (RLF) / handover failure (HOF) prediction.

[0050] RRM measurement prediction includes cell-level measurement prediction and beam-level measurement prediction. Cell-level measurement prediction refers to the prediction of cell-level measurement results, either directly or indirectly. Specifically, RRM measurement prediction includes time / frequency / spatial domain RRM measurement prediction. In the time domain, historical RRM measurement results are used to predict future RRM measurement results; in the frequency domain, RRM measurement results at one frequency are used to predict the RRM measurement results at another frequency; and in the spatial domain, RRM measurement results at some beams within the same cell are used to predict the RRM measurement results at other beams.

[0051] Measurement event prediction includes direct and indirect measurement event prediction. Direct measurement event prediction means that the AI ​​model outputs whether a measurement event is met or the probability of it being met. Indirect measurement event prediction means that the AI ​​model outputs the RRM (Real-Modified Response) prediction results, and the event prediction results are obtained through post-processing based on the RRM prediction results. For example, after obtaining the RRM prediction results of the serving cell and neighboring cells, the system determines whether the predicted measurement results meet the triggering conditions of the measurement event to predict whether the measurement event will be met in the future.

[0052] In related technologies, a measurement configuration mainly consists of a measurement object, a reporting configuration, and a measurement identifier (ID). The measurement object is the frequency point to be measured. The reporting configuration includes reporting criteria (periodic / event-triggered); reference signal type (SSB / CSI-RS); measurement reporting quantity (any combination of RSRP / RSRQ / SINR); whether to report beam measurement results; and the maximum number of beams that can be reported. The measurement identifier (measId) is used to associate a measurement object with a reporting configuration. One measurement object can be associated with multiple reporting configurations, and one reporting configuration can be associated with multiple measurement objects.

[0053] In NR, the three can be linked together in the following way:

[0054] The reporting configuration can include event-triggered reporting. The measurement events defined in NR are shown in Table 1.

[0055] Table 1.

[0056] Taking event A3 as an example, the meanings of the parameters in the entry and exit conditions are as follows:

[0057] Mn: Neighbor cell measurement results, without considering any offset;

[0058] Ofn: Specific offset of the neighboring cell measurement object;

[0059] Ocn: Neighboring cell-level specific offset;

[0060] Mp: SpCell (primary serving cell) measurement result, without considering any offset;

[0061] Ofp: SpCell measures a specific offset of an object;

[0062] Ocp: SpCell cell-level specific offset;

[0063] Hys: The hysteresis parameter of the event;

[0064] Off: The offset parameter for the event.

[0065] If the reporting type is event-triggered, in order to avoid frequent reporting or ping-pong handover, the base station configures a trigger time (timeToTrigger) parameter for each event. If the L3 filtered signal quality of one or more candidate cells meets the event entry conditions within the time of timeToTrigger, the measurement reporting is triggered.

[0066] In indirect measurement event prediction using related technologies, the RRM prediction measurement results of the serving cell and neighboring cells are compared to determine whether the event triggering conditions will continue to be met within the timeToTrigger period, thus predicting whether the event will occur. However, in practice, the prediction results of the two cells performing event prediction may be obtained based on different AI models, or the RRM measurement results of the two cells performing event prediction may be obtained by measurement and prediction, respectively. In such cases, prediction errors introduced by the AI ​​model may lead to inaccurate event predictions, and incorrect reporting of measurement events may result in handover failures and other problems.

[0067] To address the aforementioned issues, this application provides an event prediction scheme to resolve the problem of misjudgment of measurement event triggering caused by errors in RRM prediction measurement results in indirect measurement event prediction.

[0068] The event prediction scheme provided in this application will be described in detail below with reference to the accompanying drawings, through some embodiments and application scenarios.

[0069] Figure 3 shows a flowchart of an event prediction method provided in an embodiment of this application. This method 300 can be executed by a terminal. In other words, the method can be executed by software or hardware installed on the terminal. As shown in Figure 3, the method may include the following steps.

[0070] S310, the terminal obtains the first parameter.

[0071] In this embodiment of the application, before predicting the target event, in order to avoid prediction errors caused by the AI ​​model, the terminal obtains a first parameter specifically for predicting the target event. The first parameter is used to correct the triggering conditions of the target event.

[0072] The first parameter may include one parameter or multiple parameters. For example, the first parameter may include at least one of the following: a first offset value or a first factor. That is, the first parameter may be an offset value or a factor, or the first parameter may include an offset value and a factor. The specific implementation of this application is not limited.

[0073] In some embodiments, the terminal can obtain the first parameter based on configuration information configured for the terminal by the network-side device. For example, the network-side device can directly configure the value of the first parameter through the configuration information. Alternatively, the network-side device can configure the value range of the first parameter through the configuration information, and the terminal determines the value of the first parameter based on the value range configured by the network-side device. Yet another example is that the network-side device can configure multiple sets of parameters through the configuration information, and the terminal selects one set of parameters as the first parameter.

[0074] S320, the terminal obtains the predicted measurement results.

[0075] In this application embodiment, the predicted measurement results include various RRM measurement prediction results that can serve the cell and neighboring cells.

[0076] Optionally, the terminal can obtain the predicted measurement results through an AI model. For example, the terminal inputs the current actual measurement results into the AI ​​model, and obtains the predicted measurement results output by the AI ​​model.

[0077] In this embodiment of the application, the predicted measurement result may optionally include at least one of the following:

[0078] 1) Predictive measurement results of the serving cell; for example, an AI model predicts the measurement results of the serving cell over a future period based on the current actual measurement results of the serving cell.

[0079] 2) Predicted measurement results of neighboring cells. For example, the AI ​​model predicts the measurement results of neighboring cells over a future period based on the current actual measurement results of neighboring cells.

[0080] In this embodiment of the application, the target event may include one of the following:

[0081] 1) Determine whether the triggering conditions are continuously met within the trigger time (timeToTrigger) based on the measurement prediction results of the serving cell or the measurement prediction results of neighboring cells; where the trigger time can be the current time period or a future time period.

[0082] 2) An event that determines whether the triggering conditions are continuously met within the trigger time (timeToTrigger) based on the measurement results of the serving cell or the measurement results of the neighboring cells, as well as the prediction results of the serving cell or the prediction results of the neighboring cells.

[0083] In other words, in this embodiment, the prediction of the target event refers to an event judged based at least on the predicted measurement results of the AI ​​model, i.e., an event predicted based at least on the predicted measurement results. For example, within the timeToTrigger period, the first period is used to determine whether the triggering conditions of the target event are met based on the actual measurement results, and the second period is used to determine whether the triggering conditions of the target event are met based on the predicted measurement results. When the triggering conditions of the target event are met, measurement reporting or cell handover may be triggered. For example, Conditional Handover (CHO) and Layer 1 / L2 triggered mobility (LTM).

[0084] S330, the terminal determines whether the triggering conditions of the target event are met based on the first parameter and the above-mentioned prediction measurement results.

[0085] In this embodiment of the application, in addition to predicting the target event based on the prediction parameters of the target event itself, the terminal also needs to predict the target event based on the first parameter.

[0086] In some implementations, determining whether the triggering condition of the target event is met may include one of the following:

[0087] 1) Based on the prediction results of the serving cell or the prediction results of neighboring cells, determine whether the triggering conditions of the target event are continuously met within the triggering time.

[0088] 2) Based on the measurement results of the serving cell or neighboring cells and the prediction results of the serving cell or neighboring cells, determine whether the triggering conditions of the target event are continuously met within the triggering time.

[0089] In some embodiments, the first parameter includes a target offset value or a target factor; the above S330 may include:

[0090] The terminal uses the predicted measurement result and the first parameter in the discriminant corresponding to the triggering condition of the target event to determine whether the triggering condition of the target event is met.

[0091] For example, taking the A3 event entry condition as an example, the actual measurement results are used to determine whether the trigger condition of the A3 time is met as Mn+Ofn+Ocn–Hys>Mp+Ofp+Ocp+Off.

[0092] When using predictive measurement results to determine whether the triggering conditions for an A3 event are met, a first parameter can be introduced. For example, the first parameter may include a target offset value. The triggering condition after introducing the target offset is one of the following:

[0093] Mn+Ofn+Ocn-Hys+(-) target offset>Mp+Ofp+Ocp+Off;

[0094] Mn+Ofn+Ocn-Hys>Mp+Ofp+Ocp+Off+(-) target offset.

[0095] Alternatively, for example, if the first parameter includes a target factor, the discriminant for the triggering condition after introducing the target factor is one of the following:

[0096] Mn*target factor + Ofn + Ocn-Hys > Mp + Ofp + Ocp + Off;

[0097] Mn+Ofn+Ocn-Hys>Mp*target factor+Ofp+Ocp+Off.

[0098] The target offset can be positive or negative, and the target factor can be 0 to 1 or greater than 1.

[0099] In some implementations, the terminal can always predict the target event in the manner described above within the TimeToTrigger of the predicted target event.

[0100] In other implementations, the terminal may also predict the target event in the manner described above during a portion of the TimeToTrigger period of the target event prediction. For example, when the prediction of the target event consists of actual measurement results + predicted measurement results (e.g., the event prediction is performed using actual measurement results in the first time period and predicted measurement results in the second time period), the event discrimination formula without the first parameter is used in the first time period, and the event discrimination formula with the first parameter is used in the second time period.

[0101] For example, when the serving cell is the actual measurement result and the neighboring cell is the predicted measurement result, the triggering condition can be one of the following:

[0102] Mn+Ofn+Ocn-Hys+(-) target offset>Mp+Ofp+Ocp+Off;

[0103] Mn*target factor + Ofn + Ocn-Hys > Mp + Ofp + Ocp + Off.

[0104] When the serving cell is a prediction result and the neighboring cell is a measurement result, the method for determining the triggering condition is one of the following:

[0105] Mn+Ofn+Ocn–Hys>Mp+Ofp+Ocp+Off+(-)target offset;

[0106] Mn+Ofn+Ocn-Hys>Mp*target factor+Ofp+Ocp+Off.

[0107] In this embodiment, the first parameter is the offset applied to the predicted measurement result or the predicted event. The first parameter is applied when the predicted measurement result from RRM measurement is involved in event prediction. That is, if the cell involved in event prediction is a predicted measurement result, the first parameter is applied; otherwise, it is not applied. The first parameter is applied for predicting predicted events, but not for traditional measurement-based event prediction.

[0108] In the embodiments of this application, the value of the first parameter can be set based on the prediction measurement results of the AI ​​model. For example, when the overall prediction measurement results of the AI ​​model are larger than the actual measurement results, a negative target offset or a target factor less than 1 is added to adjust the prediction results of the target event. When the overall prediction results of the AI ​​model are smaller than the actual results, a positive offset or a factor greater than 1 is added to adjust the prediction results of the target event.

[0109] In this embodiment of the application, the value of the first parameter can also be set with the goal of making the target event more difficult to trigger. For example, a positive offset can be added on the serving cell side (i.e., the right side of the above formula) or a negative offset can be added on the neighboring cell side (i.e., the left side of the above formula) to make the target event more difficult to satisfy.

[0110] Due to inherent errors in the AI ​​model, inaccurate event predictions may occur, and erroneous measurement reports could lead to abnormal switching. In the technical solution provided in this application, when predicting a target event, a first parameter related to the AI ​​model can be considered to compensate for errors introduced by the AI ​​model. Alternatively, the first parameter can be configured to make the predicted target event less likely to be triggered, thereby reducing abnormal switching caused by inaccurate predictions.

[0111] Figure 4 shows another schematic flowchart of an event prediction method provided in an embodiment of this application. This method 400 can be executed by a terminal. In other words, the method can be executed by software or hardware installed on the terminal. As shown in Figure 4, the method may include the following steps.

[0112] S410, the terminal obtains the configuration information configured for the terminal by the network-side device, which includes the first parameter.

[0113] In this embodiment of the application, the network-side device configures a target offset value or target factor for the terminal to determine whether the triggering conditions of the target event are met. For example, the network-side device can configure the above configuration information for the terminal through Radio Resource Control (RRC) commands.

[0114] The target parameters are the same as those in method 300.

[0115] In some implementations, the network-side device can directly configure the value of the first parameter in the configuration information, and the terminal can obtain the first parameter based on the configuration of the network-side device.

[0116] In some implementations, the first parameter configured on the network-side device may be associated with at least one of the following:

[0117] 1) Measurement configuration, wherein the target event is a predicted event configured in the measurement configuration, that is, when the terminal makes a prediction for any event configured in the measurement configuration, it considers the first parameter mentioned above;

[0118] 2) Measurement object, wherein the target event is a predicted event associated with a frequency point in the measurement object, that is, when the terminal predicts the event associated with the frequency point in the measurement object, it considers the first parameter mentioned above;

[0119] 3) Reporting configuration, wherein the target event is a predicted event predicted using the reporting configuration, that is, when the terminal uses the reporting configuration to predict the event, it considers the first parameter mentioned above;

[0120] 4) AI function, wherein the target event is a predicted event for predicting a cell using the AI ​​function. That is, when the terminal predicts events related to a cell using the AI ​​function, it considers the first parameter mentioned above. For example, when the serving cell uses the AI ​​function to obtain predicted measurement results, the terminal considers the first parameter mentioned above when predicting events using the predicted measurement results of the serving cell.

[0121] The AI ​​function can be an AI algorithm function, which may include one or more AI models.

[0122] 5) AI model, wherein the target event is a predicted event for a cell using the AI ​​model. That is, when the terminal predicts events related to a cell using the AI ​​model, it considers the first parameter mentioned above. For example, when a neighboring cell uses the AI ​​function to obtain prediction results, the terminal considers the first parameter mentioned above when predicting events using the prediction results of the neighboring cell.

[0123] S420, the terminal obtains the predicted measurement results.

[0124] This step is the same as S320 above. For details, please refer to the relevant description in S320 above. It will not be repeated here.

[0125] S430, the terminal determines whether the triggering conditions of the target event are met based on the first parameter and the predicted measurement result.

[0126] This step is the same as S330 above. For details, please refer to the relevant description in S330 above. It will not be repeated here.

[0127] In this embodiment of the application, in addition to predicting the target event based on the prediction parameters of the target event itself, the terminal also predicts the target event based on the first parameter.

[0128] Through the technical solutions provided in the embodiments of this application, the network-side device can configure a first parameter for the terminal based on the error of the AI ​​model. By configuring the first parameter, the error brought by the AI ​​model can be compensated, or the difficulty of predicting event triggering can be increased by configuring the first parameter, so as to reduce abnormal switching caused by inaccurate prediction.

[0129] Figure 5 illustrates another flowchart of an event prediction method provided in an embodiment of this application, which can be executed by a terminal. In other words, the method can be executed by software or hardware installed on the terminal. As shown in Figure 5, the method may include the following steps.

[0130] S510, the terminal obtains the configuration information configured for the terminal by the network-side device, which includes the first parameter and the model accuracy threshold.

[0131] In this embodiment, in addition to configuring the first parameter for the terminal, the network-side device can also configure a model accuracy threshold, instructing the terminal to use the first parameter when the model accuracy of the AI ​​model is lower than the model accuracy threshold.

[0132] S520, the terminal obtains the predicted measurement results.

[0133] This step is the same as S320 above. For details, please refer to the relevant description in S320 above. It will not be repeated here.

[0134] S530: The terminal acquires the prediction accuracy of the AI ​​model associated with the predicted measurement results.

[0135] The AI ​​model associated with the predicted measurement results can be an AI model used to output the predicted measurement results based on the actual measurement results. For example, when the target event is predicted based on the actual measurement results of the serving cell and the predicted measurement results of neighboring cells, the AI ​​model associated with the predicted measurement results is an AI model used to output the predicted measurement results of neighboring cells.

[0136] In this embodiment, the terminal can determine the prediction accuracy of the AI ​​model by comparing the predicted measurement results and the actual measurement results output by the AI ​​model within a certain time range. For example, when the AI ​​model outputs the predicted measurement results of neighboring cells, the terminal can obtain the prediction accuracy of the AI ​​model by comparing the difference between the predicted measurement results output by the AI ​​model and the actual measurement results of neighboring cells within a certain time range. For example, the prediction accuracy of the AI ​​model can be the root mean square error, mean absolute error, or mean absolute percentage error between the predicted measurement results and the actual measurement results within that time range.

[0137] S540, if the prediction accuracy is lower than the model accuracy threshold, the terminal determines whether the triggering condition of the target event is met based on the first parameter and the prediction measurement result.

[0138] The method by which the terminal predicts the target event based on the first parameter and the predicted measurement result is the same as in S330 above. For details, please refer to the relevant description of S330 above, and it will not be repeated here.

[0139] In this embodiment, the terminal can decide whether to apply or not to apply the first parameter configured by the network-side device based on the model accuracy threshold. When a model accuracy threshold is configured, the terminal can determine whether to apply the first parameter based on the model accuracy threshold. For example, if the prediction accuracy of the AI ​​model is higher than the model accuracy threshold, the first parameter is not applied to predict the target event; if the prediction accuracy of the AI ​​model is lower than the model accuracy threshold, the first parameter is applied to predict the target event.

[0140] Since the AI ​​model's prediction accuracy is below the model accuracy threshold, it indicates a large prediction error. If the target event is predicted based on the AI ​​model's measurement results, it may lead to misjudgment of the target event triggering. Therefore, in this embodiment, when the AI ​​model's prediction accuracy is below the model accuracy threshold set by the network-side device, the terminal determines whether the triggering conditions of the target event are met based on the first parameter and the prediction measurement results. This allows the first parameter to compensate for the prediction error caused by the AI ​​model, improving the accuracy of event prediction. Conversely, when the AI ​​model's accuracy is good, the first parameter is not used to predict the target event to ensure timely triggering of the target event.

[0141] In some implementations, if the prediction accuracy is lower than the model accuracy threshold, the terminal may also report to the network-side device, so that the network-side device can know that the terminal is currently predicting the target event based on the first parameter. Therefore, in these implementations, after the terminal obtains the prediction accuracy of the AI ​​model associated with the prediction measurement result, the method may further include: if the prediction accuracy is lower than the model accuracy threshold, the terminal sends third indication information to the network-side device, wherein the third indication information is used to instruct the terminal to use the first parameter to determine whether the triggering condition of the target event is met.

[0142] In the above embodiments, the third indication information can be the value of the first parameter, or the identifier of the first parameter. Alternatively, the third indication information can also be indicated indirectly. For example, if the value of the third indication information is 0, the terminal is instructed to use the first parameter to predict the target event. If the value of the third indication information is 1, the terminal is instructed to use the second parameter to measure the target event. The specific indication method is not limited in this application embodiment.

[0143] Figure 6 illustrates another flowchart of an event prediction method provided in an embodiment of this application, which can be executed by a terminal. In other words, the method can be executed by software or hardware installed on the terminal. As shown in Figure 6, the method may include the following steps.

[0144] S610, the terminal obtains the configuration information configured for the terminal by the network-side device. This configuration information includes multiple sets of first parameters and the monitoring threshold corresponding to each set of first parameters.

[0145] In this embodiment, the network-side device configures multiple sets of first parameters for the terminal and monitoring thresholds corresponding to each set of first parameters.

[0146] S620, the terminal obtains the predicted measurement results.

[0147] This step is the same as S320 above. For details, please refer to the relevant description in S320 above. It will not be repeated here.

[0148] S630: The terminal acquires the prediction error of the AI ​​model associated with the predicted measurement results.

[0149] The AI ​​model associated with the predicted measurement results can be an AI model used to output the measurement results. For example, when the prediction parameters of the target event include the predicted measurement results of the serving cell and the actual measurement results of neighboring cells, the AI ​​model associated with the predicted measurement results is an AI model used to output the predicted measurement results of the serving cell.

[0150] In this embodiment of the application, the terminal can determine the prediction error of the AI ​​model by comparing the predicted measurement results output by the AI ​​model with the actual measurement results within a certain time range. For example, when the AI ​​model outputs the predicted measurement results of the serving cell, the terminal can obtain the prediction error of the AI ​​model by comparing the predicted measurement results output by the AI ​​model with the actual measurement results of the serving cell within a certain time range.

[0151] S640, the terminal selects one set of first parameters from the multiple sets of first parameters whose monitoring threshold matches the prediction error.

[0152] In this embodiment, the terminal can select a first parameter that matches the monitoring threshold with the prediction error of the AI ​​model to predict the target event.

[0153] For example, the network-side device is configured with two sets of first parameters: parameter 1 and parameter 2. The monitoring threshold corresponding to parameter 1 is 5dB, and the monitoring threshold corresponding to parameter 2 is 10dB. If the prediction error of the AI ​​model associated with the prediction measurement result is 6dB, the terminal selects parameter 1 to predict the target event.

[0154] S650, the terminal determines whether the triggering conditions of the target event are met based on the selected first parameter and the predicted measurement result.

[0155] The method by which the terminal predicts the target event based on the first parameter is the same as in S330 above. For details, please refer to the relevant description of S330 above, which will not be repeated here.

[0156] In some implementations, the terminal may also report to the network-side device so that the network-side device can know the first parameter selected by the terminal. Therefore, in these implementations, after S630, the method may further include: the terminal sending fourth indication information to the network-side device, wherein the fourth indication information is used to indicate the selected set of the first parameters.

[0157] In the above embodiments, the fourth indication information can be the value of the selected first parameter or the identifier of the selected first parameter, such as the configuration index associated with the first parameter. Alternatively, the fourth indication information can also be indicated indirectly. For example, if the network-side device is configured with two sets of first parameters, if the value of the fourth indication information is 0, the terminal is instructed to use the first set of first parameters to predict the target event; if the value of the fourth indication information is 1, the terminal is instructed to use the second set of first parameters to predict the target event. The specific indication method is not limited in this embodiment.

[0158] Figure 7 illustrates another flowchart of an event prediction method provided in an embodiment of this application, which can be executed by a terminal. In other words, the method can be executed by software or hardware installed on the terminal. As shown in Figure 7, the method may include the following steps.

[0159] S710, the terminal obtains configuration information configured for the terminal by the network-side device. The configuration information includes a first parameter and a second parameter. The second parameter is used to determine whether the triggering conditions of the target event are met based on the actual measurement results.

[0160] In this embodiment of the application, the network-side device can configure two sets of parameters for the target event, namely the first parameter and the second parameter. The second parameter is the event parameter used to determine whether the triggering conditions of the target event are met by using the actual measurement results (e.g., a3-Offset in the A3 event). The first parameter is the parameter used to predict the event or the event when the prediction measurement results are involved in the prediction.

[0161] S720, the terminal obtains the predicted measurement results.

[0162] This step is the same as S320 above. For details, please refer to the relevant description in S320 above. It will not be repeated here.

[0163] S730, when predicting the target event, the terminal determines whether the triggering conditions of the target event are met based on the first parameter and the prediction measurement result.

[0164] In the embodiments of this application, if the predicted measurement result of the cell is involved in the event prediction, the terminal applies the first parameter to predict the event; otherwise, it applies the second parameter. Alternatively, for the prediction of a predicted event, the first parameter is applied to predict the event, and for the traditional determination of the triggering conditions of a measurement-based event, the second parameter is applied to determine the event.

[0165] In some implementations, the configuration information may further include a model accuracy threshold. In S730, the terminal can obtain the prediction accuracy of the AI ​​model associated with the predicted target event. If the obtained prediction accuracy is lower than the model accuracy threshold, based on the first parameter and the prediction measurement result, it determines whether the triggering condition of the target event is met, i.e., it predicts the target event. This allows the first parameter to compensate for the prediction error caused by the AI ​​model when the AI ​​model's prediction accuracy is poor, thereby improving the accuracy of event prediction. Conversely, if the AI ​​model's accuracy is good, the first parameter is not used to determine whether the triggering condition of the target event is met, ensuring that the target event can be triggered in a timely manner.

[0166] Through the technical solution provided in this application embodiment, the network-side device can incorporate the first parameter into the event evaluation parameter corresponding to whether the triggering condition of the target event is met based on the actual measurement result. The target event can be associated with two sets of event evaluation parameters. When determining whether the triggering condition of the target event is met based on the AI-based prediction measurement result, one set of parameters, namely the first parameter, is used. When determining whether the triggering condition of the target event is met based on the actual measurement result, the other set of parameters, namely the second parameter, is used. This allows the terminal to use its respective configuration parameters in different scenarios.

[0167] In some implementations, after S730, the terminal may also report to the network-side device so that the network-side device can know that the terminal is currently predicting the target event based on the first parameter. Therefore, in these implementations, the method may further include: the terminal sending indication information (e.g., the aforementioned third indication information) to the network-side device, wherein the indication information is used to instruct the terminal to use the first parameter to determine whether the triggering condition of the target event is met.

[0168] Figure 8 shows another schematic flowchart of an event prediction method provided in an embodiment of this application, which can be executed by a terminal. In other words, the method can be executed by software or hardware installed on the terminal. As shown in Figure 8, the method may include the following steps.

[0169] S810, the terminal obtains the first parameter indicated by the network-side device through network signaling.

[0170] In this embodiment of the application, the network-side device can dynamically indicate the first parameter through network signaling. For example, the network-side device can indicate the first parameter to the terminal through the Medium Access Control (MAC) control element (CE).

[0171] In some implementations, S810 may include the following steps:

[0172] Step 1: The terminal obtains the first indication information of the network signaling indication, wherein the first indication information is used to indicate the offset value of the first parameter relative to the configuration value of the first parameter, and the configuration value is the value configured by the network side device for the first parameter.

[0173] Step 2: The terminal determines the value of the first parameter based on the configuration value and the offset value.

[0174] In the above embodiments, network signaling can indicate the offset value of the first parameter relative to the configuration value of the first parameter, where the configuration value is the value configured by the network-side device for the first parameter. For example, before S810, the method of the terminal obtaining configuration information configured by the network-side device for the terminal, as described in the above embodiments, may also be included. For example, in S410 or S510, the terminal determines the value of the first parameter based on the configuration value and the offset value. For example, if the network-side device includes a target offset in the first parameter, network signaling can indicate the delta value between the target offset of the current application and the first offset configured by the network-side device.

[0175] In other embodiments, S810 may include the following steps:

[0176] Step 1: The terminal obtains the second indication information of the network signaling indication, wherein the second indication information is used to indicate one set of parameters among multiple sets of parameters configured by the network-side device for the target event;

[0177] For example, prior to S810, the method may also include the aforementioned S610 or S710, where the network-side device configures multiple sets of parameters for predicting target events for the terminal via RRC, and the network-side device dynamically instructs one of the multiple sets of parameters via network signaling.

[0178] Step 2: The terminal obtains the first parameter based on the second indication information.

[0179] Through the above implementation methods, the network-side device can configure multiple sets of parameters for target event evaluation, and then dynamically instruct the terminal to use one of the sets of parameters based on changes in the terminal's environment or configuration, thereby enabling the parameters used by the terminal to adapt to the current model.

[0180] In some implementations, prior to S810, the method may further include: the terminal sending reporting information to the network-side device, wherein the reporting information includes at least one of the following:

[0181] 1) RRM measurement results monitored by the first AI model of the network-side device;

[0182] 2) Predicted results of RRM measurements monitored by the first AI model of the network-side device;

[0183] 3) Prediction results of measurement events monitored by the first AI model of the network-side device;

[0184] 4) The monitoring results of the second AI model of the terminal;

[0185] 5) The value of the first parameter recommended by the terminal.

[0186] Through the above implementation methods, network-side devices can obtain real-time model monitoring results.

[0187] S820, the terminal obtains the predicted measurement results.

[0188] This step is the same as S320 above. For details, please refer to the relevant description in S320 above. It will not be repeated here.

[0189] S830, the terminal determines whether the triggering conditions of the target event are met based on the first parameter and the predicted measurement result.

[0190] This step is the same as S330 above, and will not be repeated here.

[0191] Since the error of the AI ​​model may change with the environment or configuration of the terminal, in this embodiment, the network-side device can dynamically adjust the first parameter based on the real-time model monitoring results, so that the first parameter is adapted to the accuracy of the current AI model and makes up for the prediction error of the AI ​​model.

[0192] Figure 9 illustrates another flowchart of an event prediction method provided in an embodiment of this application, which can be executed by a terminal. In other words, the method can be executed by software or hardware installed on the terminal. As shown in Figure 9, the method may include the following steps.

[0193] S910, the terminal obtains the value range of the first parameter configured by the network-side device.

[0194] In this embodiment of the application, the network-side device configures a range of values ​​for the first parameter for the terminal, and the terminal can select a value within this range based on the prediction accuracy of the AI ​​model.

[0195] The value range of the first parameter mentioned above may include the configuration information described in the various embodiments above.

[0196] S920, the terminal obtains the predicted measurement results.

[0197] This step is the same as S320 above. For details, please refer to the relevant description in S320 above. It will not be repeated here.

[0198] S930, the terminal acquires the monitoring results of the AI ​​model associated with the predicted measurement results.

[0199] The monitoring results of the AI ​​model can be either the prediction accuracy or the prediction error of the AI ​​model. For example, the terminal can obtain the prediction accuracy of the AI ​​model by comparing the predicted measurement results output by the AI ​​model with the actual measurement results within a certain time range. For instance, when the AI ​​model outputs the predicted measurement results of the serving cell, the terminal can obtain the prediction accuracy of the AI ​​model by comparing the predicted measurement results output by the AI ​​model with the actual measurement results of the serving cell within a certain time range.

[0200] S940, the terminal determines the value of the first parameter within the range of the monitored results.

[0201] In this embodiment, the terminal can determine the value of the first parameter based on the monitoring results of the AI ​​model. For example, when the AI ​​model's prediction result is larger than the actual result, when the first parameter is the target offset, the target offset can be a negative value within the range of values. The larger the difference between the predicted result and the actual result, the larger the absolute value of the target offset. When the AI ​​model's prediction result is smaller than the actual result, when the first parameter is the target offset, the target offset can be a positive value within the range of values. The larger the difference between the actual result and the predicted result, the larger the absolute value of the target offset.

[0202] S950, the terminal determines whether the triggering conditions of the target event are met based on the first parameter and the predicted measurement result.

[0203] This step is similar to S330; please refer to the relevant description in S330 for details, which will not be repeated here.

[0204] In some implementations, after the terminal determines that the first parameter falls within the range of values, the method may further include: the terminal sending fifth indication information to the network-side device, wherein the fifth indication information is used to indicate the determination of the value of the first parameter. This implementation allows the network-side device to know the value of the first parameter currently used by the terminal, thereby determining the monitoring result of the current AI model and facilitating adjustments to the value of the first parameter by the network-side device.

[0205] The technical solution provided in this application embodiment allows the terminal to adjust its configuration based on the value range of the first parameter configured by the network-side device, combined with the monitoring results of the AI ​​model, making the configuration simpler and more flexible.

[0206] Based on the same technical concept, this application also provides another event prediction method. This method is executed by the network-side device corresponding to the aforementioned terminal side.

[0207] It should be noted that the following embodiments only describe the operation of the network-side device. For other matters not covered, please refer to the relevant descriptions of methods 300 to 900 above.

[0208] Figure 10 shows a flowchart of another event prediction method provided in an embodiment of this application. This method 1000 can be executed by a network-side device. In other words, the method can be executed by software or hardware installed on the network-side device. As shown in Figure 10, the method mainly includes the following steps.

[0209] S1010, the network-side device sends configuration information to the terminal, wherein the configuration information includes a first parameter, and the configuration information is used to instruct the terminal to determine whether the triggering conditions of the target event are met based on the predicted measurement results and the first parameter.

[0210] Optionally, the above configuration information may include one or more sets of first parameters. Optionally, the above configuration information may include the value of the first parameter, or the range of values ​​for the first parameter.

[0211] Optionally, the above configuration information can be associated with at least one of the following:

[0212] 1) Measurement configuration, wherein the target event is a predicted event configured in the measurement configuration;

[0213] 2) Measurement object, wherein the target event is a predicted event associated with a frequency point in the measurement object;

[0214] 3) Reporting configuration, wherein the target event is a predicted event predicted using the reporting configuration;

[0215] 4) AI function, wherein the target event is a predicted event used to predict the cell using the AI ​​function;

[0216] 5) AI model, wherein the target event is a predicted event used to predict the cell using the AI ​​model.

[0217] In some implementations, the configuration information may further include a second parameter, which is used to instruct the terminal to determine whether the triggering conditions of the target event are met based on the second parameter and the actual measurement results.

[0218] In some implementations, after the network-side device sends configuration information to the terminal, the method may further include:

[0219] The network-side device receives a third indication message sent by the terminal, wherein the third indication message is used to instruct the terminal to use the first parameter in the process of determining whether the triggering conditions of the target event are met.

[0220] In some implementations, the configuration information includes multiple sets of the first parameters and a monitoring threshold corresponding to each set of the first parameters.

[0221] In some implementations, after the network-side device sends configuration information to the terminal, the method may further include:

[0222] The network-side device receives a fourth indication message sent by the terminal, wherein the fourth indication message is used to indicate a set of the first parameters used by the terminal in determining whether the triggering conditions of the target event are met.

[0223] In some implementations, after the network-side device sends configuration information to the terminal, the method may further include:

[0224] The network-side device sends network signaling to the terminal, wherein the network signaling is used to indicate the value of the first parameter.

[0225] In some implementations, the network signaling is used to indicate one of the following:

[0226] First indication information, wherein the first indication information is used to indicate the offset value of the first parameter relative to the configuration value of the first parameter, wherein the configuration value is the value configured by the network-side device for the first parameter;

[0227] The second indication information is used to indicate the first parameter among multiple sets of parameters configured by the network-side device for the target event.

[0228] In some embodiments, before the network-side device sends network signaling to the terminal, the method may further include: the network-side device receiving reporting information sent by the terminal, wherein the reporting information includes at least one of the following:

[0229] RRM measurement results monitored by the first AI model used in the network-side device;

[0230] Prediction results monitored by the first AI model used in the network-side device;

[0231] The results monitored by the second AI model of the terminal;

[0232] The value of the first parameter recommended by the terminal.

[0233] In the above embodiments, the network-side device can send the above-mentioned network signaling to the terminal based on the above-mentioned reported information, and dynamically indicate the first parameter to the terminal.

[0234] In some implementations, the configuration information includes a range of values ​​for the first parameter. In these implementations, the terminal can select a value for the first parameter within this range based on the monitoring results of the AI ​​model.

[0235] In some embodiments, after the network-side device sends configuration information to the terminal, the method may further include: the network-side device receiving fifth indication information sent by the terminal, wherein the fifth indication information is used to indicate the value of the first parameter determined by the terminal.

[0236] Through the method provided in the embodiments of this application, the network-side device can compensate for the prediction error of the AI ​​model by configuring the first parameter, and avoid the problem of misjudgment of measurement event triggering due to the error of RRM prediction measurement results.

[0237] The event prediction method provided in this application can be executed by an event prediction device. This application uses an event prediction device executing the event prediction method as an example to illustrate the event prediction device provided in this application.

[0238] This application provides an event prediction device. As an example, the event prediction device may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0239] The event prediction device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, etc., such as central processing units (CPUs), microprocessors, digital signal processors (DSPs), artificial intelligence (AI) processors, graphics processing units (GPUs), application-specific integrated circuits (ASICs), network processors (NPs), field-programmable gate arrays (FPGAs), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceivers, pins, circuits, buses, radio frequency units, etc.

[0240] Specifically, referring to Figure 11, when the event prediction device is a terminal or a component in a terminal, the event prediction device 1100 includes a processing module 1101, used to: acquire a first parameter; acquire a prediction measurement result; and determine whether the triggering conditions of the target event are met based on the first parameter and the prediction measurement result.

[0241] In some implementations, the processing module 1101 obtains the first parameter by: obtaining configuration information configured by the network-side device for the terminal, wherein the configuration information includes the first parameter.

[0242] In some implementations, the configuration information further includes a second parameter; the processing module 1101 is also used to determine whether the triggering conditions of the target event are met based on the second parameter and the actual measurement results.

[0243] In some embodiments, as shown in FIG11, the apparatus may further include: a receiving module 1102, configured to receive network signaling sent by a network-side device, wherein the network signaling is used to indicate the first parameter; the processing module 1101 obtains the first parameter by: obtaining the first parameter based on the indication of the network signaling.

[0244] In some implementations, the processing module 1101 obtains the first parameter based on the indication of the network signaling, including:

[0245] Obtain first indication information of the network signaling indication, wherein the first indication information is used to indicate the offset value of the first parameter relative to the configuration value of the first parameter, and the configuration value is the value configured by the network-side device for the first parameter;

[0246] The value of the first parameter is determined based on the configuration value and the offset value.

[0247] In some implementations, the processing module 1101 obtains the first parameter based on the indication of the network signaling, including:

[0248] Obtain second indication information of the network signaling indication, wherein the second indication information is used to indicate the first parameter among multiple sets of parameters configured by the network-side device for the target event;

[0249] Based on the second indication information, the first parameter is obtained.

[0250] In some embodiments, as shown in FIG11, the device further includes: a sending module 1103, configured to send reporting information to the network-side device, wherein the reporting information includes at least one of the following:

[0251] RRM measurement results monitored by the first AI model used in the network-side device;

[0252] Predictive results of RRM measurements monitored by the first AI model for the network-side device;

[0253] Predictive results of measurement events monitored by the first AI model used in the network-side device;

[0254] The results monitored by the terminal's second AI model;

[0255] The value of the first parameter recommended by the terminal.

[0256] In some implementations, the configuration information further includes: a model accuracy threshold; the processing module 1101 determines whether the triggering conditions of the target event are met based on the first parameter and the prediction measurement result, including:

[0257] Obtain the prediction accuracy of the AI ​​model associated with the predicted target event;

[0258] If the prediction accuracy is lower than the model accuracy threshold, it is determined whether the triggering condition of the target event is met based on the first parameter and the prediction measurement result.

[0259] In some embodiments, as shown in FIG11, the device further includes a sending module 1103, which is used to send third indication information to the network-side device when the prediction accuracy is lower than the model accuracy threshold, wherein the third indication information is used to instruct the terminal to use the first parameter to determine whether the triggering condition of the target event is met.

[0260] In some implementations, the configuration information includes multiple sets of the first parameters and a monitoring threshold corresponding to each set of the first parameters; the processing module 1101 obtains the first parameters by:

[0261] Obtain the prediction error of the AI ​​model associated with the predicted measurement results;

[0262] Select the set of first parameters from the multiple sets of first parameters that matches the monitoring threshold with the prediction error.

[0263] In some embodiments, as shown in FIG11, the device further includes a sending module 1103, configured to send fourth indication information to the network-side device, wherein the fourth indication information is used to indicate a selected set of the first parameters.

[0264] In some implementations, the processing module 1101 acquires the first parameter, including:

[0265] Obtain the value range of the first parameter configured on the network side device;

[0266] Obtain the monitoring results of the AI ​​model associated with the predicted measurement results;

[0267] Based on the monitoring results, the value of the first parameter within the specified range is determined.

[0268] In some embodiments, as shown in FIG11, the device further includes: a sending module 1103, configured to send fifth indication information to the network-side device, wherein the fifth indication information is used to indicate the value of the first parameter.

[0269] In some implementations, the first parameter configured by the network-side device is associated with at least one of the following:

[0270] Measurement configuration, wherein the target event is a predicted event configured in the measurement configuration;

[0271] The measurement object, wherein the target event is a predicted event associated with a frequency point in the measurement object;

[0272] The reporting configuration is used to predict the target event, which is a predicted event that is predicted using the reporting configuration.

[0273] Artificial intelligence (AI) function, wherein the target event is a predicted event used to predict the cell using the AI ​​function;

[0274] AI model, wherein the target event is a predicted event used to predict the cell using the AI ​​model.

[0275] In some implementations, the predicted measurement result includes at least one of the following:

[0276] Predictive measurement results for the service area;

[0277] Predicted measurement results for neighboring areas.

[0278] In some implementations, the processing module 1101 determines whether the triggering conditions of the target event are met based on the first parameter and the predicted measurement result, including one of the following:

[0279] Based on the predicted measurement results of the serving cell or the predicted results of neighboring cells, determine whether the triggering conditions of the target event are continuously met within the triggering time.

[0280] Based on the actual measurement results of the serving cell or neighboring cells, and the predicted measurement results of the serving cell or neighboring cells, it is determined whether the triggering conditions of the target event are continuously met within the triggering time.

[0281] In some implementations, the first parameter includes a target offset value or a target factor; the processing module 1101 determines whether the triggering condition of the target event is met based on the first parameter and the predicted measurement result, including: using the predicted measurement result and the first parameter in the discriminant corresponding to the triggering condition of the target event to determine whether the triggering condition of the target event is met.

[0282] Referring to Figure 12, when the event prediction device is a network-side device or a component of a network-side device, the event prediction device 1200 includes a sending module 1201 for sending configuration information to a terminal. The configuration information includes a first parameter, which is used to instruct the terminal to determine whether the triggering conditions of the target event are met based on the prediction measurement results and the first parameter.

[0283] In some implementations, the configuration information further includes a second parameter, which is used to instruct the terminal to determine whether the triggering conditions of the target event are met based on the second parameter and the actual measurement results.

[0284] In some embodiments, as shown in FIG12, the device further includes: a receiving module 1202, configured to receive third indication information sent by the terminal, wherein the third indication information is configured to instruct the terminal to use the first parameter in the process of determining whether the triggering conditions of the target event are met.

[0285] In some implementations, the configuration information includes multiple sets of the first parameters and a monitoring threshold corresponding to each set of the first parameters; as shown in FIG12, the device further includes: a receiving module 1202, used to receive a fourth indication information sent by the terminal, wherein the fourth indication information is used to indicate a set of the first parameters used by the terminal in the process of determining whether the triggering conditions of the target event are met.

[0286] In some implementations, the sending module 1201 is further configured to send network signaling to the terminal, wherein the network signaling is used to indicate the value of the first parameter.

[0287] In some embodiments, as shown in FIG12, the device further includes: a receiving module 1202, configured to receive reporting information sent by the terminal, wherein the reporting information includes at least one of the following:

[0288] RRM measurement results monitored by the first AI model used in the network-side device;

[0289] Prediction results monitored by the first AI model used in the network-side device;

[0290] The results monitored by the second AI model of the terminal;

[0291] The value of the first parameter recommended by the terminal.

[0292] In some embodiments, the configuration information includes the value range of the first parameter; as shown in FIG12, the device further includes: a receiving module 1202, used to receive fifth indication information sent by the terminal, wherein the fifth indication information is used to indicate the value of the first parameter determined by the terminal.

[0293] In some implementations, the configuration information is associated with at least one of the following:

[0294] Measurement configuration, wherein the target event is a predicted event configured in the measurement configuration;

[0295] The measurement object, wherein the target event is a predicted event associated with a frequency point in the measurement object;

[0296] The reporting configuration is used to predict the target event, which is a predicted event that is predicted using the reporting configuration.

[0297] AI function, wherein the target event is a predicted event used to predict the cell using the AI ​​function;

[0298] AI model, wherein the target event is a predicted event used to predict the cell using the AI ​​model.

[0299] The predictive event evaluation device provided in this application embodiment can implement the various processes implemented in the method embodiments of Figures 3 to 10 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0300] As shown in Figure 13, this application embodiment also provides a communication device 1300, including a processor 1301 and a memory 1302. The memory 1302 stores a program or instructions that can run on the processor 1301. For example, when the communication device 1300 is a terminal, when the program or instructions are executed by the processor 1301, they implement the various steps of the above-described predictive event evaluation methods 300 to 900, and achieve the same technical effect. When the communication device 1300 is a network-side device, when the program or instructions are executed by the processor 1301, they implement the various steps of the above-described predictive event evaluation method 1000, and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0301] This application also provides a terminal, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps in the method embodiments shown in Figures 3 to 9. This terminal embodiment corresponds to the above-described terminal-side method embodiments, and all implementation processes and methods of the above-described method embodiments can be applied to this terminal embodiment and achieve the same technical effect. The terminal may be the predictive event evaluation device shown in Figure 11. Specifically, Figure 14 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of this application.

[0302] The terminal 1400 includes, but is not limited to, at least some of the following components: radio frequency unit 1401, network module 1402, audio output unit 1403, input unit 1404, sensor 1405, display unit 1406, user input unit 1407, interface unit 1408, memory 1409, and processor 1410.

[0303] Those skilled in the art will understand that the terminal 1400 may also include a power supply (such as a battery) for powering various components. The power supply can be logically connected to the processor 1410 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The terminal structure shown in Figure 14 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.

[0304] It should be understood that, in this embodiment, the input unit 1404 may include a graphics processor 14041 and a microphone 14042. The graphics processor 14041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1406 may include a display panel 14061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1407 includes at least one of a touch panel 14071 and other input devices 14072. The touch panel 14071 is also called a touch screen. The touch panel 14071 may include a touch detection device and a touch controller. Other input devices 14072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0305] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 1401 can transmit it to the processor 1410 for processing; in addition, the radio frequency unit 1401 can send uplink data to the network-side device. Typically, the radio frequency unit 1401 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0306] The memory 1409 can be used to store software programs or instructions, as well as various data. The memory 1409 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1409 may include volatile memory or non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1409 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0307] Processor 1410 may include one or more processing units; optionally, processor 1410 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 1410.

[0308] The processor 1410 is used for:

[0309] Get the first parameter;

[0310] Obtain the predictive measurement results;

[0311] Based on the first parameter and the predicted measurement result, determine whether the triggering conditions of the target event are met.

[0312] In some implementations, the processor 1410 acquiring the first parameter includes: acquiring configuration information configured by the network-side device for the terminal, wherein the configuration information includes the first parameter.

[0313] In some embodiments, the radio frequency unit 1401 is used to receive network signaling sent by a network-side device, wherein the network signaling is used to indicate the first parameter; the processor 1410 obtains the first parameter by: obtaining the first parameter based on the indication of the network signaling.

[0314] In some implementations, the processor 1410 obtains the first parameter based on the instruction of the network signaling, including:

[0315] Obtain first indication information of the network signaling indication, wherein the first indication information is used to indicate the offset value of the first parameter relative to the configuration value of the first parameter, the configuration value being the value configured for the first parameter by the network-side device; determine the value of the first parameter based on the configuration value and the offset value.

[0316] In some implementations, the processor 1410 obtains the first parameter based on the instruction of the network signaling, including:

[0317] Obtain second indication information of the network signaling indication, wherein the second indication information is used to indicate the first parameter among multiple sets of parameters configured by the network-side device for the target event; obtain the first parameter based on the second indication information.

[0318] In some embodiments, the radio frequency unit 1401 is configured to send reporting information to the network-side device, wherein the reporting information includes at least one of the following:

[0319] RRM measurement results monitored by the first AI model used in the network-side device;

[0320] Predictive results of RRM measurements monitored by the first AI model for the network-side device;

[0321] Predictive results of measurement events monitored by the first AI model used in the network-side device;

[0322] The results monitored by the terminal's second AI model;

[0323] The value of the first parameter recommended by the terminal.

[0324] In some implementations, the configuration information further includes: a model accuracy threshold; the processor 1410 determines whether the triggering conditions of the target event are met based on the first parameter and the prediction measurement result, including:

[0325] Obtain the prediction accuracy of the AI ​​model associated with the predicted measurement results;

[0326] If the prediction accuracy is lower than the model accuracy threshold, determine whether the triggering conditions of the target event are met based on the first parameter and the prediction measurement result.

[0327] In some embodiments, the radio frequency unit 1401 is configured to send third indication information to the network-side device when the prediction accuracy is lower than the model accuracy threshold, wherein the third indication information is used to instruct the terminal to use the first parameter to determine whether the triggering condition of the target event is met.

[0328] In some implementations, the configuration information includes multiple sets of the first parameters and a monitoring threshold corresponding to each set of the first parameters; the processor 1410 acquires the first parameters by:

[0329] Obtain the prediction error of the AI ​​model associated with the predicted measurement results;

[0330] Select the set of first parameters from the multiple sets of first parameters that matches the monitoring threshold with the prediction error.

[0331] In some embodiments, the radio frequency unit 1401 is configured to send fourth indication information to the network-side device, wherein the fourth indication information is used to indicate a selected set of the first parameters.

[0332] In some implementations, the processor 1410 acquires the first parameter, including:

[0333] Obtain the value range of the first parameter configured on the network side device;

[0334] Obtain the monitoring results of the AI ​​model associated with the predicted measurement results;

[0335] Based on the monitoring results, the value of the first parameter within the specified range is determined.

[0336] In some embodiments, the radio frequency unit 1401 is used to send fifth indication information to the network-side device, wherein the fifth indication information is used to indicate the value of the first parameter.

[0337] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant descriptions of method embodiments 300 to 900 and achieve the same or corresponding technical effects. To avoid repetition, it will not be described again here.

[0338] This application also provides a network-side device, including a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method embodiment shown in FIG10. This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[0339] Specifically, this application embodiment also provides a network-side device, which may be the event prediction device shown in FIG12. As shown in FIG15, the network-side device 1500 includes: an antenna 1501, a radio frequency device 1502, a baseband device 1503, a processor 1504, and a memory 1505. The antenna 1501 is connected to the radio frequency device 1502. In the uplink direction, the radio frequency device 1502 receives information through the antenna 1501 and sends the received information to the baseband device 1503 for processing. In the downlink direction, the baseband device 1503 processes the information to be transmitted and sends it to the radio frequency device 1502, which processes the received information and then transmits it through the antenna 1501.

[0340] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 1503, which includes a baseband processor.

[0341] The baseband device 1503 may include at least one baseband board, on which multiple chips are disposed, as shown in FIG15. One of the chips is, for example, a baseband processor, which is connected to the memory 1505 via a bus interface to call the program or instructions in the memory 1505 to execute the network-side device operation shown in the above method embodiment.

[0342] The network-side device may also include a network interface 1506, such as a Common Public Radio Interface (CPRI).

[0343] The radio frequency device 1502 is used to send configuration information to the terminal. The configuration information includes a first parameter, which is used to instruct the terminal to determine whether the triggering conditions of the target event are met based on the predicted measurement results and the first parameter.

[0344] In addition, the network-side device 1500 of this application embodiment also includes: a program or instructions stored in the memory 1505 and executable on the processor 154. The processor 1504 calls the program or instructions in the memory 1505 to execute the methods executed by each module shown in FIG12 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0345] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described event prediction method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0346] The processor mentioned above is either the processor in the terminal described in the above embodiments or the processor in the network-side device. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[0347] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described event prediction method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0348] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0349] This application also provides a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the above-described event prediction method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0350] This application also provides a wireless communication system, including: a terminal and a network-side device, wherein the terminal can be used to execute the steps of the event prediction method 300 to 900 as described above, and the network-side device can be used to execute the steps of the event prediction method 1000 as described above.

[0351] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0352] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.), and the computer software product includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0353] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. A method for event prediction, comprising: obtaining, by a terminal, a first parameter; obtaining, by the terminal, a predicted measurement result; determining, by the terminal, whether a triggering condition of a target event is met according to the first parameter and the predicted measurement result.

2. The method of claim 1, wherein, The obtaining, by the terminal, of the first parameter comprises: obtaining, by the terminal, configuration information configured by a network-side device for the terminal, wherein the configuration information comprises the first parameter.

3. The method of claim 2, wherein, The configuration information further comprises a second parameter. The method further comprises determining, by the terminal, whether the triggering condition of the target event is met according to the second parameter and an actual measurement result.

4. The method according to any one of claims 1 to 3, wherein, The obtaining, by the terminal, of the first parameter comprises: obtaining, by the terminal, the first parameter indicated by the network-side device through network signaling.

5. The method of claim 4, wherein, The obtaining, by the terminal, of the first parameter indicated by the network-side device through network signaling comprises: obtaining, by the terminal, first indication information indicated by the network signaling, wherein the first indication information is used to indicate an offset value of a value of the first parameter relative to a configured value of the first parameter, and the configured value is a value configured by the network-side device for the first parameter; determining, by the terminal, the value of the first parameter based on the configured value and the offset value.

6. The method of claim 4, wherein, The obtaining, by the terminal, of the first parameter indicated by the network-side device through network signaling comprises: obtaining, by the terminal, second indication information indicated by the network signaling, wherein the second indication information is used to indicate one set of parameters configured by the network-side device for the target event; obtaining, by the terminal, the first parameter based on the second indication information.

7. The method according to any one of claims 4 to 6, wherein, Before the obtaining, by the terminal, of the first parameter indicated by the network-side device through network signaling, the method further comprises: sending, by the terminal, reporting information to the network-side device, wherein the reporting information comprises at least one of: a radio resource management (RRM) measurement result monitored by a first AI model of the network-side device; a prediction result of an RRM measurement monitored by the first AI model of the network-side device; a prediction result of a measurement event monitored by the first AI model of the network-side device; a result monitored by a second AI model of the terminal; a value of the first parameter recommended by the terminal.

8. The method of claim 2 or 3, wherein, The configuration information further comprises a model accuracy threshold, and the determining, by the terminal, whether the triggering condition of the target event is met according to the first parameter and the predicted measurement result comprises: obtaining, by the terminal, a prediction accuracy of an AI model associated with the predicted measurement result; in a case where the prediction accuracy is lower than the model accuracy threshold, determining, by the terminal, whether the triggering condition of the target event is met according to the first parameter and the predicted measurement result.

9. The method of claim 8, wherein, After the obtaining, by the terminal, of the prediction accuracy of the AI model associated with the predicted measurement result, the method further comprises: in a case where the prediction accuracy is lower than the model accuracy threshold, sending, by the terminal, third indication information to the network-side device, wherein the third indication information is used to indicate that the terminal uses the first parameter to determine whether the triggering condition of the target event is met.

10. The method of claim 2, wherein, The configuration information includes multiple sets of the first parameters and a monitoring threshold corresponding to each set of the first parameters; and the terminal acquires the first parameters, including: The terminal acquires a prediction error of an AI model associated with the predicted measurement result; The terminal selects one set of the first parameters in which the monitoring threshold matches the prediction error from the multiple sets of the first parameters.

11. The method of claim 10, wherein, After the terminal acquires the one set of the first parameters in which the monitoring threshold matches the prediction error, the method further includes: The terminal sends fourth indication information to the network side device, where the fourth indication information is used to indicate the selected one set of the first parameters.

12. The method of claim 1, wherein, The terminal acquires the first parameters, including: The terminal acquires a value range of the first parameters configured by the network side device; The terminal acquires a monitoring result of an AI model associated with the predicted measurement result; The terminal determines a value of the first parameter within the value range based on the monitoring result.

13. The method of claim 12, wherein, After the terminal determines the value of the first parameter within the value range based on the monitoring result, the method further includes: The terminal sends fifth indication information to the network side device, where the fifth indication information is used to indicate the determined value of the first parameter.

14. The method according to any one of claims 2 to 13, wherein, The first parameter configured by the network side device is associated with at least one of the following: A measurement configuration, where the target event is a prediction event configured in the measurement configuration; A measurement object, where the target event is a prediction event associated with a frequency point in the measurement object; A reporting configuration, where the target event is a prediction event predicted using the reporting configuration; An artificial intelligence (AI) function, where the target event is a prediction event for predicting a cell using the AI function; An AI model, where the target event is a prediction event for predicting a cell using the AI model.

15. The method according to any one of claims 1 to 14, wherein, The predicted measurement result includes at least one of the following: A predicted measurement result of a serving cell; A predicted measurement result of a neighboring cell.

16. The method of claim 15, wherein, The terminal determines whether the trigger condition of the target event is met based on the first parameter and the predicted measurement result, including one of the following: Based on the predicted measurement result of the serving cell or the predicted result of the neighboring cell, it is determined whether the trigger condition of the target event is continuously met within a trigger time; Based on the actual measurement result of the serving cell or the neighboring cell and the predicted measurement result of the serving cell or the neighboring cell, it is determined whether the trigger condition of the target event is continuously met within a trigger time.

17. The method of any one of claims 1 to 16, wherein, The first parameter includes a target offset value or a target factor; The terminal determines whether the trigger condition of the target event is met based on the first parameter and the predicted measurement result, including: The terminal uses the predicted measurement result and the first parameter in a discriminant corresponding to the trigger condition of the target event to determine whether the trigger condition of the target event is met.

18. An event prediction method, comprising: A network side device sends configuration information to a terminal, where the configuration information includes a first parameter, and the configuration information is used to instruct the terminal to determine whether a trigger condition of a target event is met based on a predicted measurement result and the first parameter.

19. The method of claim 18, wherein, The configuration information further includes a second parameter, and the configuration information is used to instruct the terminal to determine whether a triggering condition of the target event is met according to the second parameter and an actual measurement result.

20. The method of claim 19, wherein, After the network-side device sends the configuration information to the terminal, the method further includes: The network-side device receives third indication information sent by the terminal, where the third indication information is used to indicate that the terminal uses the first parameter in a process of determining whether a triggering condition of the target event is met.

21. The method of any one of claims 18 to 20, wherein, The configuration information includes multiple sets of the first parameter and a monitoring threshold corresponding to each set of the first parameter.

22. The method of claim 21, wherein, After the network-side device sends the configuration information to the terminal, the method further includes: The network-side device receives fourth indication information sent by the terminal, where the fourth indication information is used to indicate a set of the first parameter used by the terminal in a process of determining whether a triggering condition of the target event is met.

23. The method of claim 18, wherein, After the network-side device sends the configuration information to the terminal, the method further includes: The network-side device sends network signaling to the terminal, where the network signaling is used to indicate a value of the first parameter.

24. The method of claim 23, wherein, The network signaling is used to indicate one of the following: First indication information, where the first indication information is used to indicate an offset value of the value of the first parameter relative to a configuration value of the first parameter, and the configuration value is a value of the first parameter configured by the network-side device; Second indication information, where the second indication information is used to indicate the first parameter in multiple sets of parameters configured by the network-side device for the target event.

25. The method of claim 23 or 24, wherein, Before the network-side device sends the network signaling to the terminal, the method further includes: The network-side device receives report information sent by the terminal, where the report information includes at least one of the following: RRM measurement results monitored by a first AI model of the network-side device; Prediction results monitored by the first AI model of the network-side device; Results monitored by a second AI model of the terminal; A value of the first parameter recommended by the terminal.

26. The method of claim 18, wherein, The configuration information includes a value range of the first parameter.

27. The method of claim 26, wherein, After the network-side device sends the configuration information to the terminal, the network-side device receives fifth indication information sent by the terminal, where the fifth indication information is used to indicate the value of the first parameter determined by the terminal. The configuration information is associated with at least one of the following:

28. The method of any one of claims 18 to 27, wherein, Measurement configuration, where the target event is a prediction event configured in the measurement configuration; Measurement object, where the target event is a prediction event associated with a frequency point in the measurement object; Report configuration, where the target event is a prediction event predicted using the report configuration; AI function, where the target event is a prediction event used to predict a cell using the AI function; AI model, where the target event is a prediction event used to predict a cell using the AI model.

29. An event prediction apparatus, comprising: a processing module configured to: obtain a first parameter; obtain a prediction measurement result; ​ According to the first parameter and the predicted measurement result, it is determined whether a triggering condition of a target event is met.

30. The apparatus of claim 29, wherein, The processing module obtains the first parameter by obtaining configuration information configured by the network-side device for the terminal, wherein the configuration information comprises the first parameter.

31. The apparatus of claim 29 or 30, wherein, The apparatus further comprises a receiving module configured to receive network signaling sent by the network-side device, wherein the network signaling is used to indicate the first parameter. The processing module obtains the first parameter based on the indication of the network signaling.

32. The apparatus of claim 31, wherein, The processing module obtains the first parameter based on the indication of the network signaling, comprising: obtaining first indication information indicated by the network signaling, wherein the first indication information is used to indicate an offset value of the value of the first parameter relative to a configuration value of the first parameter, and the configuration value is a value configured by the network-side device for the first parameter; determining the value of the first parameter based on the configuration value and the offset value.

33. The apparatus of claim 31, wherein, The processing module obtains the first parameter based on the indication of the network signaling, comprising: obtaining second indication information indicated by the network signaling, wherein the second indication information is used to indicate the first parameter in a plurality of sets of parameters configured by the network-side device for the target event; obtaining the first parameter based on the second indication information.

34. The apparatus of any one of claims 31 to 33, wherein, Further comprising: a sending module configured to send reporting information to the network-side device, wherein the reporting information comprises at least one of the following: RRM measurement results monitored by the first AI model of the network-side device; prediction results of RRM measurement monitored by the first AI model of the network-side device; prediction results of measurement events monitored by the first AI model of the network-side device; results monitored by the second AI model of the terminal; a value of the first parameter recommended by the terminal.

35. The apparatus of claim 30, wherein, The configuration information further comprises a model accuracy threshold; and the processing module determines whether the triggering condition of the target event is met according to the first parameter and the predicted measurement result, comprising: obtaining a prediction accuracy of an AI model associated with the predicted measurement result; in a case where the prediction accuracy is lower than the model accuracy threshold, determining whether the triggering condition of the target event is met according to the first parameter and the predicted measurement.

36. The apparatus of claim 35, wherein, Further comprising: a sending module configured to send third indication information to the network-side device in a case where the prediction accuracy is lower than the model accuracy threshold, wherein the third indication information is used to instruct the terminal to determine whether the triggering condition of the target event is met using the first parameter.

37. The apparatus of claim 30, wherein, The configuration information comprises a plurality of sets of the first parameter and a monitoring threshold corresponding to each set of the first parameter; and the processing module obtains the first parameter by: obtaining a prediction error of an AI model associated with the predicted measurement result; selecting a set of the first parameter in the plurality of sets of the first parameter, whose monitoring threshold matches the prediction error.

38. The apparatus of claim 37, wherein, Further comprising: The sending module is configured to send fourth indication information to the network-side device, where the fourth indication information is used to indicate a selected set of the first parameters.

39. The apparatus of claim 29, wherein, The processing module obtains the first parameters, including: obtaining a value range of the first parameters configured by the network-side device; obtaining a monitoring result of an AI model associated with the predicted measurement result; determining a value of the first parameter in the value range based on the monitoring result.

40. The apparatus of claim 39, wherein, Further comprising: The sending module is configured to send fifth indication information to the network-side device, where the fifth indication information is used to indicate the determined value of the first parameter.

41. An event prediction apparatus, comprising: The sending module is configured to send configuration information to the terminal, where the configuration information includes first parameters, and the configuration information is used to instruct the terminal to determine whether a trigger condition of a target event is met based on a predicted measurement result and the first parameters.

42. The device of claim 41, wherein, Further comprising: The receiving module is configured to receive third indication information sent by the terminal, where the third indication information is used to indicate that the terminal uses the first parameters to predict the target event in the process of determining whether the trigger condition of the target event is met.

43. The device of claim 41, wherein, The configuration information includes multiple sets of the first parameters and a monitoring threshold corresponding to each set of the first parameters; the apparatus further comprises a receiving module configured to receive fourth indication information sent by the terminal, where the fourth indication information is used to indicate a set of the first parameters used by the terminal in the process of determining whether the trigger condition of the target event is met.

44. The device of claim 41, wherein, The sending module is further configured to send network signaling to the terminal, where the network signaling is used to indicate the value of the first parameter.

45. The device of claim 44, wherein, Further comprising: The receiving module is configured to receive report information sent by the terminal, where the report information includes at least one of the following: RRM measurement results for first AI model monitoring of the network-side device; predicted results for first AI model monitoring of the network-side device; results of second AI model monitoring of the terminal; a recommended value of the first parameter of the terminal.

46. The device of claim 41, wherein, The configuration information includes a value range of the first parameters; the apparatus further comprises a receiving module configured to receive fifth indication information sent by the terminal, where the fifth indication information is used to indicate the value of the first parameter determined by the terminal.

47. A terminal comprising a processor and a memory, the memory storing programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement steps of the event prediction method according to any one of claims 1 to 17.

48. A network-side device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, and when the programs or instructions are executed by the processor, implement steps of the event prediction method according to any one of claims 18 to 28.

49. A readable storage medium, on which a program or instructions are stored, the program or instructions being executed by a processor to implement the steps of the event prediction method according to any one of claims 1 to 17, or to implement the steps of the event prediction method according to any one of claims 18 to 28.

Images