WO2025167884A1 - Radio link failure prediction method and apparatus, and communication device and storage medium - Google Patents

Abstract

The present application belongs to the technical field of communications. Disclosed are a radio link failure (RLF) prediction method and apparatus, and a communication device and a storage medium. The RLF prediction method in the embodiments of the present application comprises: a terminal acquiring first information, wherein the first information is used for indicating information related to a first cell; and the terminal inputting the first information into an artificial intelligence (AI) unit for processing, so as to obtain an RLF prediction result of the first cell.

Description

Wireless link failure prediction method, device, communication equipment and storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese patent application number 202410165804.0, filed on February 5, 2024, entitled “Prediction method, device, communication equipment and storage medium for wireless link failure,” the entire contents of which are incorporated by reference into this application.

Technical Field

The present application belongs to the field of communication technology, and specifically relates to a method, apparatus, communication equipment, and storage medium for predicting wireless link failure.

Background Art

Radio Link Failure (RLF) refers to the situation in a communication system where the wireless signal transmission between the transmitter and receiver is interrupted or terminated due to poor signal quality, interference, equipment failure, etc. Currently, when the terminal is in the Radio Resource Control Connected (RRC_CONNECTED) state, there are several ways to trigger RLF:

Method 1: T310 timer expiration: During the Radio Link Monitoring (RLM) process, the reported "out-of-sync" condition is used to determine if RLF has occurred, and the reported "in-sync" condition is used to determine if RLF has recovered. The specific process is as follows:

When N310 "out-of-sync" are reported consecutively, the T310 timer is started;

If N311 "in-sync" are reported consecutively while the T310 timer is running, stop the T310 timer.

When the T310 timer times out, it is considered that RLF has occurred and the terminal side triggers the RRC connection re-establishment process.

Among them, N310, N311 and T310 are RLF detection configuration parameters configured in the network.

Method 2: When RLC uses AM, the maximum number of retransmissions exceeds the threshold;

Method 3: Random access fails;

Method 4: T312 timer timeout: To shorten the RLF determination time, the T312 timer, which is shorter than T310, is introduced. Its working process is as follows:

After the terminal starts the T310 timer, during the operation of T310, if the terminal measures that the handover event meets the duration of the continuous trigger time (Time to Trigger, TTT), the terminal starts the T312 timer and triggers a measurement report (attempting to initiate a handover); if the handover is not triggered until the T312 timer expires (due to channel conditions, the terminal does not receive the handover command sent by the base station), and the T310 timer has not expired at this time, the terminal immediately declares the radio link failure (there is no need to wait until T310 times out before declaring the radio link failure), and performs the RRC re-establishment process to restore the service connection as soon as possible.

Among them, the occurrence of RLF will cause the terminal to disconnect from the network, resulting in data interruption; however, although the terminal can reestablish the cell and connect to other cells when RLF occurs, the reconstruction process is time-consuming, resulting in a longer duration of data interruption, affecting the service performance of the terminal.

Summary of the Invention

The embodiments of the present application provide a method, apparatus, communication device, and storage medium for predicting a radio link failure to solve the problem that RLF causes data interruption in a terminal, thereby affecting the service performance of the terminal.

In a first aspect, a method for predicting radio link failure is provided, the method comprising:

The terminal obtains first information, where the first information is used to indicate relevant information of the first cell;

The terminal inputs the first information into an artificial intelligence (AI) unit for processing to obtain a radio link failure (RLF) prediction result of the first cell.

In a second aspect, a method for predicting radio link failure is provided, the method comprising:

The network side device receives the radio link failure (RLF) prediction result sent by the terminal, where the RLF prediction result is obtained by an artificial intelligence (AI) unit.

In a third aspect, a device for predicting radio link failure is provided, which is applied to a terminal, and the device includes:

an acquiring module, configured to acquire first information, wherein the first information is used to indicate relevant information of the first cell;

A prediction module is used to input the first information into an artificial intelligence AI unit for processing to obtain a radio link failure RLF prediction result of the first cell.

In a fourth aspect, a device for predicting radio link failure is provided, which is applied to a network-side device. The method includes:

The first receiving module is used to receive the radio link RLF prediction result sent by the terminal, where the RLF prediction result is obtained by an artificial intelligence AI unit.

In a fifth aspect, a communication 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 first aspect or the second aspect are implemented.

In a sixth aspect, a communication device is provided, including a processor and a communication interface;

When the communication device is a terminal, the processor is configured to:

Acquire first information, where the first information is used to indicate relevant information of the first cell;

Inputting the first information into an artificial intelligence (AI) unit for processing to obtain a radio link failure (RLF) prediction result of the first cell;

When the communication device is a network-side device, the communication interface is used to:

A radio link failure (RLF) prediction result sent by a receiving terminal is obtained by an artificial intelligence (AI) unit.

In a seventh 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 or the second aspect are implemented.

In an eighth aspect, a wireless link failure prediction 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.

In a ninth 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 configured to run a program or instruction to implement the method described in the first aspect or the second aspect.

In a tenth 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 the second aspect.

In an eleventh aspect, an embodiment of the present application provides a device for predicting a wireless link failure, which is used to execute the steps of the method for predicting a wireless link failure as described in the first aspect or the second aspect.

In the embodiment of the present application, the terminal can obtain first information indicating relevant information of the first cell, thereby inputting the first information into the AI unit and outputting the RLF prediction result of the first cell. It can be seen that in the embodiment of the present application, the terminal can predict RLF through the AI unit, so that the terminal can promptly detect the RLF, thereby facilitating timely resolution of the RLF, thereby avoiding the time-consuming cell reestablishment until the RLF actually occurs, thereby reducing the impact of data interruption caused by the RLF on the terminal service.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a block diagram of a wireless communication system to which embodiments of the present application may be applied;

FIG2 is a flow chart of a method for predicting wireless link failure in an embodiment of the present application;

FIG3 is a schematic diagram of a neural network in an embodiment of the present application;

FIG4 is a schematic diagram of neurons in a neural network according to an embodiment of the present application;

FIG5 is a schematic diagram of an artificial intelligence (AI)/machine learning (ML) framework in an embodiment of the present application;

FIG6 is a flowchart of another method for predicting wireless link failure in an embodiment of the present application;

FIG7 is a structural block diagram of a device for predicting wireless link failure according to an embodiment of the present application;

FIG8 is a structural block diagram of another apparatus for predicting wireless link failure in an embodiment of the present application;

FIG9 is a structural block diagram of a communication device in an embodiment of the present application;

FIG10 is a block diagram of a terminal in an embodiment of the present application;

FIG11 is a structural block diagram of a network-side device in an embodiment of the present application.

Specific embodiments

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

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

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

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 example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as ^6th Generation (6G) communication systems.

FIG1 shows a block diagram of a wireless communication system applicable to embodiments of the present application. The wireless communication system includes a terminal 11 and a network-side device 12 . Among them, the terminal 11 can be a mobile phone, tablet computer (Tablet Personal Computer), laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile Internet device (MID), augmented reality (AR), virtual reality (VR) equipment, robot, wearable device (Wearable Device), flight vehicle, vehicle user equipment (VUE), shipborne equipment, pedestrian user equipment (PUE), smart home (home appliances with wireless communication function, such as refrigerator, TV, washing machine or furniture, etc.), game console, personal computer (PC), ATM or 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 called 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 can be called Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, base The Basic Service Set (BSS), Extended Service Set (ESS), home Node B (HNB), home evolved Node B, 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 embodiments of the present application, only the base station in the NR system is introduced as an example, and the specific type of the base station is not limited.

The following describes in detail the method for predicting wireless link failure provided by the embodiments of the present application through some embodiments and their application scenarios in conjunction with the accompanying drawings.

2 , an embodiment of the present application provides a method for predicting radio link failure, which may include the following steps 201 to 202:

Step 201: The terminal obtains first information.

The first information is used to indicate relevant information of the first cell; the first cell may include one or more cells; the first cell may include at least one of a serving cell, a neighboring cell, a switching candidate cell, and a switching target cell.

In addition, it should be noted that the first information is input into the AI unit for processing to obtain the RLF prediction result of the first cell. Therefore, the first cell can be called a predicted cell.

Optionally, the first information includes at least one of the following items A-1 to A-4:

Item A-1: historical signal quality of the first cell;

Item A-2: current signal quality of the first cell;

The signal quality in item A-1 or item A-2 may include at least one of cell-level signal quality and beam-level signal quality; the signal quality may be represented by at least one of RSRP, RSRQ, and SINR;

Item A-3: first auxiliary information related to the mobility of the terminal, where the first auxiliary information may include at least one of the speed, position, and moving direction of the terminal;

Item A-4: Second auxiliary information related to the network side device, which may include at least one of the location, beam configuration, and beam width of the network side device (such as base station/cell/transmit-receive point (TRP)).

Step 202: The terminal inputs the first information into an artificial intelligence (AI) unit for processing to obtain a radio link failure (RLF) prediction result of the first cell.

The AI unit may also be referred to as an AI model, 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 unit may also refer to a processing unit capable of implementing specific algorithms, formulas, processing procedures, capabilities, etc. related to AI, or the AI unit may be a processing method, algorithm, function, module or unit for a specific data set, or the AI unit may be a processing method, algorithm, function, module or unit running on AI/ML related hardware such as a graphics processing unit (GPU), a neural network processor (NPU), a tensor processing unit (TPU), or an application specific integrated circuit (ASIC), and this application does not make specific limitations on this. Optionally, the specific data set includes at least one of the input and output of the AI unit/AI model.

In addition, there are many ways to implement the AI unit, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. The embodiments of this application use neural networks as an example for illustration, but do not limit the specific type of AI unit. A schematic diagram of the structure of a simple neural network is shown in Figure 3.

Furthermore, neural networks are composed of neurons, as shown in Figure 4. In Figure 4, a ₁ , a ₂ , … a _K represent inputs, w represents weights (i.e., multiplicative coefficients), b represents biases (i.e., additive coefficients), and σ(.) represents the activation function. Common activation functions include sigmoid (which maps variables to between 0 and 1), tanh (a shift and contraction of sigmoid), and rectified linear units (ReLUs).

The parameters of a neural network can be optimized using a gradient optimization algorithm. A gradient optimization algorithm is a type of algorithm that minimizes or maximizes an objective function (sometimes also called a loss function), which is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, a neural network model f(.) can be constructed. Based on the input x, the predicted output f(x) can be obtained, and the difference between the predicted value and the true value (f(x)-Y) can be calculated. This is the loss function. The optimization goal of the gradient optimization algorithm is to find the appropriate w (i.e., weight) and b (i.e., bias) to minimize the value of the aforementioned loss function. The smaller the loss value, the closer the model is to the true situation.

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

In addition, common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method (Momentum), Nesterov (the name of the inventor, specifically stochastic gradient descent with momentum) adaptive gradient descent (ADAptive GRADient descent, Adagrad), Adagrad's extended algorithm (Adadelta), root mean square prop (RMSprop), adaptive momentum estimation (Adaptive Moment Estimation, Adam), etc.

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

In addition, the main process of an AI/ML framework for air interface AI can be shown in Figure 5. Among them, data collection is used to provide input data for model training, management, and inference;

Model Training: This is used to perform AI/ML model training, validation, and testing. It is also responsible for data preparation, i.e., data preprocessing and conversion into specific formats.

Management: used for model selection/activation/deactivation/switching/rollback, etc.

Inference: used to provide the output after applying AI/ML models or AI/ML functions;

Model Storage: used to save trained/updated models;

Model Transfer/Delivery: Used to deliver AI/ML models to inference function nodes.

It should be noted that in an embodiment of the present application, the AI unit is used to perform RLF prediction, that is, the above-mentioned relevant information of the first cell (for example, at least one item of A-1 to A-4 mentioned above) is input into the AI unit for processing, and the RLF prediction result of the first cell can be obtained.

As can be seen from steps 201 to 202 above, in this embodiment of the present application, the terminal can obtain first information indicating relevant information about the first cell, thereby inputting the first information into the AI unit and outputting an RLF prediction result for the first cell. Thus, in this embodiment of the present application, the terminal can predict RLF through the AI unit, enabling the terminal to promptly detect and resolve the RLF. This avoids the time-consuming process of delaying cell reestablishment until an RLF actually occurs, thereby reducing the impact of data interruption caused by the RLF on terminal services.

Optionally, the RLF prediction result includes at least one of the following items B-1 to B-4:

Item B-1: first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell;

Item B-2: Future time information of when the RLF occurs in the first cell; the future time information may be a time point (i.e., a moment) or a time period; and the future time information of when the RLF occurs in the first cell may be represented based on one of the following methods:

Method 1: NR air interface time based on the System Frame Number (SFN)/time slot/Orthogonal Frequency Division Multiplexing symbol (OFDM symbol) sequence number;

Method 2: Absolute time based on the 5G system clock;

Method 3: Time based on satellite timing.

Item B-3: The probability of RLF occurring in the first cell.

The probability can be expressed in one of the following ways:

Method 1: Use N bits to represent X% to Y%. For example, 2 bits can be used to represent 25% to 100%, which can represent 25%, 50%, 75%, and 100%.

Method 2: Expressed using a CHOICE structure; for example, there are four options: 25%, 50%, 75%, and 100%, and the RLF prediction reports one of them.

Item B-4: Causes of RLF.

Exemplarily, the terminal may report at least one of B-1 to B-3 above to the serving cell; or, if the terminal performs cell reconstruction, after the reconstruction, the terminal may report at least one of B-1 to B-4 above to the network side device.

Optionally, in the above item B-4, the cause of the RLF includes at least one of the following items L-1 to L-3:

L-1: The terminal predicts that the first timer will time out;

The first timer may be one of the T310 timer and the T312 timer, or may be a new timer.

L-2: The terminal predicts that random access fails;

Item L-3: The terminal predicts that the number of RLC ARQ retransmissions reaches the maximum number; the maximum number of retransmissions can be configured by the network side equipment or agreed upon by the protocol.

Optionally, the method further includes:

When at least one first condition among the following C-1 to C-12 is satisfied, the terminal facilitates the AI unit to perform RLF prediction:

Item C-1: Arrival of the first cycle;

That is, the AI unit can periodically predict RLF, wherein the first period can be configured by the network side device or agreed upon by the protocol.

Item C-2: the cell signal quality of the first cell is less than or equal to a first threshold;

Exemplarily, when the cell signal quality of the first cell is less than or equal to a first threshold, the terminal may use the AI unit to perform RLF prediction on the first cell; wherein the first threshold may be configured by a network side device or agreed upon by a protocol.

Item C-3: The best beam signal quality of the first cell is less than or equal to a second threshold;

Exemplarily, when the signal quality of the optimal beam of the first cell is less than or equal to a second threshold, the terminal can use the AI unit to perform RLF prediction on the first cell; wherein, the second threshold can be configured by the network side device or agreed upon by the protocol.

Item C-4: Trigger or enter radio link monitoring RLM measurement relaxation;

Exemplarily, when the terminal triggers or enters RLM measurement relaxation, the AI unit may be used to perform RLF prediction.

Among them, in the RRC connected state, when the discontinuous reception (C-DRX) period in the connected state is less than or equal to 40ms, if the terminal determines that the conditions for measurement relaxation are met based on the measurement relaxation criteria configured by the network, then the terminal can trigger or enter RLM measurement relaxation, that is, reduce RLM measurements, that is, increase the measurement interval, and reduce the number of measurement samples, thereby reducing power consumption and reducing the impact on service delay.

The measurement relaxation criteria include a low mobility determination criterion and a cell quality determination criterion.

The cell quality judgment criterion is based on the quality of the wireless link, that is, the Signal to Interference plus Noise Ratio (SINR). When the SINR is higher than Qin+offset, the system enters RLM relaxation. When the terminal triggers out-of-sync or starts T310, it exits RLM relaxation.

The low mobility criterion is the network-configured signal quality evaluation duration and change value threshold. When the signal quality change of the terminal in the serving cell within a period of time is less than the change value threshold, the terminal is considered to meet the "low mobility" criterion.

In addition, the terminal determines the RLM relaxation state according to the two configured criteria and reports the relaxation state to the network side.

It should be noted that after the terminal triggers or enters RLM measurement relaxation, RLF is more likely to occur due to reduced measurements. Therefore, in this case, the terminal can perform RLF prediction through the AI unit.

Item C-5: N310 reaches a first value, where N310 represents the number of consecutive out-of-sync events.

For example, when N310 reaches a first value (i.e., when the terminal continuously receives the first value of "out-of-sync"), the terminal can use the AI unit to perform RLF prediction. The first value can be configured by the network side device or agreed upon by the protocol.

It should be noted that the terminal can determine the Qout and Qin threshold values, and compare the measurement results of the radio link monitoring reference signal (RLM-RS) with the threshold values. When the measurement result is worse than the Qout threshold value, an "out-of-sync" event is reported; when the measurement result is better than the Qin threshold value, an "in-sync" event is reported.

Qin represents the threshold value at which the terminal's downlink channel quality is good enough for reliable transmission. This value is actually converted into the channel quality when the block error rate (BLER) detected on the Physical Downlink Control Channel (PDCCH) reaches BLER _in .

Qout indicates the threshold value at which the downlink channel quality of the terminal is no longer able to perform reliable transmission, which is actually converted into the channel quality when the BLER detected on the PDCCH reaches BLER _out .

Exemplarily, the configurations of BLER _in and BLER _out are shown in Table 1.

Table 1 BLER _in and BLER _out configuration examples

In addition, RLM-RS can be a synchronization signal block (SSB), a channel state information reference signal (CSI-RS), or a mixture of SSB and CSI-RS.

Item C-6: First timer starts;

The first timer may be one of the T310 timer and the T312 timer, or a new timer. It should be noted that when the first timer is a new timer, after the first timer times out, the terminal determines that RLF occurs and triggers RRC reestablishment.

Exemplarily, when the first timer starts, the terminal may start the AI unit to perform RLF prediction.

Item C-7: The timing duration of the first timer reaches the first duration;

For example, when the first timer reaches a first duration, the terminal may use the AI unit to perform RLF prediction, wherein the first duration may be configured by a network-side device or agreed upon by a protocol.

C-8: The number of random access RACHs reaches the third threshold;

For example, when the number of random access attempts by the terminal reaches a third threshold, the terminal may use the AI unit to perform RLF prediction, wherein the third threshold may be configured by a network-side device or agreed upon by a protocol.

Item C-9: The number of RLC ARQ retransmissions at the radio link control layer reaches the fourth threshold;

For example, when the terminal's RLC ARQ count reaches a fourth threshold (i.e., when the RETX_COUNT corresponding to a Radio Link Control Service Data Unit (RLC SDU) reaches the fourth threshold), the terminal can use the AI unit to perform RLF prediction. The fourth threshold can be configured by network-side devices or agreed upon by the protocol. RETX_COUNT represents a counter maintained by the RLC SDU that counts the number of retransmissions of an RLC SDU or RLC SDU segment.

Item C-10: Meeting the radio resource management RRM measurement reporting conditions;

For example, when the terminal meets the RRM measurement reporting conditions, the terminal can use the AI unit to perform RLF prediction. The RRM measurement reporting conditions can be configured by the network side device or agreed upon by the protocol.

Among them, the RRM measurement configuration mainly consists of measurement object, reporting configuration and measurement ID;

Measurement Object: the frequency point to be measured;

Report Configuration (ReportConfig): Associated reporting criteria (periodic/event-triggered), reference signal type (SSB/CSI-RS), measurement reporting quantity (any combination of Reference Signal Received Power (RSRP)/Reference Signal Received Quality (RSRQ)/SINR); whether to report beam measurement results, the maximum number of reportable beams, etc.

Measurement identifier (measId): used to associate a measurement object with a reporting configuration. A measurement object can be associated with multiple reporting configurations, and a reporting configuration can be associated with multiple measurement objects.

In addition, the reporting configuration can associate events to trigger reporting. The event associations defined in NR are shown in Table 2.

Table 2 Trigger event examples

Taking the above A3 event as an example, the meanings of the parameters of the entry and exit conditions are as follows:
Mn: indicates the neighboring cell measurement result, without considering any offset;
Ofn: indicates the specific offset of the neighboring measurement object;
Ocn: indicates the neighboring cell-level specific offset;
Mp: indicates the measurement result of the primary serving cell (SpCell), without considering any offset;
Ofp: represents the SpCell measurement object specific offset;
Ocp: indicates the SpCell cell-level specific offset;
Hys: represents the hysteresis parameter of the event;
Off: Indicates the offset parameter of the event.

It should be noted that if the reporting type is event-triggered reporting, in order to avoid ping-pong switching, the base station configures the timeToTrigger parameter for each event. When the L3 filtered signal quality of one or more candidate cells within the timeToTrigger time meets the entry conditions of the event, the RRM measurement report is triggered.

Item C-11: Trigger RRM measurement reporting;

Exemplarily, when the terminal triggers RRM measurement reporting, the terminal may use the AI unit to perform RLF prediction.

Item C-12: The terminal receives second indication information sent by the network side device, and the second indication information is used to instruct the use of the AI unit to perform RLF prediction.

Exemplarily, when the network side device instructs the terminal to use the AI unit for RLF prediction, the terminal can use the AI unit for RLF prediction, that is, the terminal can turn on the AI unit for RLF prediction according to the instruction of the network side device.

It should be noted that the second indication information can be associated with the terminal and the downlink bandwidth part (DL BWP) of the cell, that is, at least one terminal can be configured with a second indication information respectively, so that the terminal configured with the second indication information can perform RLF prediction for any activated DL BWP; at least one cell can also be configured with a second indication information, so that the terminal enables RLF prediction for the designated cell, such as the serving cell or the target cell; at least one DL BWP can also be configured with a second indication information, so that RLF prediction can be performed only when the DL BWP currently activated by the terminal is the designated DL BWP.

Optionally, the method further includes:

When at least one second condition among the following D-1 to D-10 is satisfied, the terminal stops the AI unit from performing RLF prediction:

Item D-1: the cell signal quality of the first cell is greater than or equal to a fifth threshold;

Exemplarily, when the cell signal quality of the first cell is greater than or equal to a fifth threshold, the terminal may stop the AI unit from performing RLF prediction on the first cell; wherein the fifth threshold may be configured by a network side device or agreed upon by a protocol.

Item D-2: The optimal beam signal quality of the first cell is greater than or equal to a sixth threshold;

Exemplarily, when the signal quality of the optimal beam of the first cell is greater than or equal to the second threshold, the terminal can stop the AI unit from performing RLF prediction on the first cell; wherein, the sixth threshold can be configured by the network side device or agreed upon by the protocol.

Item D-3: Exit or stop RLM measurement relaxation;

Exemplarily, when the terminal exits or stops RLM measurement relaxation, the AI unit may be stopped from performing RLF prediction.

D-4: N311 reaches the second value, N311 represents the number of consecutive synchronizations;

For example, when N311 reaches a second value (i.e., when the terminal continuously receives the second value "in-sync"), the terminal can stop the AI unit from performing RLF prediction. The second value can be configured by the network side device or agreed upon by the protocol.

Item D-5: The terminal reports the RLF prediction result to the network-side device;

Exemplarily, after the terminal reports the RLF prediction result to the network-side device, the AI unit may stop predicting RLF.

D-6: The first timer stops running;

The first timer may be one of the T310 timer and the T312 timer, or may be a new timer.

Exemplarily, when the first timer stops running, the terminal may stop the AI unit from performing RLF prediction.

D-7: Triggering RLF;

Exemplarily, when the terminal triggers RLF, the AI unit may be stopped from performing RLF prediction.

D-8: One of the following occurs: cell handover, reestablishment, or redirection;

For example, when a cell handover, reestablishment, or redirection occurs in the terminal, the AI unit may be stopped from performing RLF prediction.

Item D-9: The terminal receives an ACK corresponding to a radio link control layer protocol service data unit RLC SDU;

For example, when the terminal receives the ACK corresponding to the RLC SDU, the AI unit can stop performing RLF prediction.

Item D-10: Random access successful.

Exemplarily, when the terminal successfully completes random access, the AI unit may be stopped from performing RLF prediction.

Optionally, the method further includes:

When at least one third condition among the following E-1 to E-4 is met, the terminal reports the RLF prediction result to the network-side device:

Item E-1: The second period has arrived; this means that the terminal can periodically report RLF prediction results to the network device. This second period can be the same as or different from the first period of RLF prediction performed by the AI unit described above. This second period can be configured by the network device or agreed upon by the protocol.

Item E-2: The terminal predicts that an RLF will occur; that is, the terminal may report the RLF prediction result to the network-side device when predicting that an RLF will occur.

Item E-3: The terminal predicts that the probability of RLF occurrence is greater than or equal to the seventh threshold; that is, the terminal may report the RLF prediction result to the network-side device when the terminal predicts that the probability of RLF occurrence is greater than the seventh threshold; the seventh threshold may be configured by the network-side device or agreed upon by the protocol.

Item E-4: The terminal triggers RRM measurement reporting; that is, when the terminal triggers RRM measurement reporting, the terminal can report the RLF prediction result to the network side device; wherein, the RRM measurement reporting can be a periodic RRM measurement reporting or an event-triggered RRM measurement reporting; for example, the RLF prediction result is reported in the measurement report corresponding to the measurement identifier that triggers the measurement reporting.

Optionally, the RLF prediction result is carried in at least one of the following G-1 to G-3:

Item G-1: RRM measurement report; that is, the RLF prediction result can be carried in an existing measurement report (MeasurementReport), and the measurement report includes the cell signal quality or beam signal quality of at least one cell among the serving cell, the neighboring cell, and the first cell;

The RLF prediction result is carried in the RRM measurement report, so that the RLF prediction result can be reported to the serving cell of the terminal, so that the serving cell can determine whether cell switching is required according to the RLF prediction result.

G-2: RLF report;

Item G-3: Radio Resource Control RRC reconfiguration completion message.

Among them, the RLF prediction result is carried in the RLF report and RRC reconfiguration completion message, so that the RLF prediction result can be reported to the target cell, so that the target cell can learn the cause of the RLF from the RLF prediction result, so that the target cell can perform relevant configuration for the terminal, thereby reducing the probability of subsequent RLF.

Optionally, the method further comprises at least one of the following H-1 to H-2:

Item H-1: The terminal performs at least one of a first behavior and a second behavior based on the RLF prediction result, wherein the first behavior includes determining that an RLF occurs and triggering cell reestablishment, and the second behavior includes reporting the RLF prediction result to a network-side device;

As can be seen from item H-1, the terminal can determine whether to declare RLF and trigger reconstruction based on the RLF prediction result.

In one embodiment, the terminal performs a first behavior (i.e., declaring RLF and triggering cell reestablishment) or a second behavior (i.e., reporting the RLF prediction result to a network-side device) based on the RLF prediction result, including one of the following:

If the RLF prediction result satisfies a fourth condition, the terminal performs at least one of the first behavior and the second behavior, the fourth condition including that the RLF prediction result indicates that RLF will occur, or the RLF prediction result indicates that the probability of RLF occurrence is greater than or equal to an eighth threshold;

If the RLF prediction result satisfies the fourth condition and the target duration is less than a ninth threshold, the terminal performs the first action, where the target duration is the duration between the future time point of RLF occurrence indicated by the RLF prediction result and the current time point;

When the RLF prediction result satisfies the fourth condition and the target duration is greater than or equal to the ninth threshold, the terminal performs the second behavior.

From this, it can be seen that the terminal can determine whether to execute at least one of the first and second behaviors based on the prediction of whether RLF will occur; it can also determine whether to execute at least one of the first and second behaviors based on the probability of predicting RLF; it can also determine whether to execute the first or second behavior based on the distance between the time point when the RLF is predicted to occur and the current time point.

It should be noted that the conditions for the above-mentioned terminal to execute the first behavior or the second behavior (ie, the above-mentioned various situations of executing the first behavior or the second behavior) can be configured by the network side device or agreed upon by the protocol.

The ninth threshold may be configured by a network-side device or agreed upon by a protocol.

In addition, when conditional handover (CHO) or layer one layer two triggered mobility (L1/L2-triggered mobility, LTM) candidate cells are configured, and attempt conditional reconfiguration (attemptCondReconfig) or attempt LTM switching (attemptLTM-Switch) is configured, if the first cell selected in the cell selection process after RLF triggered by the RLF prediction result is a candidate cell, the terminal can switch to the candidate cell.

Item H-2: The terminal determines whether to start a first timer according to the RLF prediction result.

As can be seen from item H-2, the terminal can determine whether to start the first timer based on the RLF prediction result. The first timer can be one of the T310 timer and the T312 timer, or a new timer.

In one embodiment, the terminal determines, according to the RLF prediction result, whether to start a first timer, including:

When the RLF prediction result indicates that RLF will occur, or when the RLF prediction result indicates that the probability of RLF occurring is greater than or equal to a tenth threshold, the terminal starts a first timer.

It can be understood that, when the RLF prediction result indicates that RLF will not occur, or when the RLF prediction result indicates that the probability of RLF occurring is less than the tenth threshold, the terminal does not start the first timer.

It can be seen from this that the terminal can determine whether to start the first timer based on whether the RLF is predicted to occur; or can determine whether to start the first timer based on the predicted probability of the RLF.

The tenth threshold may be configured by a network-side device or agreed upon by a protocol.

Optionally, the method further includes:

The terminal receives at least one of the following items J-1 to J-14 configured by the network side device:

Item J-1: The number of times the AI unit is used to continuously predict RLF; that is, the network-side device can configure the terminal to enable the AI unit for RLF prediction, and the number of times RLF prediction needs to be performed continuously.

Item J-2: Identification information of the AI unit; that is, the network-side device can instruct the terminal to use identification information of the AI unit for RLF prediction.

Optionally, the identifier of the AI unit 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 unit, or an identifier of a specific scenario, environment, channel feature, or device related to the AI/ML, or an identifier of a function, feature, capability, or module related to the AI/ML. This application does not specifically limit this.

Item J-3: Functional information of the AI unit; that is, the network-side device can instruct the terminal to use functional information of the AI unit for RLF prediction, such as the function ID; among which, AI functionality: that is, an AI algorithm function, which can include multiple AI Models.

Item J-4: The first information used as the input of the AI unit; that is, the network-side device can instruct the terminal to use the input content of the AI unit for RLF prediction.

Item J-5: Output of the AI unit; that is, the network-side device can instruct the terminal to use the output content of the AI unit for RLF prediction.

Item J-6: The model structure of the AI unit; that is, the network-side device can instruct the terminal to use the model structure of the AI unit for RLF prediction.

Item J-7: Model parameters of the AI unit; that is, the network-side device can instruct the terminal to use the model parameters of the AI unit for RLF prediction.

Item J-8: The first condition for using the AI unit to perform RLF prediction; that is, the network side device can instruct the terminal to turn on the first condition of the AI unit for performing RLF prediction.

The first condition may include at least one of the following:

The first cycle arrives;

The cell signal quality of the first cell is less than or equal to a first threshold;

The optimal beam signal quality of the first cell is less than or equal to a second threshold;

Trigger or enter radio link monitoring RLM measurement relaxation;

N310 reaches a first value, where N310 represents the number of consecutive times of being out of sync;

The first timer starts;

The timing duration of the first timer reaches a first duration;

The number of random access RACH times reaches a third threshold;

The number of RLC ARQ retransmissions at the radio link control layer reaches the fourth threshold;

Meet the radio resource management RRM measurement reporting conditions;

Trigger RRM measurement reporting;

The terminal receives second indication information sent by the network side device, where the second indication information is used to instruct the use of the AI unit to perform RLF prediction.

Item J-9: The second condition for stopping the AI unit from performing RLF prediction; that is, the network side device can instruct the terminal to stop the second condition for the AI unit used for RLF prediction.

The second condition may include at least one of the following:

The cell signal quality of the first cell is greater than or equal to a fifth threshold;

The optimal beam signal quality of the first cell is greater than or equal to a sixth threshold;

Exit or stop RLM measurement relaxation;

N311 reaches a second value, N311 indicating the number of consecutive synchronizations;

The terminal reports the RLF prediction result to the network side device;

The first timer stops running;

Triggering RLF;

One of the following occurs: cell handover, reestablishment, or redirection;

The terminal receives a positive acknowledgement ACK corresponding to a radio link control layer protocol service data unit RLC SDU;

Random access successful.

Item J-10: Instruction for reporting the RLF prediction result; that is, the network-side device may instruct the terminal to report the RLF prediction result.

Item J-11: The third condition for reporting the RLF prediction result; that is, the condition under which the network-side device can instruct the terminal to report the RLF prediction result.

The third condition may include at least one of the following:

The second cycle arrives;

The terminal predicts that RLF will occur;

The terminal predicts that a probability of RLF occurrence is greater than or equal to a seventh threshold;

The terminal triggers RRM measurement reporting.

Item J-12: The content included in the RLF prediction result; that is, the network-side device can instruct the terminal to report which information related to the RLF prediction result.

Item J-13: Instruction information for instructing to execute the first behavior or the second behavior according to the RLF prediction result, the first behavior includes determining that an RLF occurs and triggering cell reconstruction, and the second behavior includes reporting the RLF prediction result to the network side device; that is, the network side device can instruct the terminal to execute the first behavior or the second behavior according to the RLF prediction result.

Item J-14: The conditions for executing the first behavior or the second behavior according to the RLF prediction result, that is, the network side device can instruct the terminal to execute the first behavior or the second behavior according to the RLF prediction result, that is, instruct the terminal under which specific circumstances the RLF prediction result can execute the first behavior or the second behavior. In this way, the terminal can determine whether to execute the first behavior or the second behavior based on the conditions indicated by the network side device. For example, the network side device configures the terminal to perform operations when it predicts that RLF will occur or the RLF probability is greater than the ninth threshold, such as: reporting the RLF prediction result or declaring RLF by itself and triggering reconstruction.

Optionally, the method further includes:

After obtaining the RLF prediction result, the terminal starts a second timer and does not use the AI unit to perform RLF prediction while the second timer is running.

From this, it can be seen that the network side device can configure a second timer, and the terminal starts the second timer after performing RLF prediction, and the terminal cannot perform RLF prediction reasoning during the running of the second timer.

6 , an embodiment of the present application provides a method for predicting radio link failure. The method may include the following step 601:

Step 601: The network-side device receives a radio link failure (RLF) prediction result sent by the terminal.

The RLF prediction result is obtained through an artificial intelligence (AI) unit.

In addition, after the terminal obtains the first information related to the first cell, it can input the first information into the AI unit for processing to obtain the RLF prediction result of the first cell, and then report the RLF prediction result to the network side device.

Optionally, the first information includes at least one of the following items A-1 to A-4:

Item A-1: historical signal quality of the first cell;

Item A-2: current signal quality of the first cell;

Item A-3: first auxiliary information related to the mobility of the terminal;

Item A-4: Second auxiliary information related to the network side device.

The relevant explanations of items A-1 to A-4 can be found in the previous text and will not be repeated here.

It should be noted that in an embodiment of the present application, the AI unit is used to perform RLF prediction, that is, the above-mentioned relevant information of the first cell (for example, at least one item of A-1 to A-4 mentioned above) is input into the AI unit for processing, and the RLF prediction result of the first cell can be obtained.

It can be seen from the above step 601 that in an embodiment of the present application, the terminal can predict RLF through the AI unit, and thereby report the RLF prediction result to the network side device, so that the network side device can detect RLF in time, thereby facilitating timely resolution of RLF, so as to avoid wasting a long time until cell reconstruction actually occurs, thereby reducing the impact of data interruption caused by RLF on terminal services.

Optionally, the RLF prediction result includes at least one of the following items B-1 to B-4:

Item B-1: first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell;

Item B-2: future time information of RLF occurrence in the first cell;

Item B-3: probability of RLF occurring in the first cell;

Item B-4: Causes of RLF.

For the relevant explanations of items B-1 to B-4, please refer to the above text and will not be repeated here.

Optionally, in the above item B-4, the cause of the RLF includes at least one of the following items L-1 to L-3:

L-1: The terminal predicts that the first timer will time out;

L-2: The terminal predicts that random access fails;

Item L-3: The terminal predicts that the number of RLC ARQ retransmissions has reached the maximum number.

Among them, the relevant explanations of items L-1 to L-3 here can be found in the previous article and will not be repeated here.

Optionally, the RLF prediction result is carried in at least one of the following G-1 to G-3:

Item G-1: RRM measurement report;

G-2: RLF report;

Item G-3: Radio Resource Control RRC reconfiguration completion message.

For the relevant explanations of items G-1 to G-3, please refer to the above text and will not be repeated here.

Optionally, the method further includes:

The network side device sends at least one of the following configurations J-1 to J-15 to the terminal:

Item J-1: The number of consecutive RLF predictions using the AI unit;

Item J-2: Identification information of the AI unit;

Item J-3: Functional information of the AI unit;

Item J-4: Input to the AI unit;

Item J-5: Output of the AI unit;

Item J-6: Model structure of the AI unit;

Item J-7: Model parameters of the AI unit;

Item J-8: First condition for performing RLF prediction using the AI unit;

Item J-9: A second condition for stopping the AI unit from performing RLF prediction;

Item J-10: Instructions for reporting the RLF forecast results;

Item J-11: The third condition for reporting the RLF forecast results;

Item J-12: Contents of the RLF prediction results;

Item J-13: instruction information for instructing to perform a first action or a second action based on the RLF prediction result, the first action including determining that an RLF occurs and triggering cell reestablishment, and the second action including reporting the RLF prediction result to a network-side device;

Item J-14: a condition for executing the first action or the second action based on the RLF prediction result;

For the relevant explanations of items J-1 to J-14, please refer to the above text and will not be repeated here.

Item J-15: Second indication information, the second indication information is used to indicate the use of the AI unit for RLF prediction; that is, the network side device can instruct the terminal to use the AI unit for RLF prediction, so that the terminal can turn on the AI unit for RLF prediction according to the instruction of the network side device.

In summary, the specific implementation of the method for predicting radio link failure in the embodiment of the present application may be as described in any one of the following implementations one to three.

Implementation method 1 includes the following steps 1.1 to 1.3:

Step 1.1: The terminal receives a network configuration, where the network configuration includes at least one of the following:

RLF forecast indication;

Conditions for enabling the AI unit for predicting RLF;

Conditions for stopping the AI unit used to predict RLF;

Identification of the AI unit used to predict RLF;

Functional identification of AI units used to predict RLF;

Predict the inputs to the AI unit used by RLF;

Predict the output of the AI unit used by RLF;

Model structure of AI unit used to predict RLF;

Predict model parameters of the AI unit used by RLF;

Instructions for reporting RLF prediction results;

The RLF prediction results include:

RLF prediction reporting conditions (i.e., conditions for reporting the RLF prediction results).

The RLF prediction result includes at least one of the following:

first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell;

Future time information of when RLF occurs in the first cell;

a probability of RLF occurring in the first cell;

Cause of RLF.

Step 1.2: Perform RLF prediction based on the network configuration in step 1.1. If the RLF prediction result meets the reporting conditions, the terminal reports the RLF prediction result.

Optionally, after predicting that RLF will occur, the terminal reports the RLF prediction result to the network, for example, through terminal assistance information (UEAssistanceInformation message).

Step 1.3: The terminal receives the handover command sent by the network-side device and performs handover to avoid possible RLF in the future.

The second embodiment includes the following steps 2.2 to 2.3:

Step 2.1: The terminal receives a network configuration, where the network configuration includes at least one of the following:

RLF forecast indication;

Conditions for enabling the AI unit for predicting RLF;

Conditions for stopping the AI unit used to predict RLF;

Identification of the AI unit used to predict RLF;

Functional identification of AI units used to predict RLF;

Predict the inputs to the AI unit used by RLF;

Predict the output of the AI unit used by RLF;

Model structure of AI unit used to predict RLF;

Predict model parameters of the AI unit used by RLF;

Instructions to declare RLF based on RLF forecast results;

Conditions for declaring RLF based on RLF prediction results.

Step 2.2: Perform RLF prediction based on the network configuration in step 2.1. If the RLF prediction result meets the conditions, the terminal declares RLF and triggers cell reestablishment.

Step 2.3: The terminal reports an RLF report in the target cell (ie, the reestablished cell), wherein the report includes the cause of the RLF and the predicted probability of the RLF.

Implementation Method 3

The network-side device configuration or protocol predefines a ninth threshold. When the target duration between the predicted RLF occurrence moment and the current moment is less than the ninth threshold, the terminal declares RLF and triggers cell reconstruction. When the target duration between the predicted RLF occurrence moment and the current moment is greater than or equal to the ninth threshold, the terminal reports the RLF prediction result.

For example, when the ninth threshold is 2s:

If the terminal predicts that RLF will occur in 1 second, the terminal declares RLF and triggers cell reestablishment;

If the terminal predicts that RLF will occur in 3 seconds, the terminal reports the RLF prediction result.

The RLF prediction result includes at least one of the following:

first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell;

Future time information of when RLF occurs in the first cell;

a probability of RLF occurring in the first cell;

Cause of RLF.

The wireless link failure prediction method provided in the embodiment of the present application can be executed by a wireless link failure prediction device. In the embodiment of the present application, the wireless link failure prediction method performed by the wireless link failure prediction device is used as an example to illustrate the wireless link failure prediction device provided in the embodiment of the present application.

7 , an embodiment of the present application provides a device for predicting radio link failure, which can be applied to a terminal. The device 70 for predicting radio link failure may include the following modules:

An acquisition module 701 is configured to acquire first information, where the first information is used to indicate relevant information of a first cell;

The prediction module 702 is used to input the first information into the artificial intelligence AI unit and output the radio link failure RLF prediction result of the first cell.

Optionally, the first information includes at least one of the following:

the historical signal quality of the first cell;

a current signal quality of the first cell;

first auxiliary information related to the mobility of the terminal;

Second auxiliary information related to the network-side device.

Optionally, the RLF prediction result includes at least one of the following:

first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell;

Future time information of when RLF occurs in the first cell;

a probability of RLF occurring in the first cell;

Cause of RLF.

Optionally, the cause of the RLF includes at least one of the following:

The terminal predicts that the first timer will time out;

The terminal predicts that random access fails;

The terminal predicts that the number of RLC ARQ retransmissions by the radio link control layer has reached the maximum number of retransmissions.

Optionally, the device further comprises:

An enabling module is configured to use the AI unit to perform RLF prediction when at least one of the following first conditions is met:

The first cycle arrives;

The cell signal quality of the first cell is less than or equal to a first threshold;

The optimal beam signal quality of the first cell is less than or equal to a second threshold;

Trigger or enter radio link monitoring RLM measurement relaxation;

N310 reaches a first value, where N310 represents the number of consecutive times of being out of sync;

The first timer starts;

The timing duration of the first timer reaches a first duration;

The number of random access RACH times reaches a third threshold;

The number of RLC ARQ times reaches the fourth threshold;

Meet the radio resource management RRM measurement reporting conditions;

Trigger RRM measurement reporting;

The terminal receives second indication information sent by the network side device, where the second indication information is used to instruct the use of the AI unit to perform RLF prediction.

Optionally, the device further comprises:

A stopping module is configured to stop the AI unit from performing RLF prediction when at least one of the following second conditions is met:

The cell signal quality of the first cell is greater than or equal to a fifth threshold;

The optimal beam signal quality of the first cell is greater than or equal to a sixth threshold;

Exit or stop RLM measurement relaxation;

N311 reaches a second value, N311 indicating the number of consecutive synchronizations;

The terminal reports the RLF prediction result to the network side device;

The first timer stops running;

Triggering RLF;

One of the following occurs: cell handover, reestablishment, or redirection;

The terminal receives a positive acknowledgement ACK corresponding to a radio link control layer protocol service data unit RLC SDU;

Random access successful.

Optionally, the device further comprises:

A reporting module, configured to report the RLF prediction result to a network-side device when at least one of the following third conditions is met:

The second cycle arrives;

The terminal predicts that RLF will occur;

The terminal predicts that a probability of RLF occurrence is greater than or equal to a seventh threshold;

The terminal triggers RRM measurement reporting.

Optionally, the RLF prediction result is carried in at least one of the following:

RRM measurement report;

RLF report;

Radio Resource Control RRC reconfiguration complete message.

Optionally, the device includes at least one of the following modules:

a first processing module, configured to perform at least one of a first behavior and a second behavior according to the RLF prediction result, wherein the first behavior includes determining that an RLF occurs and triggering cell reestablishment, and the second behavior includes reporting the RLF prediction result to a network-side device;

The second processing module is used to determine whether to start a first timer according to the RLF prediction result.

Optionally, the first processing module is specifically configured to perform one of the following:

If the RLF prediction result satisfies a fourth condition, performing at least one of the first action and the second action, the fourth condition including that the RLF prediction result indicates that RLF will occur, or the RLF prediction result indicates that the probability of RLF occurring is greater than or equal to an eighth threshold;

If the RLF prediction result satisfies the fourth condition and the target duration is less than a ninth threshold, executing the first action, where the target duration is the duration between the future time point of RLF occurrence indicated by the RLF prediction result and the current time point;

When the RLF prediction result satisfies the fourth condition and the target duration is greater than or equal to the ninth threshold, the second behavior is performed.

Optionally, the second processing module is specifically configured to:

When the RLF prediction result indicates that RLF will occur, or when the RLF prediction result indicates that the probability of RLF occurring is greater than or equal to a tenth threshold, a first timer is started.

Optionally, the device further comprises:

The second receiving module is configured to receive at least one of the following items configured by the network side device:

The number of consecutive RLF predictions after using the AI unit;

Identification information of the AI unit;

Function information of the AI unit;

first information used as input to the AI unit;

output of the AI unit;

The model structure of the AI unit;

Model parameters of the AI unit;

A first condition for performing RLF prediction using the AI unit;

A second condition for stopping the AI unit from performing RLF prediction;

an instruction to report the RLF prediction result;

The third condition for reporting the RLF prediction result;

The RLF prediction results include:

Instruction information for instructing to perform a first action or a second action according to the RLF prediction result, the first action including determining that an RLF occurs and triggering cell reestablishment, and the second action including reporting the RLF prediction result to a network-side device;

A condition for executing the first behavior or the second behavior according to the RLF prediction result.

Optionally, the device further comprises:

The third processing module is configured to start a second timer after obtaining the RLF prediction result, and not use the AI unit to perform RLF prediction during the running of the second timer.

The wireless link failure prediction in the embodiments of the present application can be an electronic device, such as an electronic device with an operating system, or a component within the electronic device, such as an integrated circuit or chip. The electronic device can be a terminal; for example, the terminal can include, but is not limited to, the types of terminal 11 listed above, and is not specifically limited in the embodiments of the present application.

The wireless link failure prediction device provided in the embodiment of the present application can implement each process implemented in the method embodiment of Figure 2 and achieve the same technical effect. To avoid repetition, it will not be described here.

8 , an embodiment of the present application provides a device for predicting radio link failure, which can be applied to a network-side device. The device 80 for predicting radio link failure may include the following modules:

The first receiving module 801 is configured to receive a radio link failure (RLF) prediction result sent by a terminal, where the RLF prediction result is obtained by an artificial intelligence (AI) unit.

Optionally, the RLF prediction result includes at least one of the following:

first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell;

Future time information of when RLF occurs in the first cell;

a probability of RLF occurring in the first cell;

Cause of RLF.

Optionally, the cause of the RLF includes at least one of the following:

The terminal predicts that the first timer will time out;

The terminal predicts that random access fails;

The terminal predicts that the number of RLC ARQ retransmissions by the radio link control layer has reached the maximum number of retransmissions.

Optionally, the RLF prediction result is carried in at least one of the following:

Radio Resource Management RRM measurement report;

RLF report;

Radio Resource Control RRC reconfiguration complete message.

Optionally, the device further comprises:

A sending module, configured to send at least one of the following configurations to the terminal:

The number of times the AI unit continuously predicts the RLF;

Identification information of the AI unit;

Function information of the AI unit;

Input of the AI unit;

output of the AI unit;

The model structure of the AI unit;

Model parameters of the AI unit;

Second indication information, where the second indication information is used to instruct the AI unit to perform RLF prediction;

A first condition for performing RLF prediction using the AI unit;

A second condition for stopping the AI unit from performing RLF prediction;

an instruction to report the RLF prediction result;

The third condition for reporting the RLF prediction result;

The RLF prediction results include:

Instruction information for instructing to perform a first action or a second action according to the RLF prediction result, the first action including determining that an RLF occurs and triggering cell reestablishment, and the second action including reporting the RLF prediction result to a network-side device;

A condition for executing the first behavior or the second behavior according to the RLF prediction result.

The wireless link failure prediction in the embodiments of the present application can be an electronic device, such as an electronic device with an operating system, or a component within the electronic device, such as an integrated circuit or chip. The electronic device can be a network-side device; exemplary network-side devices can include, but are not limited to, the types of network-side devices 12 listed above, and are not specifically limited in the embodiments of the present application.

The wireless link failure prediction device provided in the embodiment of the present application can implement the various processes implemented in the method embodiment of Figure 6 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

As shown in Figure 9, an embodiment of the present application further provides a communication device 900, including a processor 901 and a memory 902. The memory 902 stores a program or instruction that can be run on the processor 901. For example, when the communication device 900 is a terminal, the program or instruction is executed by the processor 901 to implement the various steps of the embodiment of the method for predicting wireless link failure applied to the terminal, and can achieve the same technical effect. When the communication device 900 is a network-side device, the program or instruction is executed by the processor 901 to implement the various steps of the embodiment of the method for predicting wireless link failure applied to the network-side device, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

The present application also provides a terminal including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in FIG2 . This terminal embodiment corresponds to the aforementioned terminal-side method embodiment, and each implementation process and implementation method of the aforementioned method embodiment is applicable to this terminal embodiment and can achieve the same technical effects. Specifically, FIG10 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.

The terminal 1000 includes but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009 and at least some of the components of the processor 1010.

Those skilled in the art will appreciate that the terminal 1000 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 1010 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The terminal structure shown in FIG10 does not limit the terminal. The terminal may include more or fewer components than shown, or may combine certain components, or have different component arrangements, which will not be described in detail here.

It should be understood that in the embodiment of the present application, the input unit 1004 may include a graphics processing unit (GPU) 10041 and a microphone 10042, and the graphics processor 10041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1007 includes a touch panel 10071 and at least one of the other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include two parts: a touch detection device and a touch controller. Other input devices 10072 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.

In the embodiment of the present application, after receiving downlink data from a network-side device, the RF unit 1001 may transmit the data to the processor 1010 for processing. Furthermore, the RF unit 1001 may send uplink data to the network-side device. Typically, the RF unit 1001 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.

The memory 1009 can be used to store software programs or instructions and various data. The memory 1009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1009 may include a volatile memory or a non-volatile memory. 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 random access memory (RAM), static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM (DRRAM). The memory 1009 in the embodiments of the present application includes, but is not limited to, these and any other suitable types of memory.

Processor 1010 may include one or more processing units. Optionally, processor 1010 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 1010.

The processor 1010 is configured to:

Acquire first information, where the first information is used to indicate relevant information of the first cell;

The first information is input into an artificial intelligence (AI) unit for processing to obtain a radio link failure (RLF) prediction result of the first cell.

Optionally, the first information includes at least one of the following:

the historical signal quality of the first cell;

a current signal quality of the first cell;

first auxiliary information related to the mobility of the terminal;

Second auxiliary information related to the network-side device.

Optionally, the RLF prediction result includes at least one of the following:

first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell;

Future time information of when RLF occurs in the first cell;

a probability of RLF occurring in the first cell;

Cause of RLF.

Optionally, the cause of the RLF includes at least one of the following:

The terminal predicts that the first timer will time out;

The terminal predicts that random access fails;

The terminal predicts that the number of RLC ARQ retransmissions by the radio link control layer has reached the maximum number of retransmissions.

Optionally, the processor 1010 is further configured to:

When at least one of the following first conditions is met, the AI unit is used to perform RLF prediction:

The first cycle arrives;

The cell signal quality of the first cell is less than or equal to a first threshold;

The optimal beam signal quality of the first cell is less than or equal to a second threshold;

Trigger or enter radio link monitoring RLM measurement relaxation;

N310 reaches a first value, where N310 represents the number of consecutive times of being out of sync;

The first timer starts;

The timing duration of the first timer reaches a first duration;

The number of random access RACH times reaches a third threshold;

The number of RLC ARQ times reaches the fourth threshold;

Meet the radio resource management RRM measurement reporting conditions;

Trigger RRM measurement reporting;

The terminal receives second indication information sent by the network side device, where the second indication information is used to instruct the use of the AI unit to perform RLF prediction.

Optionally, the processor 1010 is further configured to:

When at least one of the following second conditions is met, the AI unit is stopped from performing RLF prediction:

The cell signal quality of the first cell is greater than or equal to a fifth threshold;

The optimal beam signal quality of the first cell is greater than or equal to a sixth threshold;

Exit or stop RLM measurement relaxation;

N311 reaches a second value, N311 indicating the number of consecutive synchronizations;

The terminal reports the RLF prediction result to the network side device;

The first timer stops running;

Triggering RLF;

One of the following occurs: cell handover, reestablishment, or redirection;

The terminal receives a positive acknowledgement ACK corresponding to a radio link control layer protocol service data unit RLC SDU;

Random access successful.

Optionally, the radio frequency unit 1001 is configured to:

When at least one of the following third conditions is met, the RLF prediction result is reported to the network side device:

The second cycle arrives;

The terminal predicts that RLF will occur;

The terminal predicts that a probability of RLF occurrence is greater than or equal to a seventh threshold;

The terminal triggers RRM measurement reporting.

Optionally, the RLF prediction result is carried in at least one of the following:

RRM measurement report;

RLF report;

Radio Resource Control RRC reconfiguration complete message.

Optionally, the processor 1010 is further configured to perform at least one of the following:

Perform at least one of a first behavior and a second behavior according to the RLF prediction result, wherein the first behavior includes determining that an RLF occurs and triggering cell reestablishment, and the second behavior includes reporting the RLF prediction result to a network-side device;

Determine whether to start a first timer according to the RLF prediction result.

Optionally, the processor 1010 performs at least one of a first action and a second action according to the RLF prediction result, including one of the following:

If the RLF prediction result satisfies a fourth condition, performing at least one of the first action and the second action, the fourth condition including that the RLF prediction result indicates that RLF will occur, or the RLF prediction result indicates that the probability of RLF occurring is greater than or equal to an eighth threshold;

If the RLF prediction result satisfies the fourth condition and the target duration is less than a ninth threshold, executing the first action, where the target duration is the duration between the future time point of RLF occurrence indicated by the RLF prediction result and the current time point;

When the RLF prediction result satisfies the fourth condition and the target duration is greater than or equal to the ninth threshold, the second behavior is performed.

Optionally, the processor 1010 determines, according to the RLF prediction result, whether to start a first timer, including:

When the RLF prediction result indicates that RLF will occur, or when the RLF prediction result indicates that the probability of RLF occurring is greater than or equal to a tenth threshold, a first timer is started.

Optionally, the radio frequency unit 1001 is further configured to:

Receive at least one of the following configurations from the network device:

The number of times the AI unit continuously predicts the RLF;

Identification information of the AI unit;

Function information of the AI unit;

first information used as input to the AI unit;

output of the AI unit;

The model structure of the AI unit;

Model parameters of the AI unit;

A first condition for performing RLF prediction using the AI unit;

A second condition for stopping the AI unit from performing RLF prediction;

an instruction to report the RLF prediction result;

The third condition for reporting the RLF prediction result;

The RLF prediction results include:

Instruction information for instructing to perform a first action or a second action according to the RLF prediction result, the first action including determining that an RLF occurs and triggering cell reestablishment, and the second action including reporting the RLF prediction result to a network-side device;

A condition for executing the first behavior or the second behavior according to the RLF prediction result.

Optionally, the processor 1010 is further configured to:

After the AI unit outputs the RLF prediction result, a second timer is started, and the AI unit is not used to perform RLF prediction during the running of the second timer.

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

The present application also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in FIG6 . This network-side device embodiment corresponds to the aforementioned network-side device method embodiment, and each implementation process and implementation method of the aforementioned method embodiment are applicable to this network-side device embodiment and can achieve the same technical effects.

Specifically, embodiments of the present application also provide a network-side device. As shown in Figure 11, the network-side device 1100 includes an antenna 111, a radio frequency device 112, a baseband device 113, a processor 114, and a memory 115. Antenna 111 is connected to radio frequency device 112. In the uplink direction, radio frequency device 112 receives information via antenna 111 and sends the received information to baseband device 113 for processing. In the downlink direction, baseband device 113 processes the information to be transmitted and sends it to radio frequency device 112. Radio frequency device 112 processes the received information and then sends it through antenna 111.

The method executed by the network-side device in the above embodiment may be implemented in the baseband device 113 , which includes a baseband processor.

The baseband device 113 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in Figure 11, one of the chips is, for example, a baseband processor, which is connected to the memory 115 through a bus interface to call the program in the memory 115 and execute the network side device operations shown in the above method embodiment.

The network side device may also include a network interface 116, which is, for example, a Common Public Radio Interface (CPRI).

Specifically, the network side device 1100 of the embodiment of the present application also includes: instructions or programs stored in the memory 115 and executable on the processor 114. The processor 114 calls the instructions or programs in the memory 115 to execute the method of execution of each module shown in Figure 8 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

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

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

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 wireless link failure prediction method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

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.

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

An embodiment of the present application also provides a wireless link failure prediction system, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the wireless link failure prediction method applied to the terminal as above, and the network side device can be used to execute the steps of the wireless link failure prediction method applied to the network side device as above.

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

Through the description of the above embodiments, 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-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.

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

Claims (36)

A method for predicting wireless link failure, wherein the method comprises: The terminal obtains first information, where the first information is used to indicate relevant information of the first cell; The terminal inputs the first information into an artificial intelligence (AI) unit for processing to obtain a radio link failure (RLF) prediction result of the first cell. The method according to claim 1, wherein the first information includes at least one of the following: the historical signal quality of the first cell; a current signal quality of the first cell; first auxiliary information related to the mobility of the terminal; Second auxiliary information related to the network-side device. The method according to claim 1 or 2, wherein the RLF prediction result includes at least one of the following: first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell; Future time information of when RLF occurs in the first cell; a probability of RLF occurring in the first cell; Cause of RLF. The method according to claim 3, wherein the cause of the RLF includes at least one of the following: The terminal predicts that the first timer will time out; The terminal predicts that random access fails; The terminal predicts that the number of RLC ARQ retransmissions by the radio link control layer has reached the maximum number of retransmissions. The method according to any one of claims 1 to 4, further comprising: When at least one of the following first conditions is met, the terminal uses the AI unit to perform RLF prediction: The first cycle arrives; The cell signal quality of the first cell is less than or equal to a first threshold; The optimal beam signal quality of the first cell is less than or equal to a second threshold; Trigger or enter radio link monitoring RLM measurement relaxation; N310 reaches a first value, where N310 represents the number of consecutive times of being out of sync; The first timer starts; The timing duration of the first timer reaches a first duration; The number of random access RACH times reaches a third threshold; The number of RLC ARQ times reaches the fourth threshold; Meet the radio resource management RRM measurement reporting conditions; Trigger RRM measurement reporting; The terminal receives second indication information sent by the network side device, where the second indication information is used to instruct the use of the AI unit to perform RLF prediction. The method according to any one of claims 1 to 5, further comprising: When at least one of the following second conditions is met, the terminal stops the AI unit from performing RLF prediction: The cell signal quality of the first cell is greater than or equal to a fifth threshold; The optimal beam signal quality of the first cell is greater than or equal to a sixth threshold; Exit or stop RLM measurement relaxation; N311 reaches a second value, N311 indicating the number of consecutive synchronizations; The terminal reports the RLF prediction result to the network side device; The first timer stops running; Triggering RLF; One of the following occurs: cell handover, reestablishment, or redirection; The terminal receives a positive acknowledgement ACK corresponding to a radio link control layer protocol service data unit RLC SDU; Random access successful. The method according to any one of claims 1 to 6, further comprising: When at least one of the following third conditions is met, the terminal reports the RLF prediction result to the network side device: The second cycle arrives; The terminal predicts that RLF will occur; The terminal predicts that a probability of RLF occurrence is greater than or equal to a seventh threshold; The terminal triggers RRM measurement reporting. The method according to any one of claims 1 to 7, wherein the RLF prediction result is carried in at least one of the following: RRM measurement report; RLF report; Radio Resource Control RRC reconfiguration complete message. The method according to any one of claims 1 to 8, wherein the method further comprises at least one of the following: The terminal performs at least one of a first behavior and a second behavior according to the RLF prediction result, wherein the first behavior includes determining that an RLF occurs and triggering cell reestablishment, and the second behavior includes reporting the RLF prediction result to a network-side device; The terminal determines whether to start a first timer according to the RLF prediction result. The method according to claim 9, wherein the terminal performs at least one of a first action and a second action based on the RLF prediction result, including one of the following: If the RLF prediction result satisfies a fourth condition, the terminal performs at least one of the first behavior and the second behavior, the fourth condition including that the RLF prediction result indicates that RLF will occur, or the RLF prediction result indicates that the probability of RLF occurrence is greater than or equal to an eighth threshold; If the RLF prediction result satisfies the fourth condition and the target duration is less than a ninth threshold, the terminal performs the first action, where the target duration is the duration between the future time point of RLF occurrence indicated by the RLF prediction result and the current time point; When the RLF prediction result satisfies the fourth condition and the target duration is greater than or equal to the ninth threshold, the terminal performs the second behavior. The method according to claim 9 or 10, wherein the terminal determines whether to start the first timer according to the RLF prediction result, including: When the RLF prediction result indicates that RLF will occur, or when the RLF prediction result indicates that the probability of RLF occurring is greater than or equal to a tenth threshold, the terminal starts a first timer. The method according to any one of claims 1 to 11, wherein the method further comprises: The terminal receives at least one of the following items configured by the network side device: The number of times the AI unit continuously predicts the RLF; Identification information of the AI unit; Function information of the AI unit; first information used as input to the AI unit; output of the AI unit; The model structure of the AI unit; Model parameters of the AI unit; A first condition for performing RLF prediction using the AI unit; A second condition for stopping the AI unit from performing RLF prediction; an instruction to report the RLF prediction result; The third condition for reporting the RLF prediction result; The RLF prediction results include: Instruction information for instructing to perform a first action or a second action according to the RLF prediction result, the first action including determining that an RLF occurs and triggering cell reestablishment, and the second action including reporting the RLF prediction result to a network-side device; A condition for executing the first behavior or the second behavior according to the RLF prediction result. The method according to any one of claims 1 to 12, wherein the method further comprises: After obtaining the RLF prediction result, the terminal starts a second timer and does not use the AI unit to perform RLF prediction while the second timer is running. A method for predicting wireless link failure, wherein the method comprises: The network side device receives the radio link failure (RLF) prediction result sent by the terminal, where the RLF prediction result is obtained by an artificial intelligence (AI) unit. The method according to claim 14, wherein the RLF prediction result includes at least one of the following: first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell; Future time information of when RLF occurs in the first cell; a probability of RLF occurring in the first cell; Cause of RLF. The method according to claim 15, wherein the cause of the RLF comprises at least one of the following: The terminal predicts that the first timer will time out; The terminal predicts that random access fails; The terminal predicts that the number of RLC ARQ retransmissions by the radio link control layer has reached the maximum number of retransmissions. The method according to any one of claims 14 to 16, wherein the RLF prediction result is carried in at least one of the following: Radio Resource Management RRM measurement report; RLF report; Radio Resource Control RRC reconfiguration complete message. The method according to any one of claims 14 to 17, wherein the method further comprises: The network side device sends at least one of the following configurations to the terminal: The number of times the AI unit continuously predicts the RLF; Identification information of the AI unit; Function information of the AI unit; Input of the AI unit; output of the AI unit; The model structure of the AI unit; Model parameters of the AI unit; Second indication information, where the second indication information is used to instruct the AI unit to perform RLF prediction; A first condition for performing RLF prediction using the AI unit; A second condition for stopping the AI unit from performing RLF prediction; an instruction to report the RLF prediction result; The third condition for reporting the RLF prediction result; The RLF prediction results include: Instruction information for instructing to perform a first action or a second action according to the RLF prediction result, the first action including determining that an RLF occurs and triggering cell reestablishment, and the second action including reporting the RLF prediction result to a network-side device; A condition for executing the first behavior or the second behavior according to the RLF prediction result. A device for predicting radio link failure, wherein the device is applied to a terminal, and comprises: an acquiring module, configured to acquire first information, wherein the first information is used to indicate relevant information of the first cell; A prediction module is used to input the first information into an artificial intelligence AI unit for processing to obtain a radio link failure RLF prediction result of the first cell. The apparatus according to claim 19, wherein the first information includes at least one of the following: the historical signal quality of the first cell; a current signal quality of the first cell; first auxiliary information related to the mobility of the terminal; Second auxiliary information related to the network-side device. The apparatus according to claim 19 or 20, wherein the RLF prediction result includes at least one of the following: first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell; Future time information of when RLF occurs in the first cell; a probability of RLF occurring in the first cell; Cause of RLF. The apparatus according to claim 21, wherein the cause of the RLF comprises at least one of the following: The terminal predicts that the first timer will time out; The terminal predicts that random access fails; The terminal predicts that the number of RLC ARQ retransmissions by the radio link control layer has reached the maximum number of retransmissions. The device according to any one of claims 19 to 22, wherein the device further comprises: An enabling module is configured to use the AI unit to perform RLF prediction when at least one of the following first conditions is met: The first cycle arrives; The cell signal quality of the first cell is less than or equal to a first threshold; The optimal beam signal quality of the first cell is less than or equal to a second threshold; Trigger or enter radio link monitoring RLM measurement relaxation; N310 reaches a first value, where N310 represents the number of consecutive times of being out of sync; The first timer starts; The timing duration of the first timer reaches a first duration; The number of random access RACH times reaches a third threshold; The number of RLC ARQ times reaches the fourth threshold; Meet the radio resource management RRM measurement reporting conditions; Trigger RRM measurement reporting; The terminal receives second indication information sent by the network side device, where the second indication information is used to instruct the use of the AI unit to perform RLF prediction. The device according to any one of claims 19 to 23, wherein the device further comprises: A stopping module is configured to stop the AI unit from performing RLF prediction when at least one of the following second conditions is met: The cell signal quality of the first cell is greater than or equal to a fifth threshold; The optimal beam signal quality of the first cell is greater than or equal to a sixth threshold; Exit or stop RLM measurement relaxation; N311 reaches a second value, N311 indicating the number of consecutive synchronizations; The terminal reports the RLF prediction result to the network side device; The first timer stops running; Triggering RLF; One of the following occurs: cell handover, reestablishment, or redirection; The terminal receives a positive acknowledgement ACK corresponding to a radio link control layer protocol service data unit RLC SDU; Random access successful. The device according to any one of claims 19 to 24, further comprising: A reporting module, configured to report the RLF prediction result to a network-side device when at least one of the following third conditions is met: The second cycle arrives; The terminal predicts that RLF will occur; The terminal predicts that a probability of RLF occurrence is greater than or equal to a seventh threshold; The terminal triggers RRM measurement reporting. The device according to any one of claims 19 to 25, wherein the device further comprises at least one of the following modules: a first processing module, configured to perform at least one of a first behavior and a second behavior according to the RLF prediction result, wherein the first behavior includes determining that an RLF occurs and triggering cell reestablishment, and the second behavior includes reporting the RLF prediction result to a network-side device; The second processing module is used to determine whether to start a first timer according to the RLF prediction result. The apparatus according to claim 26, wherein the first processing module is specifically configured to perform at least one of the following: If the RLF prediction result satisfies a fourth condition, performing at least one of the first action and the second action, the fourth condition including that the RLF prediction result indicates that RLF will occur, or the RLF prediction result indicates that the probability of RLF occurring is greater than or equal to an eighth threshold; If the RLF prediction result satisfies the fourth condition and the target duration is less than a ninth threshold, executing the first action, where the target duration is the duration between the future time point of RLF occurrence indicated by the RLF prediction result and the current time point; When the RLF prediction result satisfies the fourth condition and the target duration is greater than or equal to the ninth threshold, the second behavior is performed. The device according to claim 26 or 27, wherein the second processing module is specifically configured to: When the RLF prediction result indicates that RLF will occur, or when the RLF prediction result indicates that the probability of RLF occurring is greater than or equal to a tenth threshold, a first timer is started. The device according to any one of claims 19 to 28, wherein the device further comprises: The second receiving module is configured to receive at least one of the following items configured by the network side device: The number of times the AI unit continuously predicts the RLF; Identification information of the AI unit; Function information of the AI unit; first information used as input to the AI unit; output of the AI unit; The model structure of the AI unit; Model parameters of the AI unit; A first condition for performing RLF prediction using the AI unit; A second condition for stopping the AI unit from performing RLF prediction; an instruction to report the RLF prediction result; The third condition for reporting the RLF prediction result; The RLF prediction results include: Instruction information for instructing to perform a first action or a second action according to the RLF prediction result, the first action including determining that an RLF occurs and triggering cell reestablishment, and the second action including reporting the RLF prediction result to a network-side device; A condition for executing the first behavior or the second behavior according to the RLF prediction result. A device for predicting wireless link failure, wherein the device is applied to a network-side device, and the device comprises: The first receiving module is used to receive the radio link RLF prediction result sent by the terminal, where the RLF prediction result is obtained by an artificial intelligence AI unit. The apparatus according to claim 30, wherein the RLF prediction result includes at least one of the following: first indication information, where the first indication information is used to indicate whether RLF occurs in the first cell; Future time information of when RLF occurs in the first cell; a probability of RLF occurring in the first cell; Cause of RLF. The apparatus according to claim 31, wherein the cause of the RLF comprises at least one of the following: The terminal predicts that the first timer will time out; The terminal predicts that random access fails; The terminal predicts that the number of RLC ARQ retransmissions by the radio link control layer has reached the maximum number of retransmissions. The apparatus according to any one of claims 30 to 32, wherein the RLF prediction result is carried in at least one of the following: Radio Resource Management RRM measurement report; RLF report; Radio Resource Control RRC reconfiguration complete message. The device according to any one of claims 30 to 33, wherein the device further comprises: A sending module, configured to send at least one of the following configurations to the terminal: The number of times the AI unit continuously predicts the RLF; Identification information of the AI unit; Function information of the AI unit; Input of the AI unit; output of the AI unit; The model structure of the AI unit; Model parameters of the AI unit; Second indication information, where the second indication information is used to instruct the AI unit to perform RLF prediction; A first condition for performing RLF prediction using the AI unit; A second condition for stopping the AI unit from performing RLF prediction; an instruction to report the RLF prediction result; The third condition for reporting the RLF prediction result; The RLF prediction results include: Instruction information for instructing to perform a first action or a second action according to the RLF prediction result, the first action including determining that an RLF occurs and triggering cell reestablishment, and the second action including reporting the RLF prediction result to a network-side device; A condition for executing the first behavior or the second behavior according to the RLF prediction result. A communication device, 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, implements the steps of the method for predicting a radio link failure as described in any one of claims 1 to 13, or implements the steps of the method for predicting a radio link failure as described in any one of claims 14 to 18. A readable storage medium, wherein the readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the program or instruction implements the steps of the method for predicting a wireless link failure as described in any one of claims 1 to 13, or implements the steps of the method for predicting a wireless link failure as described in any one of claims 14 to 18.