Prediction method, communication method, terminal device, and network device

Abstract

The present application belongs to the field of communications. Disclosed are a prediction method, a communication method, a terminal device and a network device. The prediction method in the embodiments of the present application comprises: a terminal inputting into a target artificial intelligence (AI) model an input parameter associated with a target event; and the terminal acquiring a trigger indication about the target event that is output by the target AI model.

Description

Prediction method, communication method, terminal device and network device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on April 3, 2024, with application number 202410403556.9 and invention name “Prediction method, communication method, terminal device and network device”. The entire contents of the Chinese patent application are incorporated herein by reference. Technical Field

[0003] The embodiments of the present application relate to the field of communications, and in particular to a prediction method, a communication method, a terminal device, and a network device. Background Art

[0004] In New Radio (NR), the base station determines whether to perform operations such as cell handover, adding a secondary cell, or releasing a secondary cell based on measurement reports corresponding to measurement events reported by the terminal. Measurement events in related technologies are all triggered by measurements of a cell's downlink signal. If a base station determines whether to perform a target operation based solely on downlink signal measurements, this can lead to inaccurate timing (e.g., too early or too late) and poor performance. Summary of the Invention

[0005] In a first aspect, a prediction method is provided, the method comprising: a terminal inputting input parameters associated with a target event into a target artificial intelligence (AI) model; and the terminal obtaining a trigger indication regarding the target event output by the target AI model.

[0006] In a second aspect, a communication method is provided, the method comprising: a network device receives first information from a terminal, the first information being used to indicate that a target event is triggered, and the target event is predicted by the terminal based on a target AI model.

[0007] In a third aspect, a prediction device is provided, comprising: an input module for inputting input parameters associated with a target event into a target artificial intelligence (AI) model; and an acquisition module for acquiring a trigger indication of the target event output by the target AI model.

[0008] In a fourth aspect, a communication device is provided, characterized in that it includes: a processing module for receiving first information from a terminal, wherein the first information is used to indicate that a target event is triggered, and the target event is predicted by the terminal based on a target AI model.

[0009] In a fifth aspect, a terminal is provided, comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0010] In a sixth aspect, a terminal is provided, comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0011] In the seventh aspect, a network side device is provided, comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the method described in the second aspect are implemented.

[0012] In an eighth aspect, a communication system is provided, comprising: a terminal and a network-side device, wherein the terminal can be used to execute the steps of the method described in the first aspect, and the network-side device can be used to execute the steps of the method described in the second aspect.

[0013] In the ninth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented.

[0014] In the tenth aspect, a chip is provided, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0015] In the eleventh aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0016] In an embodiment of the present application, input parameters associated with a target event are input into a target artificial intelligence (AI) model through a terminal; the terminal obtains a trigger indication regarding the target event output by the target AI model, and predicts the target event by using the AI ​​model. This can solve problems such as inaccurate timing (for example, too early or too late) of executing target operations (such as cell switching, adding secondary cells, releasing secondary cells, etc.), poor execution performance of target operations, and thus improve the stability of terminal communication. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG1 shows a schematic diagram of a wireless communication system applicable to an embodiment of the present application.

[0018] FIG2 a is a schematic flow chart of a prediction method according to an embodiment of the present application;

[0019] FIG2 b is a schematic diagram of a prediction method according to an embodiment of the present application;

[0020] FIG3 is a schematic flow chart of a prediction method according to another embodiment of the present application;

[0021] FIG4 is a schematic flow chart of a communication method according to an embodiment of the present application;

[0022] FIG5 is a schematic flowchart of a communication method according to another embodiment of the present application;

[0023] FIG6 is a schematic structural diagram of a prediction device according to an embodiment of the present application;

[0024] FIG7 is a schematic structural diagram of a communication device according to an embodiment of the present application;

[0025] FIG8 is a schematic structural diagram of a network device according to another embodiment of the present application;

[0026] FIG9 is a schematic structural diagram of a terminal device according to another embodiment of the present application. DETAILED DESCRIPTION

[0027] 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.

[0028] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that 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, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0029] 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) and 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 applications other than NR system applications, such as 6th Generation (6G) communication systems.

[0030] 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 . The terminal 11 may be a mobile phone, a tablet personal computer, a laptop computer or a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, a vehicle-mounted device (VUE), a pedestrian terminal (PUE), a smart home (a home appliance with wireless communication capabilities, such as a refrigerator, a television, a washing machine, or furniture), a game console, a personal computer (PC), an ATM, or a self-service machine, etc. The wearable device includes: a smart watch, a smart bracelet, a smart headset, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), a smart wristband, smart clothing, 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 12 may also be referred to as a radio access network device, a radio access network (RAN), a radio access network function, or a radio access network unit. The access network device 12 may include a base station, a WLAN access point, or a WiFi node, etc. The base station may be referred to as a node B, an evolved node B (eNB), an access point, a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home node B, a home evolved node B, a transmitting and receiving point (TRP), or other appropriate terms in the field. As long as the same technical effect is achieved, the base station is not limited to a specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.

[0031] The prediction method provided in the embodiments of the present application is described in detail below through some embodiments and their application scenarios in conjunction with the accompanying drawings.

[0032] As shown in FIG2a , an embodiment of the present application provides a prediction method 200. The method may be executed by a terminal device. In other words, the method may be executed by software or hardware installed on the terminal device. The method includes the following steps:

[0033] S202: The terminal inputs the input parameters associated with the target event into the target artificial intelligence AI model.

[0034] The target event may include various events in the communication process, including but not limited to at least one of measurement events, suggestion events, demand events, request events, and the like.

[0035] In one implementation, the target event may be different from an existing measurement event and may be a newly introduced measurement event. The measurement event may include at least one of a cell switching measurement event, a secondary cell addition measurement event, and a secondary cell release measurement event. The cell switching measurement event indicates a measurement event for performing a cell switching, or a measurement event in which the terminal generates a need to perform a cell switching, or a measurement event in which the terminal recommends performing a cell switching. Similarly, the secondary cell addition / release measurement event indicates a measurement event for performing a secondary cell addition / release, or a measurement event in which the terminal generates a need to perform a secondary cell addition / release, or a measurement event in which the terminal recommends performing a secondary cell addition measurement event. In another implementation, the target event may reuse an existing measurement event, that is, the target event includes at least one of the A1 to A6 measurement events and the B1 to B2 measurement events.

[0036] A measurement report configuration ReportConfig is used to configure trigger-related parameters and reporting-related parameters of the measurement report, including event-triggered reporting. Some of the events that trigger reporting include: Event A1 indicates that the serving cell signal is above the threshold (Serving becomes better than threshold); Event A2 indicates that the serving cell signal is worse than the threshold (Serving becomes worse than threshold); Event A3 indicates that the neighbor cell signal is better than the SpCell signal by one offset (Neighbour becomes offset better than SpCell); Event A4 indicates that the neighbor cell signal is better than the threshold (Neighbour becomes better than threshold); Event A5 indicates that the SpCell signal is worse than threshold 1 and the neighbor cell signal is better than threshold 2 (SpCell becomes worse than threshold1 and neighbor becomes better than threshold2); Event A6 indicates that the neighbor cell signal is better than the SCell signal by one offset (Neighbour becomes offset better than SCell); Event B1 indicates that the inter-RAT neighbor signal is better than threshold (Inter RAT neighbor becomes better than threshold); Event B2 indicates that the PCell signal is worse than threshold 1 and the inter-RAT neighbor signal is better than threshold 2 (PCell becomes worse than threshold1 and inter-RAT neighbor becomes better than threshold2).

[0037] In one implementation, the target event is a suggestion event, which may include at least one of a cell handover suggestion, a secondary cell addition suggestion, and a secondary cell release suggestion. A suggestion event indicates a proposal to perform an action and may also be referred to as a proposal event or a demand event. For example, a cell handover suggestion event indicates a proposal to perform a cell handover.

[0038] The target artificial intelligence (AI) model is trained using a large amount of training data. The target AI model can be implemented in a variety of ways, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. The embodiments of this application do not limit the specific type of the target AI model. The embodiments of this application combine the target AI model with communication technology to train a target AI model for mobility event prediction.

[0039] The input parameters of the target AI model are associated with the attributes of the target event. In one implementation, the input parameters associated with the target event include at least one of the following:

[0040] The target AI model predicts the duration information of the target event; that is, the AI ​​model can predict the target event within the duration information by performing one inference. For example, if the duration information indicates 5 seconds, the AI ​​model can predict the switching event or switching suggestion within 5 seconds by performing one inference;

[0041] location information of the terminal;

[0042] Moving speed information of the terminal;

[0043] Moving direction information of the terminal;

[0044] The terminal's historical measurement information; for example, the reference signal received power of the serving cell and neighboring cells within the previous 5 seconds

[0045] (Reference Signal Received Power, RSRP) measurement value and / or Reference Signal Received Quality (RSRQ) measurement value;

[0046] The measurement information of the terminal includes the current measurement information of the UE, such as the RSRP measurement value and / or RSRQ measurement value of the current serving cell and neighboring cells;

[0047] The predicted frequency may include a predicted frequency or a frequency list consisting of multiple predicted frequencies. The UE predicts whether the cell corresponding to the frequency or the frequency in the frequency list can be used as a candidate target cell associated with the target event. There is an association between the candidate target cell and the triggering of the target event. For example, when the target event includes a handover event, the candidate target cell associated with the target event is a candidate target cell for handover. If the input parameter is a predicted frequency, it indicates whether the cell corresponding to the frequency is predicted to be a candidate target cell for handover.

[0048] Predicted cell; may include a predicted cell or a cell list consisting of multiple predicted cells, and the UE predicts whether the cell or the cell in the cell list can be used as a candidate target cell; when the target event includes a handover event, predict whether the cell can be used as a candidate target cell for handover;

[0049] Frequency blacklist: exclude cells corresponding to frequencies in the blacklist from candidate target cells;

[0050] Blacklist of communities; that is, exclude communities on the blacklist from candidate target communities;

[0051] The triggering condition of the target event;

[0052] The measurement event type of the target event;

[0053] Configuration parameters of the measurement event of the target event.

[0054] In one implementation, when the target event includes at least one of a cell handover measurement event, a secondary cell addition measurement event, a secondary cell release measurement event, a cell handover suggestion, a secondary cell addition suggestion, and a secondary cell release suggestion, the input parameters associated with the target event include at least one of the following:

[0055] The target AI model predicts the duration information of the target event; that is, the AI ​​model can predict a switching event or switching suggestion within the duration information, such as 5 seconds, by performing a reasoning operation. As shown in FIG2b , the UE performs AI model reasoning at t1 when the first condition is met, and the predicted duration range is from t1 to t2. The reasoning result is that no switching event is triggered or switching is not recommended. In addition, the UE periodically performs model reasoning, performs AI model reasoning at t2, and predicts the duration range is from t2 to t4. The AI ​​model reasoning result is that the switching event is triggered or switching is recommended at time point t3 or 1 second later.

[0056] location information of the terminal;

[0057] Moving speed information of the terminal;

[0058] Moving direction information of the terminal;

[0059] Historical measurement information of the terminal; for example, RSRP measurement values ​​and RSRQ measurement values ​​of the serving cell and neighboring cells within the previous 5 seconds;

[0060] The measurement information of the terminal includes the current measurement information of the UE, such as the RSRP measurement value and / or RSRQ measurement value of the current serving cell and neighboring cells;

[0061] The predicted frequency may include a predicted frequency or a frequency list consisting of multiple predicted frequencies. The UE predicts whether a cell at the frequency or a frequency in the frequency list can be used as a candidate target cell.

[0062] Predicted cell; may include a predicted cell or a cell list consisting of multiple predicted cells, and the UE predicts whether the cell or the cell in the cell list can be used as a candidate target cell;

[0063] Frequency blacklist: exclude cells with frequencies in the blacklist as candidate target cells;

[0064] Blacklist of cells; that is, exclude cells in the blacklist as candidate target cells.

[0065] The AI ​​model on the UE side can predict handover events within the range of the above-specified frequency, frequency list, cell or cell list, and output which cells can be used as candidate target cells for handover.

[0066] Optionally, when the first condition is met, the UE starts AI model reasoning to obtain output parameters. After starting, the reasoning can be performed periodically at intervals of the first duration. For example, the first condition is the signal quality of the serving cell, such as RSRP or Reference Signal Received Quality (RSRQ) is less than or equal to the first threshold, or the amount of data cached by the UE is greater than a certain threshold. The reasoning is stopped until the first condition is no longer met, thereby reducing the number of reasonings and saving UE resources. Alternatively, the UE can always perform reasoning periodically at intervals of the first duration to achieve better switching performance. The first threshold and / or the first duration can be configured by the base station, or can be determined by the UE, or the first duration can be equal to the duration range predicted by the AI ​​model, that is, the first duration can reuse the value of the duration range predicted by the AI ​​model.

[0067] In one implementation, when the target event includes at least one of measurement events A1 to A6 and measurement events B1 to B2, the input parameter associated with the target event includes at least one of the following:

[0068] The target AI model predicts the duration information of the target event;

[0069] location information of the terminal;

[0070] Moving speed information of the terminal;

[0071] Moving direction information of the terminal;

[0072] historical measurement information of the terminal;

[0073] measurement information of the terminal;

[0074] Predicted frequency point; that is, the measurement frequency point in the measurement configuration;

[0075] The measurement event type of the target event, i.e., the type of Ax / Bx event, such as A3, A5;

[0076] Configuration parameters of the measurement event of the target event, that is, configuration parameters of the Ax / Bx event, such as the threshold or offset associated with the event.

[0077] As a result, UE can fully consider various factors through AI models.

[0078] In one implementation, the terminal may input the input parameters associated with the target event into the target artificial intelligence (AI) model when a first condition is met; wherein the first condition includes at least one of the following:

[0079] The signal quality of the serving cell of the terminal is less than or equal to a first threshold;

[0080] The amount of data cached by the terminal is greater than or equal to a second threshold;

[0081] A first timer times out, where the first timer is a periodic timer.

[0082] It should be noted that the terminal inputs the input parameters associated with the target event into the target artificial intelligence AI model. It can also be considered that the terminal inputs the input parameters associated with the target event into the target artificial intelligence AI model to execute the reasoning of the target AI model, and the target AI model executes the reasoning to generate output.

[0083] S204: The terminal obtains a trigger indication of the target event output by the target AI model.

[0084] When the target event is a measurement event, and the measurement event includes at least one of a cell switching measurement event, a secondary cell addition measurement event, and a secondary cell release measurement event, at least one of a trigger indication of a cell switching measurement event, a trigger indication of a secondary cell addition measurement event, and a trigger indication of a secondary cell release measurement event can be obtained in this step.

[0085] When the target event includes at least one of measurement events A1 to A6 and measurement events B1 to B2, at least one of trigger indications of measurement events A1 to A6 and measurement events B1 to B2 may be obtained in this step.

[0086] When the target event is a suggestion event, and the suggestion event includes at least one of a cell switching suggestion, a secondary cell addition suggestion, and a secondary cell release suggestion, at least one of a trigger indication of a cell switching suggestion, a trigger indication of a secondary cell addition suggestion, and a trigger indication of a secondary cell release suggestion can be obtained in this step.

[0087] In one implementation, the target event may be associated with a measurement identifier (ID), such as a measurement ID specified by a protocol.

[0088] In one implementation, the trigger indication is used to indicate at least one of the following information:

[0089] Predicting whether the target event is triggered;

[0090] The predicted time point when the target event is triggered;

[0091] A time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output; for example, the target event is triggered after the time length has elapsed since the trigger indication is output;

[0092] A cell prediction value of the serving cell corresponding to the predicted time point when the target event is triggered; the base station may refer to the cell prediction value when determining whether to trigger the target event;

[0093] The reason why the target event is triggered;

[0094] The identifier of the cell associated with the target event; a cell associated with the target event is a cell that has an association with the triggering of the target event. For example, when the target event is a handover, the cell associated with the handover event may be the cell that triggered the handover event. Optionally, the cell identifier may also include frequency information corresponding to the cell; optionally, the cell identifier may also include identifiers of one or more candidate target cells. Multiple candidate target cells may be sorted by priority, for example, with cells ranked earlier having a higher priority.

[0095] A cell prediction value corresponding to the cell associated with the target event;

[0096] The beam information corresponding to the cell associated with the target event; the beam information corresponding to the cell associated with the target event is used for allocating associated RACH resources to the target base station.

[0097] A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered;

[0098] The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

[0099] In one implementation, the reason includes at least one of the following reasons:

[0100] Downlink signal reason;

[0101] Uplink signal reason;

[0102] Data transmission reasons, such as the target cell can provide more transmission resources, the current serving cell is congested, etc.

[0103] In one implementation, when the target event includes at least one of measurement events A1 to A6 and measurement events B1 to B2, the trigger indication is used to indicate at least one of the following information:

[0104] Predicting whether the target event is triggered;

[0105] The predicted time point when the target event is triggered;

[0106] A time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output; for example, the target event is triggered after the time length has elapsed since the trigger indication is output;

[0107] The identifier of the triggered cell;

[0108] A predicted cell value of the serving cell corresponding to the time point when the target event is triggered; the base station may refer to the cell prediction value when making relevant decisions;

[0109] The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

[0110] In one implementation, in this step, the terminal periodically obtains a trigger indication of the target event output by the target AI model.

[0111] The prediction method provided in the embodiment of the present application is to input the input parameters associated with the target event into the target artificial intelligence AI model through the terminal, and the terminal obtains the trigger indication of the target event output by the target AI model. The terminal can consider more factors to predict the target event through the AI ​​model, thereby avoiding the base station determining whether to execute the target operation (such as cell switching, secondary cell addition, secondary cell release, etc.) based only on the downlink signal, which may lead to inaccurate timing of execution of the target operation (for example, too early or too late), poor execution performance of the target operation, and other problems.

[0112] As shown in FIG3 , an embodiment of the present application provides a prediction method 300. The method may be executed by a terminal device. In other words, the method may be executed by software or hardware installed on the terminal device. The method includes the following steps:

[0113] S300: The terminal receives a predicted configuration or a reported configuration from a network device.

[0114] The prediction configuration is used to instruct the terminal to obtain a trigger indication regarding the target event based on the target AI model, and the reporting configuration is used to instruct the terminal to report the target event.

[0115] The prediction configuration includes at least one of the following:

[0116] First indication information, where the first indication information is used to instruct the terminal to obtain a trigger indication about the target event based on the target AI model, that is, the first indication information may be used to instruct the UE to predict the target event based on the AI ​​model; when the target event is a handover event, the first indication information may be used to instruct the UE to predict the handover event based on the AI ​​model; when the target event includes at least one of A1 to A6 measurement events and B1 to B2 measurement events, the first indication information is used to instruct the UE to predict the corresponding Ax / Bx event based on the AI ​​model;

[0117] second indication information, where the second indication information is used to indicate a predicted frequency or a frequency list;

[0118] The target AI model predicts the duration information of the target event; that is, the duration range information predicted by the AI ​​model, that is, predicting the target event within the duration range. When the target event includes a switching event, predicting the switching event within the duration range; when the target event includes at least one of the A1 to A6 measurement events and the B1 to B2 measurement events, instructing the target AI model to predict the duration information of the target event, that is, predicting the Ax / Bx event within the duration range;

[0119] Configuration of the first condition: when the first condition is met, the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model; the UE starts AI model inference when the first condition is met;

[0120] A first duration, where the first duration is used to indicate a period for obtaining a trigger indication of the target event output by the target AI model, or in other words, the first duration is used to indicate a period for the target AI model to perform inference;

[0121] Predicted frequency or frequency list; the UE predicts whether the cell at the frequency or the frequency in the frequency list can be used as a candidate target cell corresponding to the target event;

[0122] Predicted cell or cell list, the UE predicts whether the cell or the cell in the cell list can be used as a candidate target cell corresponding to the target event;

[0123] The frequency blacklist excludes cells corresponding to the frequencies in the blacklist as candidate target cells corresponding to the target event.

[0124] The blacklist of cells means excluding cells in the blacklist as candidate target cells corresponding to the target event.

[0125] Thus, the terminal is explicitly or implicitly instructed to obtain a trigger indication regarding the target event based on the target AI model.

[0126] In one implementation, the reporting configuration is used to indicate at least one of the following:

[0127] When the trigger indication indicates that the target event is triggered, reporting associated information of the target event;

[0128] The maximum number of cells associated with the target event is reported. The cells associated with the target event are the cells that trigger the target event.

[0129] Thus, the terminal is explicitly or implicitly instructed to report the prediction result of whether the target event is triggered.

[0130] In one implementation, the prediction configuration is a measurement configuration measConfig. In one implementation, the reporting configuration is the measConfig.

[0131] S302: The terminal inputs the input parameters associated with the target event into the target artificial intelligence AI model.

[0132] This step can be described using the same steps as those in the embodiment of FIG2a , and will not be described again here.

[0133] S304: The terminal obtains a trigger indication of the target event output by the target AI model.

[0134] This step can be described using the same steps as those in the embodiment of FIG2a , and will not be described again here.

[0135] S306: The terminal sends first information to the network device.

[0136] The first information is used to indicate that the target event is triggered. Optionally, the first information may explicitly indicate that the target event is triggered. Optionally, the first information may implicitly indicate that the target event is triggered, and the first information is further used to indicate at least one of the following:

[0137] The target event is triggered based on the prediction of the indication information;

[0138] The predicted time point when the target event is triggered;

[0139] Time length, which is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output; this time length is used to indicate that it is recommended to execute the target event after this time length; for example, if the target event is a handover and the time length is 1 second, it means that the handover will be executed 1 second from now;

[0140] The predicted cell prediction value of the serving cell corresponding to the time point when the target event is triggered; the cell prediction value can be used as a reference for the base station to make a handover decision.

[0141] The reason why the target event is triggered;

[0142] The cell identifier associated with the target event; optionally, the cell identifier may also include frequency information corresponding to the cell, and may also include frequency information of one or more candidate target cells. The multiple candidate target cells may be sorted according to priority, for example, a higher priority is given to a cell that is sorted earlier;

[0143] A cell prediction value corresponding to the cell associated with the target event;

[0144] Beam information corresponding to the cell associated with the target event;

[0145] A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered;

[0146] The beam information corresponding to the cell associated with the target event at the time the target event is triggered is used by the base station to allocate associated RACH resources. This beam information can be output by the target AI model, or the target AI model can output the target cell, and another AI model can output the best beam information for the target cell.

[0147] In some implementations, after the entry condition of the event is met, it is necessary to wait for a trigger observation time (TimeToTrigger, TTT) before reporting the measurement report to determine whether the entry condition of the event is continuously met during the TTT. In one implementation, in response to obtaining the trigger indication, the terminal skips the TTT to send the first information to the network device. After obtaining that the handover event is triggered, the UE does not need to wait for the TTT time and can immediately send the first information to the base station.

[0148] In one implementation, the terminal sends a measurement report message to the network device, where the measurement report message includes the first information. In other words, the first information is carried in the measurement report message.

[0149] After receiving the first information, the base station can make a judgment based on the first information, such as deciding whether to execute the target event, the time or method of executing the target event, etc. For example, executing the target event at the execution time indicated in the first information, executing before or after the execution time indicated in the first information, etc. When the target event is a switching event, the method of executing the target event can be, for example, which cell to switch to. Because the UE has more information, it can consider more factors (such as downlink signal factors, uplink signal factors, data transmission factors, etc.) based on the AI ​​model to predict switching events or switching suggestions, thereby overcoming the limitations of existing switching based on A3 or A5 and improving mobility performance.

[0150] The prediction method provided in the embodiment of the present application is to input the input parameters associated with the target event into the target artificial intelligence AI model through the terminal, and the terminal obtains the trigger indication of the target event output by the target AI model. The terminal can consider more factors to predict the target event through the AI ​​model, thereby avoiding the base station determining whether to perform the target operation (such as cell switching, secondary cell addition, secondary cell release, etc.) based only on the downlink signal, which may lead to inaccurate timing of the target operation execution (for example, too early or too late), poor execution performance of the target operation, and other problems. In addition, by receiving the prediction configuration from the network device, the terminal is displayed or implicitly instructed to obtain the trigger indication of the target event based on the target AI model. The first information is sent to the network device by the terminal to report the prediction result.

[0151] The prediction method according to an embodiment of the present application is described in detail above with reference to Figures 2a to 3. The communication method according to another embodiment of the present application will be described in detail below with reference to Figure 4. It will be understood that the interaction between the network device and the terminal device described from the network device side is the same as the description of the terminal device side in the method shown in Figures 2a to 3. To avoid repetition, the relevant description is appropriately omitted.

[0152] FIG4 is a flow chart of a method for implementing communication according to an embodiment of the present application, which can be applied on a network device side. As shown in FIG4 , the method 400 includes:

[0153] S402: The network device receives first information from the terminal.

[0154] In one implementation, the first information is used to indicate that a target event is triggered, and the target event is predicted by the terminal based on a target AI model.

[0155] The target event is a measurement event, and the measurement event includes at least one of a cell handover measurement event, a secondary cell addition measurement event, and a secondary cell release measurement event.

[0156] In one implementation, the measurement event includes at least one of: A1 to A6 measurement events and B1 to B2 measurement events.

[0157] In one implementation, the target event is a suggestion event, and the suggestion event includes at least one of a cell switching suggestion, a secondary cell addition suggestion, and a secondary cell release suggestion.

[0158] In one implementation, the first information is further used to indicate at least one of the following:

[0159] The target event is triggered based on the prediction of the indication information;

[0160] The predicted time point when the target event is triggered;

[0161] Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output;

[0162] a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered;

[0163] The reason why the target event is triggered;

[0164] an identifier of a cell associated with the target event;

[0165] A cell prediction value corresponding to the cell associated with the target event;

[0166] Beam information corresponding to the cell associated with the target event;

[0167] A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered;

[0168] The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

[0169] In one implementation, the network device receives a measurement report message from the terminal, where the measurement report message includes the first information.

[0170] In one implementation, after the network device receives the first information, the network device performs a switching decision or a carrier management operation based on the first information.

[0171] The communication method provided in the embodiment of the present application enables the terminal to predict the target event by considering more factors through the AI ​​model, avoiding the base station determining whether to perform the target operation (such as cell switching, secondary cell addition, secondary cell release, etc.) based only on the downlink signal, which may lead to inaccurate timing of execution of the target operation (for example, too early or too late), poor execution performance of the target operation, and other problems, and sends the first information to the network device to report the prediction result.

[0172] FIG5 is a flow chart of a method for implementing communication according to an embodiment of the present application, which can be applied on a network device side. As shown in FIG5 , the method 500 includes:

[0173] S500: The network device sends a predicted configuration or a reported configuration to the terminal.

[0174] The prediction configuration is used to instruct the terminal to obtain a trigger indication regarding the target event output by the target AI model, and the reporting configuration is used to instruct the terminal to report the target event.

[0175] The trigger indication is used to indicate at least one of the following information:

[0176] Predicting whether the target event is triggered;

[0177] The predicted time point when the target event is triggered;

[0178] Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output;

[0179] a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered;

[0180] The reason why the target event is triggered;

[0181] an identifier of a cell associated with the target event;

[0182] A cell prediction value corresponding to the cell associated with the target event;

[0183] Beam information corresponding to the cell associated with the target event;

[0184] A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered;

[0185] The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

[0186] In one implementation, the reason includes at least one of the following reasons:

[0187] Downlink signal reason;

[0188] Uplink signal reason;

[0189] The reason for data transmission.

[0190] In one implementation, the prediction configuration is used to instruct the terminal to input at least one of the following parameters into the target AI model:

[0191] The target AI model predicts the duration information of the target event;

[0192] location information of the terminal;

[0193] Moving speed information of the terminal;

[0194] Moving direction information of the terminal;

[0195] historical measurement information of the terminal;

[0196] measurement information of the terminal;

[0197] Predicted frequency;

[0198] Predicted cell;

[0199] Frequency blacklist;

[0200] The community’s blacklist;

[0201] The triggering condition of the target event;

[0202] The measurement event type of the target event;

[0203] Configuration parameters of the measurement event of the target event.

[0204] In one implementation, the prediction configuration is used to instruct the terminal to input input parameters associated with the target event into a target artificial intelligence AI model when a first condition is met;

[0205] The first condition includes at least one of the following:

[0206] The signal quality of the serving cell of the terminal is less than or equal to a first threshold;

[0207] The amount of data cached by the terminal is greater than or equal to a second threshold;

[0208] A first timer times out, where the first timer is a periodic timer.

[0209] In one implementation, the prediction configuration is used to instruct the terminal to periodically obtain a trigger indication of the target event output by the target AI model.

[0210] In one implementation, the prediction configuration includes at least one of the following:

[0211] First indication information, where the first indication information is used to instruct the terminal to obtain a trigger indication regarding the target event based on the target AI model;

[0212] Second indication information, where the second indication information is used to indicate a predicted frequency point;

[0213] The target AI model predicts the duration information of the target event;

[0214] Configuration of a first condition, where, when the first condition is met, the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model;

[0215] A first duration, where the first duration is used to indicate a period for obtaining a trigger indication of the target event output by the target AI model, or in other words, the first duration is used to indicate a period for the target AI model to perform inference;

[0216] Predicted frequency;

[0217] Predicted cell;

[0218] Frequency blacklist;

[0219] The community’s blacklist.

[0220] In one implementation, the reporting configuration is used to indicate at least one of the following:

[0221] When the trigger indication indicates that the target event is triggered, reporting associated information of the target event;

[0222] Report the maximum number of cells associated with the target event.

[0223] In one implementation, the prediction configuration is a measurement configuration measConfig, or the reporting configuration is the measConfig.

[0224] S502: The network device receives first information from the terminal.

[0225] The first information is used to indicate that a target event is triggered, and the target event is predicted by the terminal based on a target AI model.

[0226] This step can be described using the same steps as those in the embodiment of FIG. 4 , and will not be described again here.

[0227] The embodiment of the present application enables the terminal to predict the target event based on more factors required for prediction through the AI ​​model, avoiding the base station determining whether to perform the target operation (such as cell switching, secondary cell addition, secondary cell release, etc.) based only on the downlink signal, which may lead to inaccurate timing of execution of the target operation (for example, too early or too late), poor execution performance of the target operation, and other problems. In addition, the prediction configuration is sent by the network device to explicitly or implicitly instruct the terminal to obtain a trigger indication about the target event based on the target AI model, and the first information is sent to the network device by the terminal to report the prediction result.

[0228] It should be noted that the prediction method provided in the embodiment of the present application can be executed by a prediction device. In the embodiment of the present application, the method of executing loading prediction by a prediction device is taken as an example to illustrate the prediction device provided in the embodiment of the present application.

[0229] FIG6 is a schematic diagram of the structure of a prediction device according to an embodiment of the present application. As shown in FIG6 , the prediction device 600 includes: an input module 610 and an acquisition module 620 .

[0230] The input module 610 is used to input the input parameters associated with the target event into the target artificial intelligence AI model; the acquisition module 620 is used to obtain the trigger indication of the target event output by the target AI model.

[0231] The target event is a measurement event, and the measurement event includes at least one of a cell handover measurement event, a secondary cell addition measurement event, and a secondary cell release measurement event.

[0232] In one implementation, the target event includes at least one of measurement events A1 to A6 and measurement events B1 to B2.

[0233] In one implementation, the target event is a suggestion event, and the suggestion event includes at least one of a cell switching suggestion, a secondary cell addition suggestion, and a secondary cell release suggestion.

[0234] In one implementation, the trigger indication is used to indicate at least one of the following information:

[0235] Predicting whether the target event is triggered;

[0236] The predicted time point when the target event is triggered;

[0237] Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output;

[0238] a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered;

[0239] The reason why the target event is triggered;

[0240] an identifier of a cell associated with the target event;

[0241] A cell prediction value corresponding to the cell associated with the target event;

[0242] Beam information corresponding to the cell associated with the target event;

[0243] A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered;

[0244] The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

[0245] In one implementation, the reason includes at least one of the following reasons:

[0246] Downlink signal reason;

[0247] Uplink signal reason;

[0248] The reason for data transmission.

[0249] In one implementation, the input parameter associated with the target event includes at least one of the following:

[0250] The target AI model predicts the duration information of the target event;

[0251] location information of the terminal;

[0252] Moving speed information of the terminal;

[0253] Moving direction information of the terminal;

[0254] historical measurement information of the terminal;

[0255] measurement information of the terminal;

[0256] Predicted frequency;

[0257] Predicted cell;

[0258] Frequency blacklist;

[0259] The community’s blacklist;

[0260] The triggering condition of the target event;

[0261] The measurement event type of the target event;

[0262] Configuration parameters of the measurement event of the target event.

[0263] In one implementation, the input module 610 is configured to, when a first condition is met, cause the terminal to input input parameters associated with the target event into the target artificial intelligence AI model;

[0264] The first condition includes at least one of the following:

[0265] The signal quality of the serving cell of the terminal is less than or equal to a first threshold;

[0266] The amount of data cached by the terminal is greater than or equal to a second threshold;

[0267] A first timer times out, where the first timer is a periodic timer.

[0268] In one implementation, the acquisition module 620 is used by the terminal to periodically acquire a trigger indication of the target event output by the target AI model.

[0269] In one implementation, the device 600 also includes: a receiving module, configured to receive a prediction configuration or a reporting configuration from a network device before the terminal inputs the input parameters associated with the target event into the target artificial intelligence AI model, wherein the prediction configuration is used to instruct the terminal to obtain a trigger indication regarding the target event based on the target AI model, and the reporting configuration is used to instruct the terminal to report the target event.

[0270] In one implementation, the prediction configuration includes at least one of the following:

[0271] First indication information, where the first indication information is used to instruct the terminal to obtain a trigger indication regarding the target event based on the target AI model;

[0272] Second indication information, where the second indication information is used to indicate a predicted frequency point;

[0273] The target AI model predicts the duration information of the target event;

[0274] Configuration of a first condition, where, when the first condition is met, the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model;

[0275] A first duration, where the first duration is used to indicate a period for obtaining a trigger indication of the target event output by the target AI model, or in other words, the first duration is used to indicate a period for the target AI model to perform inference;

[0276] Predicted frequency;

[0277] Predicted cell;

[0278] Frequency blacklist;

[0279] The community’s blacklist.

[0280] In one implementation, the reporting configuration is used to indicate at least one of the following:

[0281] When the trigger indication indicates that the target event is triggered, reporting associated information of the target event;

[0282] Report the maximum number of cells associated with the target event.

[0283] In one implementation, the prediction configuration is a measurement configuration measConfig, or the reporting configuration is the measConfig.

[0284] In one implementation, the device 600 further includes a sending module, which sends first information to a network device after the terminal obtains a trigger indication of the target event output by the target AI model, wherein the first information is used to indicate that the target event is triggered.

[0285] In one implementation, the first information is further used to indicate at least one of the following:

[0286] The target event is triggered based on the prediction of the indication information;

[0287] The predicted time point when the target event is triggered;

[0288] Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the current time;

[0289] a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered;

[0290] The reason why the target event is triggered;

[0291] an identifier of a cell associated with the target event;

[0292] A cell prediction value corresponding to the cell associated with the target event;

[0293] Beam information corresponding to the cell associated with the target event;

[0294] A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered;

[0295] The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

[0296] In one implementation, the sending module is configured to, in response to obtaining the trigger indication, cause the terminal to skip the trigger observation time TimeToTrigger and send the first information to the network device.

[0297] In one implementation, the sending module is configured to send a measurement report message to the network device, where the measurement report message includes the first information.

[0298] The prediction device 600 in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be a device other than a terminal. Exemplarily, the terminal can include but is not limited to the types of terminals 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application. The prediction device 600 provided in the embodiment of the present application can implement the various processes implemented by the method embodiments of Figures 2a to 3 and achieve the same technical effects. To avoid repetition, they will not be described here.

[0299] It should be noted that the communication method provided in the embodiment of the present application can be executed by a communication device. In the embodiment of the present application, the communication device provided in the embodiment of the present application is explained by taking the method of executing loading communication by a communication device as an example.

[0300] FIG7 is a schematic diagram of the structure of a communication device according to an embodiment of the present application. As shown in FIG7 , the communication device 700 includes: a processing module 710 .

[0301] The processing module 710 is used to receive first information from the terminal, where the first information is used to indicate that a target event is triggered, and the target event is predicted by the terminal based on a target AI model.

[0302] In one implementation, the target event is a measurement event, and the measurement event includes at least one of a cell handover measurement event, a secondary cell addition measurement event, and a secondary cell release measurement event.

[0303] In one implementation, the measurement event includes at least one of: A1 to A6 measurement events and B1 to B2 measurement events.

[0304] In one implementation, the target event is a suggestion event, and the suggestion event includes at least one of a cell switching suggestion, a secondary cell addition suggestion, and a secondary cell release suggestion.

[0305] In one implementation, the first information is further used to indicate at least one of the following:

[0306] The target event is triggered based on the prediction of the indication information;

[0307] The predicted time point when the target event is triggered;

[0308] Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output;

[0309] a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered;

[0310] The reason why the target event is triggered;

[0311] an identifier of a cell associated with the target event;

[0312] A cell prediction value corresponding to the cell associated with the target event;

[0313] Beam information corresponding to the cell associated with the target event;

[0314] A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered;

[0315] The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

[0316] In one implementation, the processing module 710 is configured to receive a measurement report message from a terminal, where the measurement report message includes the first information.

[0317] In one implementation, the apparatus 700 further includes a decision module configured to perform a handover decision or a carrier management operation based on the first information after the network device receives the first information.

[0318] In one implementation, the processing module 710 is used to send a prediction configuration or a reporting configuration to the terminal before the network device receives the first information. The prediction configuration is used to instruct the terminal to obtain a trigger indication of the target event output by the target AI model, and the reporting configuration is used to instruct the terminal to report the target event.

[0319] In one implementation, the trigger indication is used to indicate at least one of the following information:

[0320] Predicting whether the target event is triggered;

[0321] The predicted time point when the target event is triggered;

[0322] Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output;

[0323] a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered;

[0324] The reason why the target event is triggered;

[0325] an identifier of a cell associated with the target event;

[0326] A cell prediction value corresponding to the cell associated with the target event;

[0327] Beam information corresponding to the cell associated with the target event;

[0328] A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered;

[0329] The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

[0330] In one implementation, the reason includes at least one of the following reasons:

[0331] Downlink signal reason;

[0332] Uplink signal reason;

[0333] The reason for data transmission.

[0334] In one implementation, the prediction configuration is used to instruct the terminal to input at least one of the following parameters into the target AI model:

[0335] The target AI model predicts the duration information of the target event;

[0336] location information of the terminal;

[0337] Moving speed information of the terminal;

[0338] Moving direction information of the terminal;

[0339] historical measurement information of the terminal;

[0340] measurement information of the terminal;

[0341] Predicted frequency;

[0342] Predicted cell;

[0343] Frequency blacklist;

[0344] The community’s blacklist;

[0345] The triggering condition of the target event;

[0346] The measurement event type of the target event;

[0347] Configuration parameters of the measurement event of the target event.

[0348] In one implementation, the prediction configuration is used to instruct the terminal to input input parameters associated with the target event into a target artificial intelligence AI model when a first condition is met;

[0349] The first condition includes at least one of the following:

[0350] The signal quality of the serving cell of the terminal is less than or equal to a first threshold;

[0351] The amount of data cached by the terminal is greater than or equal to a second threshold;

[0352] A first timer times out, where the first timer is a periodic timer.

[0353] In one implementation, the prediction configuration is used to instruct the terminal to periodically obtain a trigger indication of the target event output by the target AI model.

[0354] In one implementation, the prediction configuration includes at least one of the following:

[0355] First indication information, where the first indication information is used to instruct the terminal to obtain a trigger indication regarding the target event based on the target AI model;

[0356] Second indication information, where the second indication information is used to indicate a predicted frequency point;

[0357] The target AI model predicts the duration information of the target event;

[0358] Configuration of a first condition, where, when the first condition is met, the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model;

[0359] A first duration, where the first duration is used to indicate a period for obtaining a trigger indication of the target event output by the target AI model, or in other words, the first duration is used to indicate a period for the target AI model to perform inference;

[0360] Predicted frequency;

[0361] Predicted cell;

[0362] Frequency blacklist;

[0363] The community’s blacklist.

[0364] In one implementation, the reporting configuration is used to indicate at least one of the following:

[0365] When the trigger indication indicates that the target event is triggered, reporting associated information of the target event;

[0366] Report the maximum number of cells associated with the target event.

[0367] In one implementation, the prediction configuration is a measurement configuration measConfig, or the reporting configuration is the measConfig.

[0368] The communication device 700 in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be a device other than a terminal. For example, the terminal can include but is not limited to the types of terminals 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application. The communication device 700 provided in the embodiment of the present application can implement the various processes implemented by the method embodiments of Figures 4 to 5 and achieve the same technical effects. To avoid repetition, they are not described here.

[0369] Specifically, embodiments of the present application also provide a network-side device. As shown in Figure 8, the network device 800 includes an antenna 801, a radio frequency device 802, a baseband device 803, a processor 804, and a memory 805. Antenna 801 is connected to radio frequency device 802. In the uplink direction, radio frequency device 802 receives information via antenna 801 and sends the received information to baseband device 803 for processing. In the downlink direction, baseband device 803 processes the information to be transmitted and sends it to radio frequency device 802. Radio frequency device 802 processes the received information and then sends it through antenna 801.

[0370] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 803 , which includes a baseband processor.

[0371] The baseband device 803 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in Figure 8, one of which is, for example, a baseband processor, which is connected to the memory 805 through a bus interface to call the program in the memory 805 and execute the network device operations shown in the above method embodiment.

[0372] The network side device may further include a network interface 806, which is, for example, a common public radio interface (CPRI).

[0373] Specifically, the network side device 800 of the embodiment of the present application also includes: instructions or programs stored in the memory 805 and can be run on the processor 804. The processor 804 calls the instructions or programs in the memory 805 to execute the method of executing the steps shown in Figures 4-5 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0374] FIG9 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application. The terminal device 900 includes, but is not limited to, at least some of the components including 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 a processor 1010.

[0375] Those skilled in the art will appreciate that the terminal device 1000 may further include a power source (such as a battery) to power various components. The power source 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 device structure shown in the figure does not limit the terminal device. The terminal device may include more or fewer components than shown, or may combine certain components or arrange the components differently, which will not be described in detail here.

[0376] It should be understood that in an 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 a static picture or video acquired by an image capture device (such as a camera) in a video capture mode or an 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 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 an operating stick, which will not be repeated here.

[0377] 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.

[0378] 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, wherein 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, or the memory 1009 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct memory bus random access memory (DRRAM). The memory 1009 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0379] 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.

[0380] Among them, the processor 1010 is used to input the input parameters associated with the target event into the target artificial intelligence AI model; and obtain the trigger indication of the target event output by the target AI model.

[0381] In one implementation, the target event is a measurement event, and the measurement event includes at least one of a cell handover measurement event, a secondary cell addition measurement event, and a secondary cell release measurement event.

[0382] In one implementation, the target event includes at least one of measurement events A1 to A6 and measurement events B1 to B2.

[0383] In one implementation, the target event is a suggestion event, and the suggestion event includes at least one of a cell switching suggestion, a secondary cell addition suggestion, and a secondary cell release suggestion.

[0384] In one implementation, the trigger indication is used to indicate at least one of the following information:

[0385] Predicting whether the target event is triggered;

[0386] The predicted time point when the target event is triggered;

[0387] Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output;

[0388] a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered;

[0389] The reason why the target event is triggered;

[0390] an identifier of a cell associated with the target event;

[0391] A cell prediction value corresponding to the cell associated with the target event;

[0392] Beam information corresponding to the cell associated with the target event;

[0393] A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered;

[0394] The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

[0395] In one implementation, the reason includes at least one of the following reasons:

[0396] Downlink signal reason;

[0397] Uplink signal reason;

[0398] The reason for data transmission.

[0399] In one implementation, the input parameter associated with the target event includes at least one of the following:

[0400] The target AI model predicts the duration information of the target event;

[0401] location information of the terminal;

[0402] Moving speed information of the terminal;

[0403] Moving direction information of the terminal;

[0404] historical measurement information of the terminal;

[0405] measurement information of the terminal;

[0406] Predicted frequency;

[0407] Predicted cell;

[0408] Frequency blacklist;

[0409] The community’s blacklist;

[0410] The triggering condition of the target event;

[0411] The measurement event type of the target event;

[0412] Configuration parameters of the measurement event of the target event.

[0413] In one implementation, the terminal inputs input parameters associated with the target event into the target artificial intelligence (AI) model, including:

[0414] When the first condition is met, the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model;

[0415] The first condition includes at least one of the following:

[0416] The signal quality of the serving cell of the terminal is less than or equal to a first threshold;

[0417] The amount of data cached by the terminal is greater than or equal to a second threshold;

[0418] A first timer times out, where the first timer is a periodic timer.

[0419] In one implementation, the terminal obtains a trigger indication of the target event output by the target AI model, including:

[0420] The terminal periodically obtains a trigger indication of the target event output by the target AI model.

[0421] In one implementation, before the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model, the method further includes:

[0422] The terminal receives a prediction configuration or a reporting configuration from a network device, where the prediction configuration is used to instruct the terminal to obtain a trigger indication regarding the target event based on the target AI model, and the reporting configuration is used to instruct the terminal to report the target event.

[0423] In one implementation, the prediction configuration includes at least one of the following:

[0424] First indication information, where the first indication information is used to instruct the terminal to obtain a trigger indication regarding the target event based on the target AI model;

[0425] Second indication information, where the second indication information is used to indicate a predicted frequency point;

[0426] The target AI model predicts the duration information of the target event;

[0427] Configuration of a first condition, where, when the first condition is met, the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model;

[0428] A first duration, where the first duration is used to indicate a period for obtaining a trigger indication of the target event output by the target AI model, or in other words, the first duration is used to indicate a period for the target AI model to perform inference;

[0429] Predicted frequency;

[0430] Predicted cell;

[0431] Frequency blacklist;

[0432] The community’s blacklist.

[0433] In one implementation, the reporting configuration is used to indicate at least one of the following:

[0434] When the trigger indication indicates that the target event is triggered, reporting associated information of the target event;

[0435] Report the maximum number of cells associated with the target event.

[0436] In one implementation, the prediction configuration is a measurement configuration measConfig, or the reporting configuration is the measConfig.

[0437] In one implementation, after the terminal obtains the trigger indication of the target event output by the target AI model, the method further includes:

[0438] The terminal sends first information to the network device, where the first information is used to indicate that the target event is triggered.

[0439] In one implementation, the first information is further used to indicate at least one of the following:

[0440] The target event is triggered based on the prediction of the indication information;

[0441] The predicted time point when the target event is triggered;

[0442] Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output;

[0443] a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered;

[0444] The reason why the target event is triggered;

[0445] an identifier of a cell associated with the target event;

[0446] A cell prediction value corresponding to the cell associated with the target event;

[0447] Beam information corresponding to the cell associated with the target event;

[0448] A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered;

[0449] The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

[0450] In one implementation, the terminal sending the first information to the network device includes:

[0451] In response to obtaining the trigger indication, the terminal skips the trigger observation time TimeToTrigger and sends the first information to the network device.

[0452] In one implementation, the terminal sending the first information to the network device includes:

[0453] The terminal sends a measurement report message to the network device, and the measurement report message includes the first information. An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of at least one embodiment of the method embodiments of Figures 2a-5 above is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0454] 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.

[0455] 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 at least one embodiment of the method embodiments of Figures 2a to 5 above, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0456] 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.

[0457] 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 at least one embodiment in the method embodiments of Figures 2a to 5 above, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0458] An embodiment of the present application also provides a communication system, including: a terminal and a network-side device, wherein the terminal can be used to execute the steps of the method embodiment of Figure 2a or Figure 3 as described above, and the network-side device can be used to execute the steps of the method embodiment of Figure 4 or Figure 5.

[0459] 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 statement "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 noted 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.

[0460] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0461] 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 without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. A method for prediction, comprising: The terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model; The terminal obtains a trigger indication of the target event output by the target AI model.

2. The method according to claim 1, wherein The target event is a measurement event, and the measurement event includes at least one of a cell handover measurement event, a secondary cell addition measurement event, and a secondary cell release measurement event.

3. The method according to claim 1 or 2, wherein The target event includes at least one of measurement events A1 to A6 and measurement events B1 to B2.

4. The method according to claim 1, wherein The target event is a suggestion event, and the suggestion event includes at least one of a cell switching suggestion, a secondary cell adding suggestion, and a secondary cell releasing suggestion.

5. The method according to any one of claims 1 to 4, wherein: The trigger indication is used to indicate at least one of the following information: Predicting whether the target event is triggered; The predicted time point when the target event is triggered; Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output; a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered; The reason why the target event is triggered; an identifier of a cell associated with the target event; A cell prediction value corresponding to the cell associated with the target event; Beam information corresponding to the cell associated with the target event; A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered; The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

6. The method according to claim 5, wherein: The reasons include at least one of the following: Downlink signal reason; Uplink signal reason; The reason for data transmission.

7. The method according to any one of claims 1 to 6, wherein: The input parameters associated with the target event include at least one of the following: The target AI model predicts the duration information of the target event; location information of the terminal; Moving speed information of the terminal; Moving direction information of the terminal; historical measurement information of the terminal; measurement information of the terminal; Predicted frequency; Predicted cell; Frequency blacklist; The community’s blacklist; The triggering condition of the target event; The measurement event type of the target event; Configuration parameters of the measurement event of the target event.

8. The method according to any one of claims 1 to 7, wherein: The terminal inputs input parameters associated with the target event into the target artificial intelligence (AI) model, including: When the first condition is met, the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model; The first condition includes at least one of the following: The signal quality of the serving cell of the terminal is less than or equal to a first threshold; The amount of data cached by the terminal is greater than or equal to a second threshold; A first timer times out, where the first timer is a periodic timer.

9. The method according to any one of claims 1 to 8, wherein: The terminal obtains a trigger indication of the target event output by the target AI model, including: The terminal periodically obtains a trigger indication of the target event output by the target AI model.

10. The method according to any one of claims 1 to 9, wherein: Before the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model, the method further includes: The terminal receives a prediction configuration or a reporting configuration from a network device, where the prediction configuration is used to instruct the terminal to obtain a trigger indication regarding the target event based on the target AI model, and the reporting configuration is used to instruct the terminal to report the target event.

11. The method according to claim 10, wherein: The prediction configuration includes at least one of the following: First indication information, where the first indication information is used to instruct the terminal to obtain a trigger indication regarding the target event based on the target AI model; Second indication information, where the second indication information is used to indicate a predicted frequency point; The target AI model predicts the duration information of the target event; Configuration of a first condition, where, when the first condition is met, the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model; A first duration, where the first duration is used to indicate a period for obtaining a trigger indication of the target event output by the target AI model; Predicted frequency; Predicted cell; Frequency blacklist; The community’s blacklist.

12. The method of claim 10, wherein: The reporting configuration is used to indicate at least one of the following: When the trigger indication indicates that the target event is triggered, reporting associated information of the target event; Report the maximum number of cells associated with the target event.

13. The method of claim 10, wherein: The prediction configuration is the measurement configuration measConfig, or the reporting configuration is the measConfig.

14. The method according to any one of claims 1 to 13, wherein: After the terminal obtains the trigger indication of the target event output by the target AI model, the method further includes: The terminal sends first information to the network device, where the first information is used to indicate that the target event is triggered.

15. The method of claim 14, wherein: The first information is further used to indicate at least one of the following: The target event is triggered based on the prediction of the indication information; The predicted time point when the target event is triggered; Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output; a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered; The reason why the target event is triggered; an identifier of a cell associated with the target event; A cell prediction value corresponding to the cell associated with the target event; Beam information corresponding to the cell associated with the target event; A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered; The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

16. The method according to any one of claims 14 to 15, wherein: The terminal sending first information to the network device includes: In response to obtaining the trigger indication, the terminal skips the trigger observation time TimeToTrigger and sends the first information to the network device.

17. The method according to any one of claims 14 to 16, wherein: The terminal sending first information to the network device includes: The terminal sends a measurement report message to the network device, where the measurement report message includes the first information.

18. A method of communication, the method comprising: The network device receives first information from the terminal, where the first information is used to indicate that a target event is triggered, and the target event is predicted by the terminal based on a target AI model.

19. The method of claim 18, wherein: The target event is a measurement event, and the measurement event includes at least one of a cell handover measurement event, a secondary cell addition measurement event, and a secondary cell release measurement event.

20. The method according to claim 18 or 19, wherein The measurement event includes at least one of measurement events A1 to A6 and measurement events B1 to B2.

21. The method of claim 18, wherein: The target event is a suggestion event, and the suggestion event includes at least one of a cell switching suggestion, a secondary cell adding suggestion, and a secondary cell releasing suggestion.

22. The method of claim 18, wherein: The first information is further used to indicate at least one of the following: The target event is triggered based on the prediction of the indication information; The predicted time point when the target event is triggered; Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output; a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered; The reason why the target event is triggered; an identifier of a cell associated with the target event; A cell prediction value corresponding to the cell associated with the target event; Beam information corresponding to the cell associated with the target event; A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered; The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

23. The method according to any one of claims 18 to 22, wherein: The network device receives first information from the terminal, including: The network device receives a measurement report message from the terminal, where the measurement report message includes the first information.

24. The method according to any one of claims 18 to 23, wherein: After the network device receives the first information, the method further includes: The network device performs a switching decision or a carrier management operation based on the first information.

25. The method according to any one of claims 18 to 24, wherein Before the network device receives the first information, the method further includes: The network device sends a prediction configuration or a reporting configuration to the terminal, where the prediction configuration is used to instruct the terminal to obtain a trigger indication of the target event output by the target AI model, and the reporting configuration is used to instruct the terminal to report the target event.

26. The method of claim 25, wherein: The trigger indication is used to indicate at least one of the following information: Predicting whether the target event is triggered; The predicted time point when the target event is triggered; Time length, where the time length is the time difference between the predicted time point when the target event is triggered and the time when the trigger indication is output; a predicted cell value of the serving cell corresponding to the time point at which the target event is triggered; The reason why the target event is triggered; an identifier of a cell associated with the target event; A cell prediction value corresponding to the cell associated with the target event; Beam information corresponding to the cell associated with the target event; A cell prediction value of the cell associated with the target event corresponding to the time point when the target event is triggered; The cell associated with the target event corresponds to the beam information at the time when the target event is triggered.

27. The method of claim 26, wherein: The reasons include at least one of the following: Downlink signal reason; Uplink signal reason; The reason for data transmission.

28. The method of claim 27, wherein: The prediction configuration is used to instruct the terminal to input at least one of the following parameters into the target AI model: The target AI model predicts the duration information of the target event; location information of the terminal; Moving speed information of the terminal; Moving direction information of the terminal; historical measurement information of the terminal; measurement information of the terminal; Predicted frequency; Predicted cell; Frequency blacklist; The community’s blacklist; The triggering condition of the target event; The measurement event type of the target event; Configuration parameters of the measurement event of the target event.

29. The method according to any one of claims 25 to 28, wherein: The prediction configuration is used to instruct the terminal to input the input parameters associated with the target event into the target artificial intelligence AI model when the first condition is met; The first condition includes at least one of the following: The signal quality of the serving cell of the terminal is less than or equal to a first threshold; The amount of data cached by the terminal is greater than or equal to a second threshold; A first timer times out, where the first timer is a periodic timer.

30. The method according to any one of claims 25 to 29, wherein: The prediction configuration is used to instruct the terminal to periodically obtain a trigger indication of the target event output by the target AI model.

31. The method of claim 30, wherein: The prediction configuration includes at least one of the following: First indication information, where the first indication information is used to instruct the terminal to obtain a trigger indication regarding the target event based on the target AI model; Second indication information, where the second indication information is used to indicate a predicted frequency point; The target AI model predicts the duration information of the target event; Configuration of a first condition, where, when the first condition is met, the terminal inputs the input parameters associated with the target event into the target artificial intelligence (AI) model; A first duration, where the first duration is used to indicate a period for obtaining a trigger indication of the target event output by the target AI model; Predicted frequency; Predicted cell; Frequency blacklist; The community’s blacklist.

32. The method of claim 25, wherein: The reporting configuration is used to indicate at least one of the following: When the trigger indication indicates that the target event is triggered, reporting associated information of the target event; Report the maximum number of cells associated with the target event.

33. The method of claim 25, wherein: The prediction configuration is the measurement configuration measConfig, or the reporting configuration is the measConfig.

34. A prediction device, comprising: An input module, used to input input parameters associated with the target event into the target artificial intelligence (AI) model; An acquisition module is used to obtain a trigger indication of the target event output by the target AI model.

35. A communication device comprising: A processing module is used to receive first information from a terminal, where the first information is used to indicate that a target event is triggered, and the target event is predicted by the terminal based on a target AI model.

36. A terminal comprising a processor and a memory, wherein the memory stores a program or instruction executable on the processor, and wherein the program or instruction, when executed by the processor, implements the steps of the prediction method according to any one of claims 1 to 17.

37. A network side 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, the steps of the communication method according to any one of claims 18 to 33 are implemented.

38. A readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the steps of the prediction method according to any one of claims 1 to 17; or implements the steps of the communication method according to any one of claims 18 to 33.

Images