Model prediction processing method and device, terminal and network side equipment

Abstract

The invention discloses a model prediction processing method and device, a terminal and network side equipment, and belongs to the field of communication, and the method comprises the steps that the terminal receives configuration information from the network side equipment; the terminal obtains a prediction result based on the target AI model, wherein the prediction result comprises first output or second output; the first output comprises at least one of the following items: an indication of whether the target timer is overtime; the timeout moment of the target timer; predicting signal quality of the serving cell; predicting signal quality of an adjacent region; predicting signal quality of the target cell; an indication of whether a first target behavior will occur; a moment at which the first target behavior occurs; the second output includes at least one of: an indication of whether the target counter will reach a maximum count value; the moment when the target counter reaches the maximum count value; predicting signal quality of the serving cell; predicting signal quality of an adjacent region; predicting signal quality of the target cell; an indication of whether a second target behavior will occur; and a moment when the second target behavior occurs.

Description

Technical Field

[0001] The present application belongs to the field of communication technology, and specifically relates to a model prediction processing method, device, terminal and network side equipment. Background Art

[0002] With the development of communication technology, timers and counters are usually set in communication systems to control the establishment, recovery and reconstruction of radio resource control (RRC) connections, as well as processes such as mobility management and beam management. However, at present, it is usually necessary to execute the relevant process only when the timer times out or the counter reaches the maximum count value, which will cause a large execution delay of the relevant process. For example, for timer T304, the terminal will continue to try to access the target cell before the timeout, resulting in a long data interruption time and unnecessary terminal power consumption waste. Therefore, there is a problem in the prior art that the timer or counter runs too long, resulting in poor communication performance. Summary of the invention

[0003] The embodiments of the present application provide a model prediction processing method, apparatus, terminal and network-side equipment, which can solve the problem of poor communication performance caused by a timer or counter running for too long.

[0004] In a first aspect, a model prediction processing method is provided, comprising:

[0005] The terminal receives configuration information from the network side device, where the configuration information is used to configure the target artificial intelligence AI model;

[0006] The terminal performs model inference based on the target AI model to obtain a prediction result, where the prediction result includes the first output or the second output of the target AI model;

[0007] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0008] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0009] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

[0010] In a second aspect, a model prediction processing method is provided, comprising:

[0011] The network-side device sends configuration information to the terminal, where the configuration information is used to configure a target artificial intelligence (AI) model, where the target AI model is used for model reasoning to obtain a prediction result, where the prediction result includes a first output or a second output of the target AI model;

[0012] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0013] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0014] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

[0015] In a third aspect, a model prediction processing device is provided, comprising:

[0016] A first receiving module, configured to receive configuration information from a network-side device, wherein the configuration information is used to configure a target artificial intelligence AI model;

[0017] An inference module, configured to perform model inference based on the target AI model to obtain a prediction result, wherein the prediction result includes the first output or the second output of the target AI model;

[0018] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0019] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0020] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

[0021] In a fourth aspect, a model prediction processing device is provided, comprising:

[0022] A first sending module, used to send configuration information to a terminal, wherein the configuration information is used to configure a target artificial intelligence AI model, wherein the target AI model is used for model reasoning to obtain a prediction result, wherein the prediction result includes a first output or a second output of the target AI model;

[0023] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0024] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0025] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

[0026] In a fifth aspect, a terminal is provided, comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0027] In a sixth aspect, a terminal is provided, comprising a processor and a communication interface, wherein the communication interface is used to receive configuration information from a network side device, and the configuration information is used to configure a target artificial intelligence AI model;

[0028] The processor is used to perform model reasoning based on the target AI model to obtain a prediction result, where the prediction result includes the first output or the second output of the target AI model;

[0029] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0030] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0031] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

[0032] In the seventh aspect, a network side device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the second aspect are implemented.

[0033] In an eighth aspect, a network side device is provided, including a processor and a communication interface, wherein the communication interface is used to send configuration information to a terminal, the configuration information is used to configure a target artificial intelligence (AI) model, the target AI model is used for model reasoning to obtain a prediction result, and the prediction result includes a first output or a second output of the target AI model;

[0034] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0035] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0036] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

[0037] In the ninth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented.

[0038] In the tenth aspect, a wireless communication system is provided, comprising: a terminal and a network side device, wherein the terminal can be used to execute the steps of the method described in the first aspect, and the network side device can be used to execute the steps of the method described in the second aspect.

[0039] In the eleventh aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect, or to implement the method described in the second aspect.

[0040] In the twelfth aspect, a computer program / program product is provided, wherein the computer program / program product is stored in a storage medium, and the program / program product is executed by at least one processor to implement the method as described in the first aspect, or to implement the method as described in the second aspect.

[0041] In an embodiment of the present application, configuration information is received from a network side device through a terminal, and the configuration information is used to configure a target artificial intelligence AI model; the terminal performs model inference based on the target AI model to obtain a prediction result, and the prediction result includes a first output or a second output of the target AI model; wherein the first output includes at least one of the following: an indication of whether a target timer will time out; the moment when the target timer times out; the predicted signal quality of the serving cell at a future moment; the predicted signal quality of the neighboring cell at a future moment; the predicted signal quality of the target cell at a future moment; an indication of whether a first target behavior will occur; the moment when the first target behavior occurs; the second output includes at least one of the following: an indication of whether a target counter will reach a maximum count value; the moment when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future moment; the predicted signal quality of the neighboring cell at a future moment; the predicted signal quality of the target cell at a future moment; an indication of whether a second target behavior will occur; the moment when the second target behavior occurs; wherein the first target behavior is the behavior corresponding to the timeout of the target timer, and the second target behavior is the behavior corresponding to the target counter reaching the maximum count value. In this way, the terminal can determine whether the first target behavior occurs before the target timer times out or determine whether the second target behavior occurs before the target counter reaches the maximum count value, so that the operation corresponding to the first target behavior or the operation corresponding to the second target behavior can be performed in advance based on the prediction result, or the prediction result can be reported to the network side device so that the terminal can perform the operation corresponding to the first target behavior or the operation corresponding to the second target behavior in advance, thereby avoiding problems such as poor service quality of the terminal, data interruption, and power consumption waste caused by the long running time of the timer or counter. Therefore, the embodiment of the present application improves communication performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a block diagram of a wireless communication system to which the embodiments of the present application can be applied;

[0043] Figure 2 It is a schematic diagram of the structure of neurons in a neural network;

[0044] Figure 3 It is a flowchart of a model prediction processing method provided in an embodiment of the present application;

[0045] Figure 4 It is a flowchart of another model prediction processing method provided in an embodiment of the present application;

[0046] Figure 5 It is a structural schematic diagram of a model prediction processing device provided in an embodiment of the present application;

[0047] Figure 6is a structural schematic diagram of another model prediction processing device provided in an embodiment of the present application;

[0048] Figure 7 It is a structural diagram of a communication device provided in an embodiment of the present application;

[0049] Figure 8 is a schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0050] Fig. 9 It is a structural diagram of a network side device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The terms "first", "second", etc. of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of one type, and the number of objects is not limited, for example, the first object can be one or more. In addition, "or" in the present application represents at least one of the connected objects. For example, "A or B" covers three schemes, namely, Scheme 1: including A but not including B; Scheme 2: including B but not including A; Scheme 3: including both A and B. The character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0052] The term "indication" in this application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, operations to be performed, or request results in the sent indication; an indirect indication can be understood as the receiver determining the corresponding information according to the indication sent by the sender, or making a judgment and determining the operation to be performed or the request result according to the judgment result.

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

[0054] Figure 1A block diagram of a wireless communication system applicable to an embodiment of the present application is shown. The wireless communication system includes a terminal 11 and a network side device 12. Among them, the terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a handheld computer, a netbook, an ultra-mobile personal computer (Ultra-mobile Personal Computer, UMPC), a mobile Internet device (Mobile Internet Device, MID), an augmented reality (Augmented Reality, AR), a virtual reality (Virtual Reality, VR) device, a robot, a wearable device (Wearable Device), an aircraft (flight vehicle), a vehicle-mounted device (Vehicle User Equipment, VUE), a ship-mounted device, a pedestrian terminal (Pedestrian User Equipment, PUE), a smart home (home appliances with wireless communication functions, such as refrigerators, televisions, washing machines or furniture, etc.), a game console, a personal computer (Personal Computer, PC), a teller machine or a self-service machine and other terminal side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be referred to as a radio access network (Radio Access Network, RAN) device, a radio access network function or a radio access network unit. The access network device may include a base station, a wireless local area network (Wireless Local Area Network, WLAN) access point (Access Point, AP) or a wireless fidelity (Wireless Fidelity, WiFi) node, etc.Among them, the base station may be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a Relay Base Station (RBS), a Serving Base Station (SBS), a Base Transceiver Station (BTS), a radio base station, a radio transceiver, a Basic Service Set (BSS), an Extended Service Set (ESS), a Home Node B (HNB), a Home Evolved Node B (home evolved Node B), a Transmission Reception Point (TRP) or other appropriate terms in the relevant field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.

[0055] The core network equipment may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (Mobility Management Entity, MME), access mobility management function (Access and Mobility Management Function, AMF), session management function (Session Management Function, SMF), user plane function (User Plane Function, UPF), policy control function (Policy Control Function, PCF), policy and charging rules function unit (Policy and Charging Rules Function, PCRF), edge application service discovery function (Edge Application Server Discovery Function, EASDF), unified data management (Unified Data Management, UDM), unified data storage (Unified Data Repository, UDR), home user server (Home Subscriber Server, HSS), centralized network configuration (CNC), network storage function (Network Repository Function, NRF), network exposure function (Network Exposure Function, NEF), local NEF (Local NEF, or L-NEF), binding support function (Binding Support Function, BSF), application function (Application Function, AF), etc. It should be noted that in the embodiments of the present application, only the core network device in the NR system is introduced as an example, and the specific type of the core network device is not limited.

[0056] For ease of understanding, some contents involved in the embodiments of the present application are described below:

[0057] 1. Artificial intelligence.

[0058] Artificial intelligence has been widely used in various fields. There are many ways to implement AI modules (i.e., AI models), such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application uses neural networks as an example for illustration, but does not limit the specific type of AI modules.

[0059] Optionally, a neural network is composed of neurons, a schematic diagram of which is shown in FIG. Figure 2As shown, a1, a2, ... aK are inputs, w is the weight, i.e. the multiplicative coefficient, b is the bias, i.e. the additive coefficient, and σ(.) is the activation function. Common activation functions include Sigmoid, tanh, and Rectified Linear Unit (ReLU). Among them, z = a1w1+···+a k w k +···+a K w K +b.

[0060] The parameters of the neural network are optimized through optimization algorithms. Optimization algorithms are a type of algorithm that can help us minimize or maximize the objective function, which can also be called the loss function. The objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we build a neural network model f(.). With the model, we can get the predicted output f(x) based on the input x, and we can calculate the difference between the predicted value and the true value (f(x)-Y), which is the loss function. Our goal is to find a suitable W,b to minimize the value of the above loss function. The smaller the loss value, the closer our model is to the actual situation.

[0061] At present, the common optimization algorithms are basically based on the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two processes: the forward propagation of the signal and the back propagation of the error. During the forward propagation, the input sample is transmitted from the input layer, processed by each hidden layer layer by layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, it will enter the error back propagation stage. Error back propagation is to propagate the output error layer by layer through the hidden layer to the input layer in some form, and distribute the error to all units in each layer, so as to obtain the error signal of each layer unit, and this error signal is used as the basis for correcting the weights of each unit. This process of adjusting the weights of each layer of the signal forward propagation and error back propagation is repeated. The process of 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 pre-set number of learning times is reached.

[0062] Common optimization algorithms include: Gradient Descent, Stochastic Gradient Descent (SGD), mini-batch gradient descent, Momentum, Nesterov, Adaptive Gradient Descent (Adagrad), Adadelta, root mean square prop (RMSprop) and Adaptive Moment Estimation (Adam).

[0063] When these optimization algorithms backpropagate errors, they all calculate the derivative or partial derivative of the current neuron based on the error or loss obtained by the loss function, add the influence of the learning rate, previous gradient, derivative or partial derivative, obtain the gradient, and pass the gradient to the previous layer.

[0064] 2. AI model.

[0065] In this application, the AI ​​model may be referred to as an AI unit, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI characteristic, a neural network, a neural network function, a neural network function, etc., or the AI ​​model may also refer to a processing unit that can implement specific algorithms, formulas, processing procedures, capabilities, etc. related to AI, or the AI ​​model may be a processing method, algorithm, function, module or unit for a specific data set, or the AI ​​model may be a processing method, algorithm, function, module or unit running on AI or ML related hardware such as a graphics processing unit (GPU), a neural processing unit (NPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), etc., and no further limitation is made here.

[0066] Optionally, the specific data set includes at least one of the input and output of the AI ​​model.

[0067] Optionally, the identifier of the AI ​​model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI ​​model, or an identifier of a specific scenario, environment, channel feature, device related to the AI ​​or ML, or an identifier of a function, feature, capability or module related to the AI ​​or ML, and no further limitation is given herein.

[0068] 3. Timer and Counter in 5G NR

[0069] In the 5G NR system, the terminal side maintains multiple timers and counters configured on the network side to control the RRC connection establishment, reestablishment, and recovery processes, as well as mobility-related processes such as Radio Link Monitoring (RLM), Beam Failure Recovery (BFD), and random access during handover.

[0070] The timer specifically includes:

[0071] T300: timer for UE to wait for RRC connection response;

[0072] T301: timer for UE to wait for RRC reestablishment process;

[0073] T304: Timer for UE to randomly access SpCell;

[0074] T310: Timer for UE to monitor radio link failure (RLF);

[0075] T311: The timer for the UE to switch to the idle state after detecting RLF;

[0076] T312: Timer for fast switching failure recovery;

[0077] T316: timer for fast MCG link recovery (fast MCG link recovery);

[0078] T319: Timer for UE to wait for RRC connection recovery response;

[0079] beamFailureDetectionTimer: a timer used in the beam failure detection process;

[0080] Beam Failure Recovery Timer (beamFailureRecoveryTimer): a timer used for beam failure recovery.

[0081] The definitions of the start and stop of each timer and the corresponding behavior after timeout are as follows.

[0082] For T300: The starting conditions include the terminal sending an RRC connection establishment request message (RRCSetupRequest). The stopping conditions include the terminal receiving an RRC establishment message (RRCSetup) or an RRC connection rejection message (RRCReject) or triggering a cell reselection process or the upper layer aborting the RRC connection establishment process. The behaviors corresponding to the T300 timeout include at least one of the following: the UE resets the Medium Access Control (MAC) entity; releases the MAC layer configuration; reestablishes the Radio Link Control (RLC) entity of all established Radio Bearers (RBs); and notifies the upper layer of the RRC connection establishment failure.

[0083] For T301: the start condition includes the UE sending an RRC Reestablishment Request message (RRCReestabilshmentRequest). The stop condition includes the UE receiving an RRC Reestablishment message (RRCReestabilshment) or an RRC Establishment message. The behavior corresponding to the timeout of T301 includes entering the idle state (RRC_IDLE).

[0084] For T304: the starting conditions include the UE receiving an RRC reconfiguration message carrying Reconfiguration with sync, or performing conditional reconfiguration. The stopping conditions include the successful completion of random access on the corresponding special cell (SpCell); for the secondary cell group (SCG), T304 stops once the SCG is released. The behavior corresponding to the T304 timeout includes at least one of the following: for MCG, for handover from NR or intra-NR handover, initiate the RRC reconstruction process; for NR handover to NR, execute the actions defined in the source radio access technology (Source Radio Access Technology, source RAT) protocol. If the Dual Active Protocol Stack (DAPS) bearer is configured and there is no RLF in the source primary cell (PCell), initiate the failure information process; for SCG, initiate the SCG failure information process to notify the network of the failure of Reconfiguration with sync.

[0085] For T310: The starting conditions include detecting physical layer problems of SpCell, such as receiving N310 consecutive out-of-sync indications from the bottom layer. The stopping conditions include receiving N311 consecutive in-sync indications of SpCell from the bottom layer; or receiving an RRC reconfiguration message carrying reconfigurationWithSync. The behaviors corresponding to T310 timeout include at least one of the following: For MCG, if the application server (AS) security is not activated, enter RRC_IDLE; otherwise, initiate the MCG failure information process or the connection reestablishment process; for SCG, initiate the SCG failure information process.

[0086] For T311: The start condition includes initiating the RRC connection reestablishment process. The stop condition includes selecting a suitable NR cell. The behavior corresponding to T311 timeout includes entering RRC_IDLE.

[0087] For T312: The start conditions include at least one of the following: If T312 is configured in MCG: During the operation of T310, the terminal triggered a measurement report corresponding to a measurement ID, and the measurement ID was configured with T312, and useT312 was configured as true; If T312 is configured in SCG and useT312 is configured as true: During the operation of T310, the terminal triggered a measurement report corresponding to a measurement ID, and the measurement ID was configured with T312. The stop conditions include receiving N311 consecutive in-sync indications from the SpCell from the bottom layer, or receiving an RRC reconfiguration message containing reconfigurationWithSync, or performing conditional reconfiguration. The behavior corresponding to the T312 timeout includes at least one of the following: If it is T312 of MCG, initiate the MCG failure information process or the connection reconstruction process; If it is T312 of SCG, initiate the SCG failure information process.

[0088] For T316: The start condition includes the transmission of MCGFailureInformation message. The stop condition includes at least one of the following: receiving RRCRelease; receiving RRCReconfiguration message carrying reconfigurationwithSync for PCell; receiving MobilityFromNRCommand from NR or initiating the reestablishment process. The behavior corresponding to T316 timeout includes initiating the connection reestablishment process.

[0089] For T319: The start conditions include the transmission of RRC Resume Request or RRCResumeRequest, and the recovery process is not initiated for Short Data Transfer (SDT). The stop conditions include the reception of RRC Resume, RRC Setup, RRC Release, RRC Release with Suspend Config, or RRC Reject messages; cell reselection. The corresponding behavior of T319 timeout includes entering RRC_IDLE.

[0090] For beamFailureDetectionTimer: The start condition includes receiving a beam failure instance (BFI) indication from the underlying layer. The behavior after timeout includes setting the Backward Failure Indicator Counter (BFI_COUNTER) to 0.

[0091] For beamFailureRecoveryTimer: the start condition includes the detection of beam failure recovery (BeamFailure Recovery, BFR). The stop condition includes the successful completion of the random access process of SpCell's BFR. The behavior after timeout includes: no longer continue to use CFRA to perform BFR, if preambleTransMax has not reached the maximum number of transmissions, CBRA can continue; if the maximum number of retransmissions is reached and RACH is still unsuccessful, MAC reports RLF to RRC.

[0092] The counters specifically include:

[0093] N310: counter that controls the start time of T310;

[0094] N311: counter that controls the stop time of T310;

[0095] Beam Failure Instance Counter (BFI_COUNTER): A counter that controls the timing of beam failure recovery triggering.

[0096] The definitions of the reset and increment of each counter and the corresponding behavior after reaching the maximum count value are as follows.

[0097] For N310: The reset condition includes at least one of the following: receiving an "in-sync" indication from the bottom layer; receiving an RRC reconfiguration message carrying reconfigurationWithSync; initiating a connection reestablishment process. The increment condition includes receiving "out-of-sync" from the bottom layer when T310 stops running. The actions performed after reaching the maximum count value include starting timer T310.

[0098] For N311: The reset condition includes at least one of the following: receiving an "in-sync" indication from the bottom layer; receiving an RRC reconfiguration message carrying reconfigurationWithSync; initiating a connection reestablishment process. The increment condition includes receiving "in-sync" from the bottom layer when T310 is running. The behavior performed after reaching the maximum count value includes stopping timer T310.

[0099] For BFI_COUNTER: The reset conditions include at least one of the following: beamFailureDetectionTimer timeout; SpCell's BFR random access process is successfully completed. The increment conditions include receiving a beam failure instance indication from the bottom layer. When the maximum count value (beamFailureInstanceMaxCount) is reached, BFR is triggered.

[0100] The model prediction processing method provided in the embodiment of the present application is described in detail below through some embodiments and their application scenarios in combination with the accompanying drawings.

[0101] Reference Figure 3 , the present application embodiment provides a model prediction processing method, such as Figure 3 As shown, the model prediction processing method includes:

[0102] Step 301: The terminal receives configuration information from a network-side device, where the configuration information is used to configure a target artificial intelligence (AI) model.

[0103] Step 302: The terminal performs model inference based on the target AI model to obtain a prediction result, where the prediction result includes the first output or the second output of the target AI model;

[0104] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0105] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0106] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

[0107] In an embodiment of the present application, the above prediction result is used to determine whether the first target behavior or the second target behavior will occur. Since the prediction result is obtained through the target AI model, it can be determined whether the first target behavior occurs before the target timer times out or whether the second target behavior occurs before the target counter reaches the maximum count value, so that the operation corresponding to the first target behavior or the operation corresponding to the second target behavior can be performed in advance based on the prediction result, or the prediction result can be reported to the network side device so that the terminal can perform the operation corresponding to the first target line or the operation corresponding to the second target behavior in advance, thereby avoiding the problem of poor service quality of the terminal, data interruption and power consumption waste caused by the long running time of the timer or counter. Therefore, the embodiment of the present application improves communication performance.

[0108] Optionally, when the above-mentioned first output includes at least one of an indication that the target timer will time out, the moment when the target timer times out, an indication that the first target behavior will occur, and the moment when the first target behavior occurs, it can be determined that the first target behavior will occur based on the first output.

[0109] Optionally, when the above-mentioned first output includes at least one of the predicted signal quality of the serving cell at the future moment, the predicted signal quality of the neighboring cell at the future moment, and the predicted signal quality of the target cell at the future moment, it can be determined whether the first target behavior occurs based on the strength of the predicted signal quality. For example, when the predicted signal quality of the serving cell at the future moment is low, or when the predicted signal quality of the neighboring cell at the future moment is high, it can be considered that the first target behavior will occur.

[0110] Optionally, when the above-mentioned second output includes at least one of an indication that the target counter will reach the maximum count value, the moment when the target counter reaches the maximum count value, an indication that the second target behavior will occur and the moment when the second target behavior occurs, it can be determined that the second target behavior will occur based on the second output.

[0111] Optionally, when the above-mentioned second output includes at least one of the predicted signal quality of the serving cell at the future moment, the predicted signal quality of the neighboring cell at the future moment, and the predicted signal quality of the target cell at the future moment, it can be determined whether the second target behavior occurs based on the strength of the predicted signal quality. For example, when the predicted signal quality of the serving cell at the future moment is low, or when the predicted signal quality of the neighboring cell at the future moment is high, it can be considered that the second target behavior will occur.

[0112] Optionally, the above-mentioned signal quality may include the reference signal receiving power (Reference Signal Receiving Quality, RSRP) of the cell or the beam within the cell, the reference signal receiving quality (Reference Signal Receiving Power, RSRP), the signal to interference plus noise ratio (Signal to Interference plus Noise Ratio, SINR) and the received signal strength indication (Received Signal Strength Indication, RSSI).

[0113] It should be noted that the time when the above-mentioned target timer times out can be specifically represented by a first time interval, and the first time interval can be understood as the interval between the time when the target timer times out and the time when the target timer is turned on or the time when the model inference is started.

[0114] The moment when the above-mentioned target counter reaches the maximum count value can be specifically represented by a second time interval, and the second time interval can be understood as the interval between the moment when the target counter reaches the maximum count value and the moment when the target counter changes from 0 to 1 or the moment when the model inference is started.

[0115] Optionally, the indication of whether the target timer will time out can be represented by 1 bit, for example, the value of the bit is 0 for timeout, 1 for not timeout; of course, it can also be the other way around, such as 1 for timeout, 0 for not timeout.

[0116] Optionally, the indication of whether the target counter will reach the maximum count value can be represented by 1 bit, for example, the value of this bit is 0, indicating that the maximum count value will be reached, and 1, indicating that the maximum count value will not be reached; of course, it can also be vice versa, such as 1 indicating that the maximum count value will be reached, and 0 indicating that the maximum count value will not be reached.

[0117] In an embodiment of the present application, configuration information is received from a network side device through a terminal, and the configuration information is used to configure a target artificial intelligence AI model; the terminal performs model inference based on the target AI model to obtain a prediction result, and the prediction result includes a first output or a second output of the target AI model; wherein the first output includes at least one of the following: an indication of whether a target timer will time out; the moment when the target timer times out; the predicted signal quality of the serving cell at a future moment; the predicted signal quality of the neighboring cell at a future moment; the predicted signal quality of the target cell at a future moment; an indication of whether a first target behavior will occur; the moment when the first target behavior occurs; the second output includes at least one of the following: an indication of whether a target counter will reach a maximum count value; the moment when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future moment; the predicted signal quality of the neighboring cell at a future moment; the predicted signal quality of the target cell at a future moment; an indication of whether a second target behavior will occur; the moment when the second target behavior occurs; wherein the first target behavior is the behavior corresponding to the timeout of the target timer, and the second target behavior is the behavior corresponding to the target counter reaching the maximum count value. In this way, the terminal can determine whether the first target behavior occurs before the target timer times out or determine whether the second target behavior occurs before the target counter reaches the maximum count value, so that the operation corresponding to the first target behavior or the operation corresponding to the second target behavior can be performed in advance based on the prediction result, or the prediction result can be reported to the network side device so that the terminal can perform the operation corresponding to the first target behavior or the operation corresponding to the second target behavior in advance, thereby avoiding problems such as poor service quality of the terminal, data interruption, and power consumption waste caused by the long running time of the timer or counter. Therefore, the embodiment of the present application improves communication performance.

[0118] Optionally, in some embodiments, after the terminal performs model inference based on the target AI model and obtains a prediction result, the method further includes at least one of the following:

[0119] When the prediction result is a first target result, the terminal performs an operation corresponding to a target behavior, where the target behavior includes the first target behavior or the second target behavior, and the first target result is that the first output indicates that the first target behavior will occur or the second output indicates that the second target behavior will occur;

[0120] When the prediction result is a second target result, the terminal continues to run the target timer or the target counter, and the second target result is that the first output indicates that the first target behavior will not occur or the second output indicates that the second target behavior will not occur.

[0121] In some embodiments of the present application, the first target result includes at least one of the following:

[0122] an indication that the target timer will time out or an indication that the target counter will reach a maximum count value;

[0123] an indication that the first target behavior will occur or an indication that the second target behavior will occur;

[0124] The moment when the first target behavior occurs or the moment when the second target behavior occurs.

[0125] Optionally, the second target result includes at least one of the following:

[0126] an indication that the target timer will not time out or an indication that the target counter will not reach a maximum count value;

[0127] An indication that the first target behavior will not occur or an indication that the second target behavior will not occur.

[0128] Optionally, in some embodiments, the above-mentioned first target result may also include at least one of the following: the predicted signal quality of the serving cell at a future moment is lower than a first threshold, the predicted signal quality of the neighboring cell at a future moment is higher than a second threshold, and the predicted signal quality of the target cell at a future moment is higher than a third threshold.

[0129] Optionally, in some embodiments, the above-mentioned second target result may also include at least one of the following: the predicted signal quality of the serving cell at a future moment is higher than a first threshold, the predicted signal quality of the neighboring cell at a future moment is lower than a second threshold, and the predicted signal quality of the target cell at a future moment is lower than a third threshold.

[0130] Optionally, the terminal executing the operation corresponding to the target behavior can be understood or replaced as: the terminal executing the operation corresponding to the target behavior in advance, that is, the terminal executes the operation corresponding to the first target behavior before the target timer times out, and executes the operation corresponding to the second target behavior before the target counter reaches the maximum count value. In this way, when the above-mentioned prediction result is the first target result, the terminal can determine that the target behavior will occur based on the first target result, and thus execute the operation corresponding to the target behavior in advance. Therefore, it is possible to avoid problems such as the poor service quality of the terminal, data interruption, and power consumption waste caused by the long running time of the timer or counter.

[0131] Optionally, in some embodiments, at least one of the first target behavior and the second target behavior includes at least one of the following: wireless link failure; beam failure; switching failure.

[0132] Optionally, in some embodiments, after the terminal performs model inference based on the target AI model and obtains a prediction result, the method further includes:

[0133] The terminal reports the prediction result to the network side device.

[0134] In the embodiment of the present application, the terminal reports the prediction result to the network side device, so that the network side device can trigger the terminal to perform the operation corresponding to the target behavior according to the prediction result. For example, the network side device triggers the terminal to perform cell switching to avoid data interruption caused by poor signal quality of the serving cell.

[0135] Optionally, in some embodiments, the terminal performs model inference based on the target AI model to obtain a prediction result, including:

[0136] The terminal performs model inference based on the target AI model at the target time to obtain a prediction result;

[0137] The target time satisfies any of the following:

[0138] The target time is the time when the target timer is started;

[0139] The target time is after the time when the target timer is started, and the target time is separated from the time when the target timer is started by a first preset time length;

[0140] The target time is the time when the target counter changes from 0 to 1;

[0141] The target time is located after the time when the target counter changes from 0 to 1, and the target time is separated from the time when the target counter changes from 0 to 1 by a second preset time length.

[0142] In an embodiment of the present application, the moment when the target counter changes from 0 to 1 can be understood as the moment when the target counter starts counting. Specifically, the moment when the target counter changes from 0 to 1 can be understood as the time point when the target counter changes from 0 to 1, or the time unit corresponding to the time point, which is seconds, milliseconds, frames, subframes, time slots or symbols.

[0143] By determining the target time for AI model reasoning based on the start time of the target timer or the time when the target counter changes from 0 to 1, the timeliness of model reasoning can be improved, ensuring that the terminal can obtain effective prediction results in a timely manner.

[0144] Optionally, in some embodiments, the terminal performs model reasoning based on the target AI model to obtain a prediction result, including:

[0145] Performing model inference on the target AI model based on the first input or the second input to obtain a preset result;

[0146] Wherein, the first input includes at least one of the following: the signal quality of the serving cell at the historical moment before the target timer is started; the signal quality of the neighboring cell at the historical moment before the target timer is started; the signal quality of the target cell at the historical moment before the target timer is started; the signal quality of the serving cell during the operation of the target timer; the signal quality of the neighboring cell during the operation of the target timer; the signal quality of the target cell during the operation of the target timer; the terminal position at the historical moment before the target timer is started; the terminal speed at the historical moment before the target timer is started; the terminal direction at the historical moment before the target timer is started; the terminal position during the operation of the target timer; the terminal speed during the operation of the target timer; the terminal direction at the historical moment during the operation of the target timer;

[0147] The second input includes at least one of the following: the signal quality of the serving cell during the period when the count value of the target counter is non-0; the signal quality of the neighboring cell during the period when the count value of the target counter is non-0; the signal quality of the target cell during the period when the count value of the target counter is non-0; the signal quality of the serving cell at the historical moment before the count value of the target counter is 1; the signal quality of the neighboring cell at the historical moment before the count value of the target counter is 1; the signal quality of the target cell at the historical moment before the count value of the target counter is 1; the terminal position during the period when the count value of the target counter is non-0; the terminal speed during the period when the count value of the target counter is non-0; the terminal direction during the period when the count value of the target counter is non-0; the terminal position at the historical moment before the count value of the target counter is 1; the terminal speed at the historical moment before the count value of the target counter is 1; the terminal direction at the historical moment before the count value of the target counter is 1.

[0148] Optionally, in some embodiments, the method further comprises:

[0149] The terminal receives target indication information from the network side device, where the target indication information is used to indicate the name of a first object to which the target AI model applies or an identifier associated with the first object, where the first object is the target timer or the target counter.

[0150] In an embodiment of the present application, the above-mentioned network side device may include a first network node and a second network node, wherein the first network node is a network node for receiving data reported by the terminal, the second network node can be understood as a node for model training, and the terminal can receive target indication information from the second network node.

[0151] Optionally, the first network node may be a radio access network (RAN) node, an operation administration and maintenance (OAM) node, a server or a core network node (such as a network data analysis function (NWDAF)).

[0152] Optionally, the second network side node may be a RAN node, an OAM node, a server or a core network node.

[0153] It should be understood that the first network node and the second network node may be the same network node or different network nodes.

[0154] It should be noted that the above-mentioned target timer can be T300, T301, T304, T310, T311, T312, T316, T319, beamFailureDetectionTimer, beamFailureRecoveryTimer, and timers in the 5G NR system or other communication systems or communication standards. Among them, when the target timer is T310, the above-mentioned first target behavior can be a radio link failure; when the above-mentioned target timer is T304, the above-mentioned first target behavior can be a handover failure; when the above-mentioned target timer is beamFailureDetectionTimer, the above-mentioned first target behavior can be a beam failure. For the specific behavior of the first target behavior corresponding to other timers, reference can be made to the relevant technology, which will not be repeated here. The above-mentioned target counter can be N310, N311, BFI_COUNTER, and a counter in the 5G NR system or other communication systems or communication standards. Among them, when the target counter is N310, the second target behavior can be related behaviors after starting T310 or starting T310, such as radio link failure. For the specific behaviors of the second target behaviors corresponding to other counters, reference may be made to the relevant technology and will not be repeated here.

[0155] Optionally, in some embodiments, before the terminal performs model inference based on the target AI model and obtains a prediction result, the method further includes:

[0156] The terminal receives a first signaling from the network side device; the first signaling is used to indicate at least one of the following:

[0157] Turning on, resuming or activating the AI ​​model function of the target timer;

[0158] Start, restore or activate the AI ​​model corresponding to the target timer;

[0159] Open, restore or activate the AI ​​model function of the target counter;

[0160] Open, restore or activate the AI ​​model corresponding to the target counter;

[0161] Turning on, restoring or activating the AI ​​model function of the first target behavior;

[0162] Open, restore or activate the AI ​​model corresponding to the first target behavior;

[0163] Turning on, restoring or activating the AI ​​model function of the second target behavior;

[0164] Start, restore or activate the AI ​​model corresponding to the second target behavior.

[0165] In the embodiment of the present application, the above-mentioned AI model function can be understood or replaced by a prediction function. Since the AI ​​model function or AI model is activated by the network side device through the first signaling, the network side device can determine whether to start the AI ​​model reasoning for prediction according to the actual situation, thereby improving the accuracy of the target AI model prediction.

[0166] Optionally, in some embodiments, the first signaling includes at least one of the following:

[0167] Identification of AI model functionality;

[0168] Identification of the AI ​​model;

[0169] the name of the target timer;

[0170] an identifier of the target timer;

[0171] the name of the target counter;

[0172] an identification of the target counter;

[0173] an identifier of the first target behavior;

[0174] An identifier of the second target behavior.

[0175] Optionally, in some embodiments, before the terminal receives the first signaling from the network side device, the method further includes:

[0176] The terminal reports capability information to the network side device, where the capability information includes at least one of the following:

[0177] Whether the AI ​​model function of the timer is available, or whether the AI ​​model corresponding to the timer is available;

[0178] Whether the AI ​​model function of the counter is available, or whether the AI ​​model corresponding to the counter is available;

[0179] Whether the AI ​​model function of the first behavior is available, or whether the AI ​​model corresponding to the first behavior is available, wherein the first behavior is a behavior corresponding to a timer timeout;

[0180] Whether the AI ​​model function of the second behavior is available, or whether the AI ​​model corresponding to the second behavior is available, wherein the second behavior is the behavior corresponding to the counter reaching the maximum count value.

[0181] Optionally, in some embodiments, the method further comprises:

[0182] The terminal receives a second signaling from the network side device, where the second signaling is used to indicate at least one of the following: stop, suspend or deactivate the AI ​​model function of the second object; stop, suspend or deactivate the AI ​​model corresponding to the second object; stop, suspend or deactivate the AI ​​model function of the first target behavior, and stop, suspend or deactivate the AI ​​model corresponding to the first target behavior; stop, suspend or deactivate the AI ​​model function of the second target behavior, and stop, suspend or deactivate the AI ​​model corresponding to the second target behavior;

[0183] The terminal determines, based on the second signaling, to stop the inference of the AI ​​model corresponding to the second object;

[0184] The second object includes at least one of the target timer and the target counter.

[0185] Optionally, in some embodiments, the method further comprises:

[0186] The terminal collects target information, and the target information is used for model training;

[0187] The target information includes at least one of the following:

[0188] First information, the first information includes at least one of the following: the name of the timer; the identifier associated with the timer; the time information corresponding to the start time of the timer; the time information corresponding to the stop time of the timer; the time information corresponding to the time when the timer times out; the signal quality of the serving cell at the historical moment before the timer is started; the signal quality of the neighboring cell at the historical moment before the timer is started; the signal quality of the target cell at the historical moment before the timer is started; the signal quality of the serving cell during the operation of the timer; the signal quality of the neighboring cell during the operation of the timer; the signal quality of the target cell during the operation of the timer; the terminal position at the historical moment before the timer is started; the terminal speed at the historical moment before the timer is started; the terminal direction at the historical moment before the timer is started; the terminal position during the operation of the timer; the terminal speed during the operation of the timer; the terminal direction at the historical moment during the operation of the timer; the moment when the first behavior occurs, the first behavior is the behavior corresponding to the timer timeout;

[0189] The second information includes at least one of the following: the name of the counter; the identifier associated with the counter; the time information corresponding to the moment when the count value of the counter is increased by 1; the time information corresponding to the moment when the count value of the counter is reset to 0; the time information corresponding to the moment when the counter reaches the maximum count value; the service cell signal quality during the period when the count value of the counter is non-0; the neighboring cell signal quality during the period when the count value of the counter is non-0; the target cell signal quality during the period when the count value of the counter is non-0; the service cell signal quality at the historical moment before the count value of the counter is 1; the neighboring cell signal quality at the historical moment before the count value of the counter is 1; the target cell signal quality at the historical moment before the count value of the counter is 1; the terminal position during the period when the count value of the counter is non-0; the terminal speed during the period when the count value of the counter is non-0; the terminal direction during the period when the count value of the counter is non-0; the terminal position at the historical moment before the count value of the counter is 1; the terminal speed at the historical moment before the count value of the counter is 1; the terminal direction at the historical moment before the count value of the counter is 1; the moment when the second behavior occurs, the second behavior is the behavior corresponding to the timer timeout.

[0190] In the embodiment of the present application, when the network side device performs model training, after the terminal collects the target information, it reports the target information to the network side device. Wherein, when the target information reported by the terminal to the network side device includes signal quality, it may further include a timestamp corresponding to the signal quality and a step length between timestamps corresponding to multiple signal qualities. Wherein, the timestamp or step length may include units such as year, month, day, hour, minute, second, millisecond, frame, subframe, time slot or symbol.

[0191] It should be noted that the manner in which the terminal sends the target data to the network side device may be determined by a protocol agreement or configured by the network side device. Specifically, the manner in which the terminal sends the target data to the network side device includes any of the following:

[0192] Periodic reporting;

[0193] Event-triggered reporting, such as timer timeout trigger, timer stop trigger, and timer restart trigger;

[0194] The trigger is when the data volume threshold configured by the network is reached, for example, when the amount of data collected by the terminal exceeds a certain threshold.

[0195] It should be understood that the above target information used for model training can be understood as: used for initial training of the model, used for retraining of the model or used for model fine-tuning.

[0196] In order to better understand the present application, the following will take network-side device training and terminal-side reasoning as examples and provide detailed explanations through some examples.

[0197] In some embodiments, it can be used for T304 prediction, specifically including the following steps.

[0198] Step 10, the terminal reports the target information collected during the operation of T304 for multiple times, and the target information includes at least one of the following: the name of T304; the identifier associated with T304; the time information corresponding to the start time of T304; the time information corresponding to the stop time of T304; the time information corresponding to the time when T304 times out; the signal quality of the serving cell at N historical moments before the start of T304; the signal quality of the neighboring cell at N historical moments before the start of T304; the signal quality of the target cell at N historical moments before the start of T304; the signal quality of the serving cell during the operation of T304; the signal quality of the neighboring cell during the operation of T304; the signal quality of the target cell during the operation of T304; the terminal position at N historical moments before the start of T304; the terminal speed at N historical moments before the start of T304; the terminal direction at historical moments before the start of T304; the terminal position during the operation of T304; the terminal speed during the operation of T304; the terminal direction at historical moments during the operation of T304; the moment when the first behavior occurs, and the first behavior is the behavior corresponding to the timeout of T304.

[0199] Step 11, the terminal receives a model for T304 timeout prediction sent by a network side device;

[0200] The input of the model is at least one of the following: the signal quality of the serving cell at the historical moment before the start of T304; the signal quality of the neighboring cell at the historical moment before the start of T304; the signal quality of the target cell at the historical moment before the start of T304; the signal quality of the serving cell during the operation of T304; the signal quality of the neighboring cell during the operation of T304; the signal quality of the target cell during the operation of T304; the terminal position at the historical moment before the start of T304; the terminal speed at the historical moment before the start of T304; the terminal direction at the historical moment before the start of T304; the terminal position during the operation of T304; the terminal speed during the operation of T304; the terminal direction at the historical moment during the operation of T304;

[0201] The output of the model is at least one of the following: an indication of whether T304 will time out; the time when T304 times out; the predicted signal quality of the serving cell at the next N time points; the predicted signal quality of the neighboring cell at the next N time points; the predicted signal quality of the target cell at the next N time points; an indication of whether the first target behavior will occur; the time when the first target behavior occurs.

[0202] Step 12: When the terminal receives an RRC reconfiguration message carrying a synchronous reconfiguration (Reconfiguration With Sync), or performs a conditional reconfiguration, or performs a layer 1 or layer 2 triggered mobility (L1 / L2-Triggered Mobility, LTM) switching, T304 is started. The terminal performs model reasoning of timer T304.

[0203] Step 13: The terminal performs the following actions based on the T304 inference result:

[0204] Case 1: It is predicted that T304 will time out, and the terminal immediately executes the action after T304 timeout, that is, initiates the RRC reconstruction process of the master cell group (MCG) or the SCG failure information process of the secondary cell group (SCG).

[0205] Case 2: It is predicted that T304 will not time out, and the terminal continues to run T304 and continues to try to access the target cell before T304 times out.

[0206] Optionally, for terminal-side training or server OTT (Over the top) server training, there are no steps 10 and 11. At this time, the network-side device instructs the terminal to start, stop, activate or deactivate the AI ​​model function or model ID predicted by the T304 timer. When the prediction function is turned on or activated, the terminal can perform the T304 prediction of steps 12 and 13. Among them, OTT server refers to a service provided by a third party other than the operator.

[0207] Optionally, in some embodiments, it can be used for T310 prediction, specifically including the following steps.

[0208] Step 20, the terminal reports the target information collected during the operation of T310 for multiple times, and the target information includes at least one of the following: the name of T310; the identifier associated with T310; the time information corresponding to the start time of T310; the time information corresponding to the stop time of T310; the time information corresponding to the time when T310 times out; the signal quality of the serving cell at N historical moments before T310 is started; the signal quality of the neighboring cell at N historical moments before T310 is started; the signal quality of the target cell at N historical moments before T310 is started; the signal quality of the serving cell during the operation of T310; the signal quality of the neighboring cell during the operation of T310; the signal quality of the target cell during the operation of T310; the terminal position at N historical moments before T310 is started; the terminal speed at N historical moments before T310 is started; the terminal direction at historical moments before T310 is started; the terminal position during the operation of T310; the terminal speed during the operation of T310; the terminal direction at historical moments during the operation of T310; the moment when the first behavior occurs, and the first behavior is the behavior corresponding to the timeout of T310.

[0209] Step 21, the terminal receives a model for T310 timeout prediction sent by a network side device;

[0210] The input of the model is at least one of the following: the signal quality of the serving cell at the historical moment before the T310 is started; the signal quality of the neighboring cell at the historical moment before the T310 is started; the signal quality of the target cell at the historical moment before the T310 is started; the signal quality of the serving cell during the operation of the T310; the signal quality of the neighboring cell during the operation of the T310; the signal quality of the target cell during the operation of the T310; the terminal position at the historical moment before the T310 is started; the terminal speed at the historical moment before the T310 is started; the terminal direction at the historical moment before the T310 is started; the terminal position during the operation of the T310; the terminal speed during the operation of the T310; the terminal direction at the historical moment during the operation of the T310;

[0211] The output of the model is at least one of the following: an indication of whether the T310 will time out; the time when the T310 times out; the predicted signal quality of the serving cell at the next N time points; the predicted signal quality of the neighboring cell at the next N time points; the predicted signal quality of the target cell at the next N time points; an indication of whether the first target behavior will occur; the time when the first target behavior occurs.

[0212] Step 22: The terminal receives the Out-of-Sync indication of connection N310 and starts T310. The terminal performs model reasoning of timer T310.

[0213] Step 23: The terminal performs the following actions according to the T310 inference result:

[0214] Case 1: If the T310 is predicted to time out, perform any of the following:

[0215] The terminal immediately executes the action after T310 timeout, that is, for MCG, if the application server (AS) security is not activated, it enters the RRC idle (RRC_IDLE) state; otherwise, it initiates the MCG failure information process or the connection reestablishment process; for SCG, it initiates the SCG failure information process;

[0216] The terminal reports the prediction result to the network, where the reported prediction result is the model output result; the terminal continues to run T310 according to the existing process;

[0217] The terminal reports the prediction result to the network and immediately executes the action after T310 times out.

[0218] Case 2: It is predicted that T310 will not time out, and the terminal continues to run T310, and stops T310 after receiving N311 consecutive In-Sync indications.

[0219] Optionally, for the terminal side training or server OTT server training method, there is no step 20 and step 21. At this time, the network side device instructs the terminal to start, stop, activate or deactivate the AI ​​model function or model ID predicted by the T310 timer. When the prediction function is turned on or activated, the terminal can perform the T310 prediction of steps 22 and 23.

[0220] Reference Figure 4 , the present application embodiment also provides a model prediction processing method, such as Figure 4 As shown, the model prediction processing method includes:

[0221] Step 401: The network-side device sends configuration information to the terminal, where the configuration information is used to configure a target artificial intelligence (AI) model, where the target AI model is used for model reasoning to obtain a prediction result, where the prediction result includes a first output or a second output of the target AI model;

[0222] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0223] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0224] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

[0225] Optionally, at least one of the first target behavior and the second target behavior includes at least one of the following: wireless link failure; beam failure; switching failure.

[0226] Optionally, after the network side device sends the configuration information to the terminal, the method further includes:

[0227] The network side device receives the prediction result from the terminal.

[0228] Optionally, the input of the target AI model includes a first input or a second input;

[0229] Wherein, the first input includes at least one of the following: the signal quality of the serving cell at the historical moment before the target timer is started; the signal quality of the neighboring cell at the historical moment before the target timer is started; the signal quality of the target cell at the historical moment before the target timer is started; the signal quality of the serving cell during the operation of the target timer; the signal quality of the neighboring cell during the operation of the target timer; the signal quality of the target cell during the operation of the target timer; the terminal position at the historical moment before the target timer is started; the terminal speed at the historical moment before the target timer is started; the terminal direction at the historical moment before the target timer is started; the terminal position during the operation of the target timer; the terminal speed during the operation of the target timer; the terminal direction at the historical moment during the operation of the target timer;

[0230] The second input includes at least one of the following: the signal quality of the serving cell during the period when the count value of the target counter is non-0; the signal quality of the neighboring cell during the period when the count value of the target counter is non-0; the signal quality of the target cell during the period when the count value of the target counter is non-0; the signal quality of the serving cell at the historical moment before the count value of the target counter is 1; the signal quality of the neighboring cell at the historical moment before the count value of the target counter is 1; the signal quality of the target cell at the historical moment before the count value of the target counter is 1; the terminal position during the period when the count value of the target counter is non-0; the terminal speed during the period when the count value of the target counter is non-0; the terminal direction during the period when the count value of the target counter is non-0; the terminal position at the historical moment before the count value of the target counter is 1; the terminal speed at the historical moment before the count value of the target counter is 1; the terminal direction at the historical moment before the count value of the target counter is 1.

[0231] Optionally, the method further comprises:

[0232] The network side device sends target indication information to the terminal, where the target indication information is used to indicate the name of a first object to which the target AI model is applicable or an identifier associated with the first object, where the first object is the target timer or the target counter.

[0233] Optionally, after the network side device sends the configuration information to the terminal, the method further includes:

[0234] The network side device sends a first signaling to the terminal; the first signaling is used to indicate at least one of the following:

[0235] Turning on, resuming or activating the AI ​​model function of the target timer;

[0236] Start, restore or activate the AI ​​model corresponding to the target timer;

[0237] Open, restore or activate the AI ​​model function of the target counter;

[0238] Open, restore or activate the AI ​​model corresponding to the target counter;

[0239] Turning on, restoring or activating the AI ​​model function of the first target behavior;

[0240] Open, restore or activate the AI ​​model corresponding to the first target behavior;

[0241] Turning on, restoring or activating the AI ​​model function of the second target behavior;

[0242] Start, restore or activate the AI ​​model corresponding to the second target behavior.

[0243] Optionally, the first signaling includes at least one of the following:

[0244] Identification of AI model functionality;

[0245] Identification of the AI ​​model;

[0246] the name of the target timer;

[0247] an identifier of the target timer;

[0248] the name of the target counter;

[0249] an identification of the target counter;

[0250] an identifier of the first target behavior;

[0251] An identifier of the second target behavior.

[0252] Optionally, before the network side device sends the first signaling to the terminal, the method further includes:

[0253] The network side device receives capability information from the terminal, where the capability information includes at least one of the following:

[0254] Whether the AI ​​model function of the timer is available, or whether the AI ​​model corresponding to the timer is available;

[0255] Whether the AI ​​model function of the counter is available, or whether the AI ​​model corresponding to the counter is available;

[0256] Whether the AI ​​model function of the first behavior is available, or whether the AI ​​model corresponding to the first behavior is available, wherein the first behavior is a behavior corresponding to a timer timeout;

[0257] Whether the AI ​​model function of the second behavior is available, or whether the AI ​​model corresponding to the second behavior is available, wherein the second behavior is the behavior corresponding to the counter reaching the maximum count value.

[0258] Optionally, the method further comprises:

[0259] The network-side device sends a second signaling to the terminal, where the second signaling is used to indicate at least one of the following: stop, pause or deactivate the AI ​​model function of the second object; stop, pause or deactivate the AI ​​model corresponding to the second object; stop, pause or deactivate the AI ​​model function of the first target behavior, stop, pause or deactivate the AI ​​model corresponding to the first target behavior; stop, pause or deactivate the AI ​​model function of the second target behavior, stop, pause or deactivate the AI ​​model corresponding to the second target behavior

[0260] The second object includes at least one of the target timer and the target counter.

[0261] The model prediction processing method provided in the embodiment of the present application can be executed by a model prediction processing device. In the embodiment of the present application, the model prediction processing device executing the model prediction processing method is taken as an example to illustrate the model prediction processing device provided in the embodiment of the present application.

[0262] Reference Figure 5 The present application also provides a model prediction processing device, such as Figure 5 As shown, the model prediction processing device 500 includes:

[0263] The first receiving module 501 is used to receive configuration information from a network side device, where the configuration information is used to configure a target artificial intelligence AI model;

[0264] A reasoning module 502, configured to perform model reasoning based on the target AI model to obtain a prediction result, wherein the prediction result includes a first output or a second output of the target AI model;

[0265] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0266] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0267] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

[0268] Optionally, the model prediction processing device 500 further includes: an execution module, configured to execute at least one of the following:

[0269] When the prediction result is a first target result, the terminal performs an operation corresponding to a target behavior, where the target behavior includes the first target behavior or the second target behavior, and the first target result is that the first output indicates that the first target behavior will occur or the second output indicates that the second target behavior will occur;

[0270] When the prediction result is a second target result, the terminal continues to run the target timer or the target counter, and the second target result is that the first output indicates that the first target behavior will not occur or the second output indicates that the second target behavior will not occur.

[0271] Optionally, the first target result includes at least one of the following:

[0272] an indication that the target timer will time out or an indication that the target counter will reach a maximum count value;

[0273] an indication that the first target behavior will occur or an indication that the second target behavior will occur;

[0274] The moment when the first target behavior occurs or the moment when the second target behavior occurs.

[0275] Optionally, at least one of the first target behavior and the second target behavior includes at least one of the following: wireless link failure; beam failure; switching failure.

[0276] Optionally, the model prediction processing device 500 further includes:

[0277] The second sending module is used to report the prediction result to the network side device.

[0278] Optionally, the reasoning module 502 is specifically used to perform model reasoning based on the target AI model at the target time to obtain a prediction result;

[0279] The target time satisfies any of the following:

[0280] The target time is the time when the target timer is started;

[0281] The target time is after the time when the target timer is started, and the target time is separated from the time when the target timer is started by a first preset time length;

[0282] The target time is the time when the target counter changes from 0 to 1;

[0283] The target time is located after the time when the target counter changes from 0 to 1, and the target time is separated from the time when the target counter changes from 0 to 1 by a second preset time length.

[0284] Optionally, the reasoning module 502 is specifically used to: perform model reasoning on the target AI model based on the first input or the second input to obtain a preset result;

[0285] Wherein, the first input includes at least one of the following: the signal quality of the serving cell at the historical moment before the target timer is started; the signal quality of the neighboring cell at the historical moment before the target timer is started; the signal quality of the target cell at the historical moment before the target timer is started; the signal quality of the serving cell during the operation of the target timer; the signal quality of the neighboring cell during the operation of the target timer; the signal quality of the target cell during the operation of the target timer; the terminal position at the historical moment before the target timer is started; the terminal speed at the historical moment before the target timer is started; the terminal direction at the historical moment before the target timer is started; the terminal position during the operation of the target timer; the terminal speed during the operation of the target timer; the terminal direction at the historical moment during the operation of the target timer;

[0286] The second input includes at least one of the following: the signal quality of the serving cell during the period when the count value of the target counter is non-0; the signal quality of the neighboring cell during the period when the count value of the target counter is non-0; the signal quality of the target cell during the period when the count value of the target counter is non-0; the signal quality of the serving cell at the historical moment before the count value of the target counter is 1; the signal quality of the neighboring cell at the historical moment before the count value of the target counter is 1; the signal quality of the target cell at the historical moment before the count value of the target counter is 1; the terminal position during the period when the count value of the target counter is non-0; the terminal speed during the period when the count value of the target counter is non-0; the terminal direction during the period when the count value of the target counter is non-0; the terminal position at the historical moment before the count value of the target counter is 1; the terminal speed at the historical moment before the count value of the target counter is 1; the terminal direction at the historical moment before the count value of the target counter is 1.

[0287] Optionally, the first receiving module 501 is also used to receive target indication information from the network side device, and the target indication information is used to indicate the name of the first object to which the target AI model is applicable or an identifier associated with the first object, and the first object is the target timer or the target counter.

[0288] Optionally, the first receiving module 501 is further used to receive a first signaling from the network side device; the first signaling is used to indicate at least one of the following:

[0289] Turning on, resuming or activating the AI ​​model function of the target timer;

[0290] Start, restore or activate the AI ​​model corresponding to the target timer;

[0291] Open, restore or activate the AI ​​model function of the target counter;

[0292] Open, restore or activate the AI ​​model corresponding to the target counter;

[0293] Turning on, restoring or activating the AI ​​model function of the first target behavior;

[0294] Open, restore or activate the AI ​​model corresponding to the first target behavior;

[0295] Turning on, restoring or activating the AI ​​model function of the second target behavior;

[0296] Start, restore or activate the AI ​​model corresponding to the second target behavior.

[0297] Optionally, the first signaling includes at least one of the following:

[0298] Identification of AI model functionality;

[0299] Identification of the AI ​​model;

[0300] the name of the target timer;

[0301] an identifier of the target timer;

[0302] the name of the target counter;

[0303] an identification of the target counter;

[0304] an identifier of the first target behavior;

[0305] An identifier of the second target behavior.

[0306] Optionally, the model prediction processing device 500 further includes:

[0307] The second sending module is configured to report capability information to the network side device, where the capability information includes at least one of the following:

[0308] Whether the AI ​​model function of the timer is available, or whether the AI ​​model corresponding to the timer is available;

[0309] Whether the AI ​​model function of the counter is available, or whether the AI ​​model corresponding to the counter is available;

[0310] Whether the AI ​​model function of the first behavior is available, or whether the AI ​​model corresponding to the first behavior is available, wherein the first behavior is a behavior corresponding to a timer timeout;

[0311] Whether the AI ​​model function of the second behavior is available, or whether the AI ​​model corresponding to the second behavior is available, wherein the second behavior is the behavior corresponding to the counter reaching the maximum count value.

[0312] Optionally, the first receiving module 501 is further used to receive a second signaling from the network side device, where the second signaling is used to indicate at least one of the following: stop, pause or deactivate the AI ​​model function of the second object; stop, pause or deactivate the AI ​​model corresponding to the second object; stop, pause or deactivate the AI ​​model function of the first target behavior, stop, pause or deactivate the AI ​​model corresponding to the first target behavior; stop, pause or deactivate the AI ​​model function of the second target behavior, stop, pause or deactivate the AI ​​model corresponding to the second target behavior;

[0313] The terminal determines, based on the second signaling, to stop the inference of the AI ​​model corresponding to the second object;

[0314] The second object includes at least one of the target timer and the target counter.

[0315] Optionally, the model prediction processing device 500 further includes:

[0316] A collection module, used to collect target information, and the target information is used for model training;

[0317] The target information includes at least one of the following:

[0318] First information, the first information includes at least one of the following: the name of the timer; the identifier associated with the timer; the time information corresponding to the start time of the timer; the time information corresponding to the stop time of the timer; the time information corresponding to the time when the timer times out; the signal quality of the serving cell at the historical moment before the timer is started; the signal quality of the neighboring cell at the historical moment before the timer is started; the signal quality of the target cell at the historical moment before the timer is started; the signal quality of the serving cell during the operation of the timer; the signal quality of the neighboring cell during the operation of the timer; the signal quality of the target cell during the operation of the timer; the terminal position at the historical moment before the timer is started; the terminal speed at the historical moment before the timer is started; the terminal direction at the historical moment before the timer is started; the terminal position during the operation of the timer; the terminal speed during the operation of the timer; the terminal direction at the historical moment during the operation of the timer; the moment when the first behavior occurs, the first behavior is the behavior corresponding to the timer timeout;

[0319] The second information includes at least one of the following: the name of the counter; the identifier associated with the counter; the time information corresponding to the moment when the count value of the counter is increased by 1; the time information corresponding to the moment when the count value of the counter is reset to 0; the time information corresponding to the moment when the counter reaches the maximum count value; the service cell signal quality during the period when the count value of the counter is non-0; the neighboring cell signal quality during the period when the count value of the counter is non-0; the target cell signal quality during the period when the count value of the counter is non-0; the service cell signal quality at the historical moment before the count value of the counter is 1; the neighboring cell signal quality at the historical moment before the count value of the counter is 1; the target cell signal quality at the historical moment before the count value of the counter is 1; the terminal position during the period when the count value of the counter is non-0; the terminal speed during the period when the count value of the counter is non-0; the terminal direction during the period when the count value of the counter is non-0; the terminal position at the historical moment before the count value of the counter is 1; the terminal speed at the historical moment before the count value of the counter is 1; the terminal direction at the historical moment before the count value of the counter is 1; the moment when the second behavior occurs, the second behavior is the behavior corresponding to the timer timeout.

[0320] Reference Figure 6 The present application also provides a model prediction processing device, such as Figure 5 As shown, the model prediction processing device 600 includes:

[0321] A first sending module 601 is used to send configuration information to a terminal, where the configuration information is used to configure a target artificial intelligence AI model, where the target AI model is used for model reasoning to obtain a prediction result, where the prediction result includes a first output or a second output of the target AI model;

[0322] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0323] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0324] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

[0325] Optionally, at least one of the first target behavior and the second target behavior includes at least one of the following: wireless link failure; beam failure; switching failure.

[0326] Optionally, the model prediction processing device 600 further includes:

[0327] The second receiving module is used to receive the prediction result from the terminal.

[0328] Optionally, the input of the target AI model includes a first input or a second input;

[0329] Wherein, the first input includes at least one of the following: the signal quality of the serving cell at the historical moment before the target timer is started; the signal quality of the neighboring cell at the historical moment before the target timer is started; the signal quality of the target cell at the historical moment before the target timer is started; the signal quality of the serving cell during the operation of the target timer; the signal quality of the neighboring cell during the operation of the target timer; the signal quality of the target cell during the operation of the target timer; the terminal position at the historical moment before the target timer is started; the terminal speed at the historical moment before the target timer is started; the terminal direction at the historical moment before the target timer is started; the terminal position during the operation of the target timer; the terminal speed during the operation of the target timer; the terminal direction at the historical moment during the operation of the target timer;

[0330] The second input includes at least one of the following: the signal quality of the serving cell during the period when the count value of the target counter is non-0; the signal quality of the neighboring cell during the period when the count value of the target counter is non-0; the signal quality of the target cell during the period when the count value of the target counter is non-0; the signal quality of the serving cell at the historical moment before the count value of the target counter is 1; the signal quality of the neighboring cell at the historical moment before the count value of the target counter is 1; the signal quality of the target cell at the historical moment before the count value of the target counter is 1; the terminal position during the period when the count value of the target counter is non-0; the terminal speed during the period when the count value of the target counter is non-0; the terminal direction during the period when the count value of the target counter is non-0; the terminal position at the historical moment before the count value of the target counter is 1; the terminal speed at the historical moment before the count value of the target counter is 1; the terminal direction at the historical moment before the count value of the target counter is 1.

[0331] Optionally, the first sending module 601 is also used to send target indication information to the terminal, wherein the target indication information is used to indicate the name of the first object to which the target AI model is applicable or an identifier associated with the first object, and the first object is the target timer or the target counter.

[0332] Optionally, the first sending module 601 is further used to send a first signaling to the terminal; the first signaling is used to indicate at least one of the following:

[0333] Turning on, resuming or activating the AI ​​model function of the target timer;

[0334] Start, restore or activate the AI ​​model corresponding to the target timer;

[0335] Open, restore or activate the AI ​​model function of the target counter;

[0336] Open, restore or activate the AI ​​model corresponding to the target counter;

[0337] Turning on, restoring or activating the AI ​​model function of the first target behavior;

[0338] Open, restore or activate the AI ​​model corresponding to the first target behavior;

[0339] Turning on, restoring or activating the AI ​​model function of the second target behavior;

[0340] Start, restore or activate the AI ​​model corresponding to the second target behavior.

[0341] Optionally, the first signaling includes at least one of the following:

[0342] Identification of AI model functionality;

[0343] Identification of the AI ​​model;

[0344] the name of the target timer;

[0345] an identifier of the target timer;

[0346] the name of the target counter;

[0347] an identification of the target counter;

[0348] an identifier of the first target behavior;

[0349] An identifier of the second target behavior.

[0350] Optionally, the model prediction processing device 600 further includes:

[0351] The second receiving module is configured to receive capability information from the terminal, where the capability information includes at least one of the following:

[0352] Whether the AI ​​model function of the timer is available, or whether the AI ​​model corresponding to the timer is available;

[0353] Whether the AI ​​model function of the counter is available, or whether the AI ​​model corresponding to the counter is available;

[0354] Whether the AI ​​model function of the first behavior is available, or whether the AI ​​model corresponding to the first behavior is available, wherein the first behavior is a behavior corresponding to a timer timeout;

[0355] Whether the AI ​​model function of the second behavior is available, or whether the AI ​​model corresponding to the second behavior is available, wherein the second behavior is the behavior corresponding to the counter reaching the maximum count value.

[0356] Optionally, the first sending module 601 is further used to send a second signaling to the terminal, and the second signaling is used to indicate at least one of the following: stop, pause or deactivate the AI ​​model function of the second object; stop, pause or deactivate the AI ​​model corresponding to the second object; stop, pause or deactivate the AI ​​model function of the first target behavior, stop, pause or deactivate the AI ​​model corresponding to the first target behavior; stop, pause or deactivate the AI ​​model function of the second target behavior, stop, pause or deactivate the AI ​​model corresponding to the second target behavior

[0357] The second object includes at least one of the target timer and the target counter.

[0358] The model prediction processing device in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than a terminal. Exemplarily, the terminal can include but is not limited to the types of terminals 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

[0359] The model prediction processing device provided in the embodiment of the present application can achieve Figure 3 to Figure 4 The various processes implemented by the method embodiment and achieving the same technical effect are not described here to avoid repetition.

[0360] like Figure 7 As shown, an embodiment of the present application also provides a communication device 700, including a processor 701 and a memory 702, and the memory 702 stores a program or instruction that can be executed on the processor 701. When the program or instruction is executed by the processor 701, the various steps of the above-mentioned model prediction processing method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0361] The embodiment of the present application also provides a terminal, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the following Figure 3 The steps in the method embodiment shown. This terminal embodiment corresponds to the above-mentioned terminal side method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to this terminal embodiment and can achieve the same technical effect. Specifically, Figure 8 A schematic diagram of the hardware structure of a terminal for implementing an embodiment of the present application.

[0362] The terminal 800 includes but is not limited to: a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809 and at least some of the components of a processor 810.

[0363] Those skilled in the art will appreciate that the terminal 800 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to the processor 810 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 8 The terminal structure shown in the figure does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0364] It should be understood that in the embodiment of the present application, the input unit 804 may include a graphics processing unit (GPU) 8041 and a microphone 8042, and the graphics processor 8041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 806 may include a display panel 8061, and the display panel 8061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 807 includes a touch panel 8071 and at least one of other input devices 8072. The touch panel 8071 is also called a touch screen. The touch panel 8071 may include two parts: a touch detection device and a touch controller. Other input devices 8072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0365] In the embodiment of the present application, after receiving downlink data from the network side device, the radio frequency unit 801 can transmit the data to the processor 810 for processing; in addition, the radio frequency unit 801 can send uplink data to the network side device. Generally, the radio frequency unit 801 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[0366] The memory 809 can be used to store software programs or instructions and various data. The memory 809 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 809 may include a volatile memory or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 809 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0367] The processor 810 may include one or more processing units; optionally, the processor 810 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 810.

[0368] The radio frequency unit 801 is used to receive configuration information from a network side device, where the configuration information is used to configure a target artificial intelligence AI model;

[0369] The processor 810 is used to perform model reasoning based on the target AI model to obtain a prediction result, where the prediction result includes the first output or the second output of the target AI model;

[0370] The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs;

[0371] The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs;

[0372] The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

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

[0374] The embodiment of the present application also provides a network side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the following Figure 4 The steps of the method embodiment shown. This network side device embodiment corresponds to the above network side device method embodiment, and each implementation process and implementation mode of the above method embodiment can be applied to this network side device embodiment and can achieve the same technical effect.

[0375] Specifically, the embodiment of the present application also provides a network side device. Fig. 9 As shown, the network side device 900 includes: an antenna 901, a radio frequency device 902, a baseband device 903, a processor 904 and a memory 905. The antenna 901 is connected to the radio frequency device 902. In the uplink direction, the radio frequency device 902 receives information through the antenna 901 and sends the received information to the baseband device 903 for processing. In the downlink direction, the baseband device 903 processes the information to be sent and sends it to the radio frequency device 902. The radio frequency device 902 processes the received information and sends it out through the antenna 901.

[0376] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 903, which includes a baseband processor.

[0377] The baseband device 903 may include, for example, at least one baseband board on which a plurality of chips are arranged. Fig. 9 As shown, one of the chips is, for example, a baseband processor, which is connected to the memory 905 through a bus interface to call the program in the memory 905 to execute the network side device operations shown in the above method embodiment.

[0378] The network side device may further include a network interface 906, which is, for example, a Common Public Radio Interface (CPRI).

[0379] Specifically, the network side device 900 of the embodiment of the present application further includes: an instruction or program stored in the memory 905 and executable on the processor 904, and the processor 904 calls the instruction or program in the memory 905 to execute Figure 7 The methods executed by the modules shown achieve the same technical effects, and therefore will not be described here in detail to avoid repetition.

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

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

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

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

[0384] The embodiments of the present application further provide a computer program / program product, which is stored in a storage medium and is executed by at least one processor to implement the various processes of the above-mentioned model prediction processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0385] An embodiment of the present 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 model prediction processing method on the terminal side as described above, and the network side device can be used to execute the steps of the model prediction processing method on the network side device as described above.

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

[0387] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general hardware platform, and of course, can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, disk, CD, etc.), including several instructions to enable a terminal or a network-side device to execute the methods described in each embodiment of the present application.

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

Claims

1. A model prediction processing method, characterized in that: include: The terminal receives configuration information from the network side device, where the configuration information is used to configure the target artificial intelligence AI model; The terminal performs model inference based on the target AI model to obtain a prediction result, where the prediction result includes the first output or the second output of the target AI model; The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs; The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs; The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

2. The method according to claim 1, characterized in that After the terminal performs model inference based on the target AI model and obtains a prediction result, the method further includes at least one of the following: When the prediction result is a first target result, the terminal performs an operation corresponding to a target behavior, where the target behavior includes the first target behavior or the second target behavior, and the first target result is that the first output indicates that the first target behavior will occur or the second output indicates that the second target behavior will occur; When the prediction result is a second target result, the terminal continues to run the target timer or the target counter, and the second target result is that the first output indicates that the first target behavior will not occur or the second output indicates that the second target behavior will not occur.

3. The method according to claim 2, characterized in that The first target result includes at least one of the following: an indication that the target timer will time out or an indication that the target counter will reach a maximum count value; an indication that the first target behavior will occur or an indication that the second target behavior will occur; The moment when the first target behavior occurs or the moment when the second target behavior occurs.

4. The method according to any one of claims 1 to 3, characterized in that: At least one of the first target behavior and the second target behavior includes at least one of the following: wireless link failure; beam failure; switching failure.

5. The method according to any one of claims 1 to 4, characterized in that: After the terminal performs model inference based on the target AI model and obtains a prediction result, the method further includes: The terminal reports the prediction result to the network side device.

6. The method according to any one of claims 1 to 5, characterized in that: The terminal performs model inference based on the target AI model to obtain a prediction result, including: The terminal performs model inference based on the target AI model at the target time to obtain a prediction result; The target time satisfies any of the following: The target time is the time when the target timer is started; The target time is after the time when the target timer is started, and the target time is separated from the time when the target timer is started by a first preset time length; The target time is the time when the target counter changes from 0 to 1; The target time is located after the time when the target counter changes from 0 to 1, and the target time is separated from the time when the target counter changes from 0 to 1 by a second preset time length.

7. The method according to any one of claims 1 to 6, characterized in that: The terminal performs model reasoning based on the target AI model to obtain a prediction result, including: Performing model inference on the target AI model based on the first input or the second input to obtain a preset result; Wherein, the first input includes at least one of the following: the signal quality of the serving cell at the historical moment before the target timer is started; the signal quality of the neighboring cell at the historical moment before the target timer is started; the signal quality of the target cell at the historical moment before the target timer is started; the signal quality of the serving cell during the operation of the target timer; the signal quality of the neighboring cell during the operation of the target timer; the signal quality of the target cell during the operation of the target timer; the terminal position at the historical moment before the target timer is started; the terminal speed at the historical moment before the target timer is started; the terminal direction at the historical moment before the target timer is started; the terminal position during the operation of the target timer; the terminal speed during the operation of the target timer; the terminal direction at the historical moment during the operation of the target timer; The second input includes at least one of the following: the signal quality of the serving cell during the period when the count value of the target counter is non-0; the signal quality of the neighboring cell during the period when the count value of the target counter is non-0; the signal quality of the target cell during the period when the count value of the target counter is non-0; the signal quality of the serving cell at the historical moment before the count value of the target counter is 1; the signal quality of the neighboring cell at the historical moment before the count value of the target counter is 1; the signal quality of the target cell at the historical moment before the count value of the target counter is 1; the terminal position during the period when the count value of the target counter is non-0; the terminal speed during the period when the count value of the target counter is non-0; the terminal direction during the period when the count value of the target counter is non-0; the terminal position at the historical moment before the count value of the target counter is 1; the terminal speed at the historical moment before the count value of the target counter is 1; the terminal direction at the historical moment before the count value of the target counter is 1.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: The terminal receives target indication information from the network side device, where the target indication information is used to indicate the name of a first object to which the target AI model applies or an identifier associated with the first object, where the first object is the target timer or the target counter.

9. The method according to any one of claims 1 to 8, characterized in that: Before the terminal performs model inference based on the target AI model and obtains a prediction result, the method further includes: The terminal receives a first signaling from the network side device; the first signaling is used to indicate at least one of the following: Turning on, resuming or activating the AI ​​model function of the target timer; Start, restore or activate the AI ​​model corresponding to the target timer; Open, restore or activate the AI ​​model function of the target counter; Open, restore or activate the AI ​​model corresponding to the target counter; Turning on, restoring or activating the AI ​​model function of the first target behavior; Open, restore or activate the AI ​​model corresponding to the first target behavior; Turning on, restoring or activating the AI ​​model function of the second target behavior; Start, restore or activate the AI ​​model corresponding to the second target behavior.

10. The method according to claim 9, characterized in that The first signaling includes at least one of the following: Identification of AI model functionality; Identification of the AI ​​model; the name of the target timer; an identifier of the target timer; the name of the target counter; an identification of the target counter; an identifier of the first target behavior; An identifier of the second target behavior.

11. The method according to claim 9, characterized in that Before the terminal receives the first signaling from the network side device, the method further includes: The terminal reports capability information to the network side device, where the capability information includes at least one of the following: Whether the AI ​​model function of the timer is available, or whether the AI ​​model corresponding to the timer is available; Whether the AI ​​model function of the counter is available, or whether the AI ​​model corresponding to the counter is available; Whether the AI ​​model function of the first behavior is available, or whether the AI ​​model corresponding to the first behavior is available, wherein the first behavior is a behavior corresponding to a timer timeout; Whether the AI ​​model function of the second behavior is available, or whether the AI ​​model corresponding to the second behavior is available, wherein the second behavior is the behavior corresponding to the counter reaching the maximum count value.

12. The method according to any one of claims 1 to 11, characterized in that: The method further comprises: The terminal receives a second signaling from the network side device, where the second signaling is used to indicate at least one of the following: stop, suspend or deactivate the AI ​​model function of the second object; stop, suspend or deactivate the AI ​​model corresponding to the second object; stop, suspend or deactivate the AI ​​model function of the first target behavior, and stop, suspend or deactivate the AI ​​model corresponding to the first target behavior; stop, suspend or deactivate the AI ​​model function of the second target behavior, and stop, suspend or deactivate the AI ​​model corresponding to the second target behavior; The terminal determines, based on the second signaling, to stop the inference of the AI ​​model corresponding to the second object; The second object includes at least one of the target timer and the target counter.

13. The method according to any one of claims 1 to 12, characterized in that: The method further comprises: The terminal collects target information, and the target information is used for model training; The target information includes at least one of the following: First information, the first information includes at least one of the following: the name of the timer; the identifier associated with the timer; the time information corresponding to the start time of the timer; the time information corresponding to the stop time of the timer; the time information corresponding to the time when the timer times out; the signal quality of the serving cell at the historical moment before the timer is started; the signal quality of the neighboring cell at the historical moment before the timer is started; the signal quality of the target cell at the historical moment before the timer is started; the signal quality of the serving cell during the operation of the timer; the signal quality of the neighboring cell during the operation of the timer; the signal quality of the target cell during the operation of the timer; the terminal position at the historical moment before the timer is started; the terminal speed at the historical moment before the timer is started; the terminal direction at the historical moment before the timer is started; the terminal position during the operation of the timer; the terminal speed during the operation of the timer; the terminal direction at the historical moment during the operation of the timer; the moment when the first behavior occurs, the first behavior is the behavior corresponding to the timer timeout; The second information includes at least one of the following: the name of the counter; the identifier associated with the counter; the time information corresponding to the moment when the count value of the counter is increased by 1; the time information corresponding to the moment when the count value of the counter is reset to 0; the time information corresponding to the moment when the counter reaches the maximum count value; the service cell signal quality during the period when the count value of the counter is non-0; the neighboring cell signal quality during the period when the count value of the counter is non-0; the target cell signal quality during the period when the count value of the counter is non-0; the service cell signal quality at the historical moment before the count value of the counter is 1; the neighboring cell signal quality at the historical moment before the count value of the counter is 1; the target cell signal quality at the historical moment before the count value of the counter is 1; the terminal position during the period when the count value of the counter is non-0; the terminal speed during the period when the count value of the counter is non-0; the terminal direction during the period when the count value of the counter is non-0; the terminal position at the historical moment before the count value of the counter is 1; the terminal speed at the historical moment before the count value of the counter is 1; the terminal direction at the historical moment before the count value of the counter is 1; the moment when the second behavior occurs, the second behavior is the behavior corresponding to the timer timeout.

14. A model prediction processing method, characterized in that: include: The network-side device sends configuration information to the terminal, where the configuration information is used to configure a target artificial intelligence (AI) model, where the target AI model is used for model reasoning to obtain a prediction result, where the prediction result includes a first output or a second output of the target AI model; The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs; The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs; The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

15. The method according to claim 14, characterized in that At least one of the first target behavior and the second target behavior includes at least one of the following: wireless link failure; beam failure; switching failure.

16. The method according to claim 14 or 15, characterized in that After the network side device sends the configuration information to the terminal, the method further includes: The network side device receives the prediction result from the terminal.

17. The method according to any one of claims 14 to 16, characterized in that The method further comprises: The network side device sends target indication information to the terminal, where the target indication information is used to indicate the name of a first object to which the target AI model is applicable or an identifier associated with the first object, where the first object is the target timer or the target counter.

18. The method according to any one of claims 14 to 17, characterized in that After the network side device sends the configuration information to the terminal, the method further includes: The network side device sends a first signaling to the terminal; the first signaling is used to indicate at least one of the following: Turning on, resuming or activating the AI ​​model function of the target timer; Start, restore or activate the AI ​​model corresponding to the target timer; Open, restore or activate the AI ​​model function of the target counter; Open, restore or activate the AI ​​model corresponding to the target counter; Turning on, restoring or activating the AI ​​model function of the first target behavior; Open, restore or activate the AI ​​model corresponding to the first target behavior; Turning on, restoring or activating the AI ​​model function of the second target behavior; Start, restore or activate the AI ​​model corresponding to the second target behavior.

19. The method according to claim 18, characterized in that Before the network side device sends the first signaling to the terminal, the method further includes: The network side device receives capability information from the terminal, where the capability information includes at least one of the following: Whether the AI ​​model function of the timer is available, or whether the AI ​​model corresponding to the timer is available; Whether the AI ​​model function of the counter is available, or whether the AI ​​model corresponding to the counter is available; Whether the AI ​​model function of the first behavior is available, or whether the AI ​​model corresponding to the first behavior is available, wherein the first behavior is a behavior corresponding to a timer timeout; Whether the AI ​​model function of the second behavior is available, or whether the AI ​​model corresponding to the second behavior is available, wherein the second behavior is the behavior corresponding to the counter reaching the maximum count value.

20. The method according to any one of claims 14 to 19, characterized in that The method further comprises: The network-side device sends a second signaling to the terminal, where the second signaling is used to indicate at least one of the following: stop, pause or deactivate the AI ​​model function of the second object; stop, pause or deactivate the AI ​​model corresponding to the second object; stop, pause or deactivate the AI ​​model function of the first target behavior, stop, pause or deactivate the AI ​​model corresponding to the first target behavior; stop, pause or deactivate the AI ​​model function of the second target behavior, stop, pause or deactivate the AI ​​model corresponding to the second target behavior The second object includes at least one of the target timer and the target counter.

21. A model prediction processing device, characterized in that: include: A first receiving module, configured to receive configuration information from a network-side device, wherein the configuration information is used to configure a target artificial intelligence AI model; An inference module, configured to perform model inference based on a target AI model to obtain a prediction result, wherein the prediction result includes a first output or a second output of the target AI model; The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs; The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs; The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

22. A model prediction processing device, characterized in that: include: A first sending module, used to send configuration information to a terminal, wherein the configuration information is used to configure a target artificial intelligence AI model, wherein the target AI model is used for model reasoning to obtain a prediction result, wherein the prediction result includes a first output or a second output of the target AI model; The first output includes at least one of the following: an indication of whether the target timer will time out; the time when the target timer times out; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the first target behavior will occur; the time when the first target behavior occurs; The second output includes at least one of the following: an indication of whether the target counter will reach a maximum count value; the time when the target counter reaches the maximum count value; the predicted signal quality of the serving cell at a future time; the predicted signal quality of the neighboring cell at a future time; the predicted signal quality of the target cell at a future time; an indication of whether the second target behavior will occur; the time when the second target behavior occurs; The first target behavior is a behavior corresponding to the target timer timing out, and the second target behavior is a behavior corresponding to the target counter reaching a maximum count value.

23. A terminal, characterized in that: It includes a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the model prediction processing method as described in any one of claims 1 to 13 are implemented.

24. A network side device, characterized in that: It includes a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the model prediction processing method as described in any one of claims 14 to 20 are implemented.

25. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the model prediction processing method according to any one of claims 1 to 20 are implemented.

Images