Information processing method and apparatus, terminal, and network device

Abstract

The present disclosure provides an information processing method and apparatus, a terminal, and a network device. The method comprises: a terminal determines a radio resource management (RRM) measurement result related to a first artificial intelligence (AI) or machine learning (ML) model input; the terminal obtains, on the basis of the RRM measurement result, first information output by a first AI or ML model; and the terminal sends second information to a network device on the basis of the first information, wherein the first information and / or the second information comprise at least one of the following parameters: an RRM prediction result, cell information of a predicted optimal cell; and a first prediction result related to the occurrence of a predicted event.

Description

Information processing method, device, terminal and network equipment

[0001] This disclosure claims priority to the Chinese patent application filed with the China Patent Office on April 3, 2024, with application number 202410403686.2 and application name “Information Processing Method, Device, Terminal and Network Equipment”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present disclosure relates to the field of communication technologies, and in particular to an information processing method, apparatus, terminal, and network equipment. Background Art

[0003] The current handover mechanism involves the terminal (User Equipment, UE) performing measurements and reporting the measurement results. The network device evaluates the measurement results reported by the UE and decides whether to trigger a handover. If the network device decides to trigger a handover, it can send a handover command to the UE. After receiving the handover command, the UE begins handover execution. There is a certain delay in the terminal triggering the reporting of measurement results based on measurement events, and there is also a certain delay in the handover command being sent from the network device to the terminal. This delay may result in the network device not receiving the measurement results reported by the terminal, or the terminal not receiving the handover command sent by the network device, which may lead to handover failure. Summary of the Invention

[0004] The present disclosure provides an information processing method, apparatus, terminal, and network equipment, which solve the problem that the current switching mechanism is prone to switching failure.

[0005] An embodiment of the present disclosure provides an information processing method, including:

[0006] The terminal determines a radio resource management (RRM) measurement result related to a first artificial intelligence (AI) or machine learning (ML) model input;

[0007] The terminal obtains, according to the RRM measurement result, first information output by a first AI or ML model;

[0008] The terminal sends second information to the network device according to the first information;

[0009] The first information and / or the second information includes at least one of the following parameters:

[0010] RRM prediction results;

[0011] Predicting cell information of the optimal cell;

[0012] The first prediction result is related to the occurrence of the predicted event.

[0013] In some embodiments, the terminal determines the second information by at least one of the following methods:

[0014] In a case where the first information includes an RRM prediction result, the terminal determines that the second information includes the RRM prediction result;

[0015] In a case where the first information includes cell information of a predicted optimal cell, the terminal determines that the second information includes the cell information of the predicted optimal cell;

[0016] In a case where the first information includes a first prediction result, the terminal determines that the second information includes the first prediction result;

[0017] In a case where the first information includes an RRM prediction result, the terminal determines, according to the RRM prediction result, the cell information of the predicted optimal cell and / or the first prediction result, and determines that the second information includes the cell information of the predicted optimal cell and / or the first prediction result;

[0018] In a case where the first information includes cell information of a predicted optimal cell, the terminal determines the first prediction result according to the cell information of the predicted optimal cell, and determines that the second information includes the first prediction result.

[0019] In some embodiments, the first information further includes at least one of the following parameters:

[0020] A timestamp corresponding to a prediction result output by the first AI or ML model; wherein the prediction result output by the first AI or ML model includes at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0021] Cell identification information corresponding to the RRM prediction result;

[0022] Beam identification information corresponding to the RRM prediction result.

[0023] In some embodiments, the second information further includes at least one of the following parameters:

[0024] identification information of the first AI or ML model;

[0025] identification information of the AI ​​or ML function corresponding to the first AI or ML model;

[0026] A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0027] The sequence number of the prediction result output by the first AI or ML model corresponding to the timestamp;

[0028] The time interval between the first AI or ML model outputting prediction results;

[0029] The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

[0030] In some embodiments, the timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, Coordinated Universal Time (UTC), Global Positioning System Time (GPST), and a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

[0031] In some embodiments, the first prediction result includes at least one of the following:

[0032] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0033] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0034] The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

[0035] In some embodiments, the terminal determines the second information by at least one of the following methods:

[0036] In a case where the first prediction result includes second indication information, the terminal determines that the second information includes the second indication information;

[0037] In a case where the first prediction result includes third indication information, the terminal determines that the second information includes the third indication information;

[0038] In a case where the first prediction result includes fourth indication information, the terminal determines that the second information includes the fourth indication information;

[0039] In a case where the first prediction result includes second indication information, the terminal determines, based on the second indication information, at least one of the first indication information, the third indication information, and the fourth indication information, and determines that the second information includes at least one of the first indication information, the third indication information, and the fourth indication information;

[0040] In a case where the first prediction result includes third indication information, the terminal determines the first indication information and / or the fourth indication information according to the third indication information, and determines that the second information includes the first indication information and / or the fourth indication information;

[0041] In a case where the first prediction result includes fourth indication information, the terminal determines the first indication information according to the fourth indication information, and determines that the second information includes the first indication information.

[0042] In some embodiments, the information processing method further includes:

[0043] The terminal receives configuration information sent by the network device;

[0044] The terminal sending second information to the network device includes:

[0045] The terminal sends the second information to the network device according to the configuration information;

[0046] The configuration information includes at least one of the following:

[0047] fifth indication information, used to indicate the parameters in the second information reported by the terminal;

[0048] Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result;

[0049] Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition;

[0050] Configuration information of the first condition.

[0051] In some embodiments, the first condition includes at least one of the following:

[0052] At the first predicted time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more predicted time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold;

[0053] At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell;

[0054] At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event;

[0055] The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

[0056] In some embodiments, the information processing method further includes:

[0057] The terminal sends terminal capability information to the network device; wherein the terminal capability information includes at least one of the following:

[0058] Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result;

[0059] Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell;

[0060] The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

[0061] In some embodiments, the triggering conditions for the event triggering reporting include, but are not limited to, at least one of the following:

[0062] The AI ​​or ML model outputs a prediction;

[0063] At the predicted time point, there are cells and / or beams that meet the triggering conditions for measurement reporting;

[0064] In the predicted time period, there are cells and / or beams that meet the triggering conditions for measurement reporting.

[0065] In some embodiments, the information processing method further includes:

[0066] The terminal monitors the inference performance of the first AI or ML model and determines a performance monitoring result;

[0067] The terminal performs at least one of the following operations based on the performance monitoring result:

[0068] Sending the performance monitoring result to the network device;

[0069] Perform AI or ML model switching;

[0070] deactivating the first AI or ML model;

[0071] Sending a first decision result to the network device; wherein the first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model.

[0072] The present disclosure provides an information processing method, including:

[0073] The network device receives the second information sent by the terminal;

[0074] The network device performs handover-related processing according to the second information;

[0075] The second information includes at least one of the following:

[0076] RRM prediction results;

[0077] Predicting cell information of the optimal cell;

[0078] The first prediction result is related to the occurrence of the predicted event.

[0079] In some embodiments, the second information further includes at least one of the following parameters:

[0080] identification information of the first AI or ML model;

[0081] identification information of the AI ​​or ML function corresponding to the first AI or ML model;

[0082] A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0083] the number of prediction results output by the first AI or ML model corresponding to the timestamp;

[0084] The time interval between the first AI or ML model outputting prediction results;

[0085] The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

[0086] In some embodiments, the timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, UTC, GPST, a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

[0087] In some embodiments, the first prediction result includes at least one of the following:

[0088] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0089] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0090] The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

[0091] In some embodiments, the information processing method further includes:

[0092] The network device sends configuration information to the terminal; wherein the configuration information includes at least one of the following:

[0093] fifth indication information, used to indicate the parameters in the second information reported by the terminal;

[0094] Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result;

[0095] Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition;

[0096] Configuration information of the first condition.

[0097] In some embodiments, the first condition includes at least one of the following:

[0098] At the first predicted time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more predicted time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold;

[0099] At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell;

[0100] At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event;

[0101] The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

[0102] In some embodiments, the information processing method further includes:

[0103] The network device receives terminal capability information sent by the terminal, wherein the terminal capability information includes at least one of the following:

[0104] Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result;

[0105] Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell;

[0106] The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

[0107] In some embodiments, the information processing method further includes at least one of the following:

[0108] The network device receives a first decision result sent by the terminal; wherein the first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model;

[0109] The network device receives a performance monitoring result of the inference performance of the first AI or ML model sent by the terminal, and sends decision indication information to the terminal based on the performance monitoring result;

[0110] The network device monitors the inference performance of the first AI or ML model, determines a performance monitoring result, and sends decision indication information to the terminal based on the performance monitoring result;

[0111] The decision indication information is used to indicate the switched AI or ML model and / or to deactivate the first AI or ML model.

[0112] The present disclosure provides an information processing method, including:

[0113] The terminal sends an RRM measurement result related to the first AI or ML model input to the network device.

[0114] In some embodiments, the terminal sends an RRM measurement result related to the first AI or ML model input to the network device, including:

[0115] The terminal receives the configuration information sent by the network device;

[0116] The terminal sends, to the network device, an RRM measurement result related to the first AI or ML model input according to the configuration information; wherein the configuration information includes at least one of the following:

[0117] The reporting period for the terminal to report RRM measurement results;

[0118] second threshold;

[0119] third threshold;

[0120] Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following:

[0121] The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold;

[0122] The speed of the terminal changes;

[0123] The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

[0124] The present disclosure provides an information processing method, including:

[0125] The network device receives an RRM measurement result related to the first AI or ML model input sent by the terminal;

[0126] The network device obtains first information output by a first AI or ML model according to the RRM measurement result;

[0127] The network device performs handover-related processing according to the first information;

[0128] The first information includes at least one of the following parameters:

[0129] RRM prediction results;

[0130] Predicting cell information of the optimal cell;

[0131] The first prediction result is related to the occurrence of the predicted event.

[0132] In some embodiments, the network device performs handover-related processing according to the first information, including at least one of the following:

[0133] In a case where the first information includes an RRM prediction result, the network device performs handover-related processing according to the RRM prediction result;

[0134] In a case where the first information includes cell information of a predicted optimal cell, the network device performs handover-related processing according to the cell information of the predicted optimal cell;

[0135] In a case where the first information includes a first prediction result, the network device performs handover-related processing according to the first prediction result;

[0136] In a case where the first information includes an RRM prediction result, the network device determines the cell information of the predicted optimal cell and / or the first prediction result according to the RRM prediction result, and performs handover-related processing according to the cell information of the predicted optimal cell and / or the first prediction result;

[0137] In a case where the first information includes cell information of a predicted optimal cell, the network device determines the first prediction result according to the cell information of the predicted optimal cell, and performs cell handover-related processing according to the first prediction result.

[0138] In some embodiments, the first prediction result includes at least one of the following:

[0139] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0140] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0141] The fourth indication information is used to indicate the cells and / or beams that meet the switching conditions within the first prediction time period.

[0142] In some embodiments, the network device performs handover-related processing according to the first information, including at least one of the following:

[0143] In a case where the first prediction result includes second indication information, the network device performs handover-related processing according to the second indication information;

[0144] In a case where the first prediction result includes third indication information, the network device performs handover-related processing according to the third indication information;

[0145] In a case where the first prediction result includes fourth indication information, the network device performs handover-related processing according to the fourth indication information;

[0146] In a case where the first prediction result includes second indication information, the network device determines at least one of the first indication information, the third indication information, and the fourth indication information according to the second indication information, and performs handover-related processing according to at least one of the first indication information, the third indication information, and the fourth indication information;

[0147] In a case where the first prediction result includes third indication information, the network device determines the first indication information and / or the fourth indication information according to the third indication information, and performs handover-related processing according to the first indication information and / or the fourth indication information;

[0148] In a case where the first prediction result includes fourth indication information, the network device determines the first indication information according to the fourth indication information, and performs handover-related processing according to the first indication information;

[0149] Among them, the first indication information is used to indicate the change trend of the RRM prediction result corresponding to the first cell and / or the first beam, and the first cell and / or the first beam meets the switching condition.

[0150] In some embodiments, before the network device receives the radio resource management RRM measurement result related to the first artificial intelligence AI or machine learning ML model input sent by the terminal, it also includes:

[0151] The network device sends configuration information to the terminal; wherein the configuration information includes at least one of the following:

[0152] The reporting period for the terminal to report RRM measurement results;

[0153] second threshold;

[0154] third threshold;

[0155] Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following:

[0156] The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold;

[0157] The speed of the terminal changes;

[0158] The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

[0159] In some embodiments, the information processing method further includes:

[0160] The network device monitors the inference performance of the first AI or ML model and determines a performance monitoring result;

[0161] The network device performs AI or ML model switching and / or deactivates the first AI or ML model based on the performance monitoring result.

[0162] An embodiment of the present disclosure provides an information processing device, including a memory, a transceiver, and a processor;

[0163] The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor is used to read the computer program in the memory and perform the following operations:

[0164] determining an RRM measurement associated with a first AI or ML model input;

[0165] Obtaining first information output by a first AI or ML model based on the RRM measurement result;

[0166] Sending second information to the network device according to the first information;

[0167] The first information and / or the second information includes at least one of the following parameters:

[0168] RRM prediction results;

[0169] Predicting cell information of the optimal cell;

[0170] The first prediction result is related to the occurrence of the predicted event.

[0171] An embodiment of the present disclosure provides a terminal, including:

[0172] a measurement unit configured to determine an RRM measurement associated with a first AI or ML model input;

[0173] a first processing unit, configured to obtain first information output by a first AI or ML model based on the RRM measurement result;

[0174] A first sending unit, configured to send second information to a network device according to the first information;

[0175] The first information and / or the second information includes at least one of the following parameters:

[0176] RRM prediction results;

[0177] Predicting cell information of the optimal cell;

[0178] The first prediction result is related to the occurrence of the predicted event.

[0179] An embodiment of the present disclosure provides an information processing device, including a memory, a transceiver, and a processor;

[0180] The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor is used to read the computer program in the memory and perform the following operations:

[0181] receiving second information sent by the terminal;

[0182] performing handover-related processing according to the second information;

[0183] The second information includes at least one of the following:

[0184] RRM prediction results;

[0185] Predicting cell information of the optimal cell;

[0186] The first prediction result is related to the occurrence of the predicted event.

[0187] An embodiment of the present disclosure provides a network device, including:

[0188] A first receiving unit, configured to receive second information sent by a terminal;

[0189] a first processing unit, configured to perform handover-related processing according to the second information;

[0190] The second information includes at least one of the following:

[0191] RRM prediction results;

[0192] Predicting cell information of the optimal cell;

[0193] The first prediction result is related to the occurrence of the predicted event.

[0194] An embodiment of the present disclosure provides an information processing device, including a memory, a transceiver, and a processor;

[0195] The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor is used to read the computer program in the memory and perform the following operations:

[0196] Sending RRM measurements associated with the first AI or ML model input to the network device.

[0197] An embodiment of the present disclosure provides a terminal, including:

[0198] A sending unit is configured to send an RRM measurement result related to the first AI or ML model input to the network device.

[0199] An embodiment of the present disclosure provides an information processing device, including a memory, a transceiver, and a processor;

[0200] The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor is used to read the computer program in the memory and perform the following operations:

[0201] receiving an RRM measurement result related to a first AI or ML model input sent by a terminal;

[0202] Obtaining first information output by a first AI or ML model based on the RRM measurement result;

[0203] performing handover-related processing according to the first information;

[0204] The first information includes at least one of the following parameters:

[0205] RRM prediction results;

[0206] Predicting cell information of the optimal cell;

[0207] The first prediction result is related to the occurrence of the predicted event.

[0208] An embodiment of the present disclosure provides a network device, including:

[0209] receiving an RRM measurement result related to a first AI or ML model input sent by a terminal;

[0210] Obtaining first information output by a first AI or ML model based on the RRM measurement result;

[0211] performing handover-related processing according to the first information;

[0212] The first information includes at least one of the following parameters:

[0213] RRM prediction results;

[0214] Predicting cell information of the optimal cell;

[0215] The first prediction result is related to the occurrence of the predicted event.

[0216] An embodiment of the present disclosure provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the steps of the information processing method described above.

[0217] An embodiment of the present disclosure provides a computer program product, including computer instructions, which implement the steps of the above-mentioned information processing method when executed by a processor.

[0218] The beneficial effects of the above technical solution disclosed in the present invention are:

[0219] In an embodiment of the present disclosure, the terminal obtains first information output by the first AI or ML model based on the RRM measurement result and the first AI or ML model reasoning, and sends second information to the network device based on the first information. The first information and / or the second information include at least one of the RRM prediction result, the cell information of the predicted optimal cell, and the first prediction result related to the occurrence of the predicted event, so that the network device can know the prediction result of a certain (or certain) moment or time period in the future at a certain (or certain) moment or time period, and perform corresponding processing in time to avoid wireless link failure, handover failure, or ping-pong effect after successful handover during the handover process, thereby solving the problem that the current handover mechanism is prone to handover failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0220] FIG1 shows a flowchart of a method for processing information on a terminal side according to an embodiment of the present disclosure;

[0221] FIG2 shows a flow chart of a method for processing information on a network device side according to an embodiment of the present disclosure;

[0222] FIG3 shows a second flowchart of the information processing method on the terminal side according to an embodiment of the present disclosure;

[0223] FIG4 shows a second flowchart of the information processing method on the network device side according to an embodiment of the present disclosure;

[0224] FIG5 shows one block diagram of an information processing device on a terminal side according to an embodiment of the present disclosure;

[0225] FIG6 shows one block diagram of a terminal according to an embodiment of the present disclosure;

[0226] FIG7 shows a block diagram of an information processing apparatus on a network device side according to an embodiment of the present disclosure;

[0227] FIG8 shows a block diagram of a network device according to an embodiment of the present disclosure;

[0228] FIG9 shows a second block diagram of the information processing device on the terminal side according to an embodiment of the present disclosure;

[0229] FIG10 shows a second block diagram of a terminal according to an embodiment of the present disclosure;

[0230] FIG11 shows a second block diagram of the information processing apparatus on the network device side according to an embodiment of the present disclosure;

[0231] FIG12 shows a second block diagram of the network device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0232] To make the technical problems, technical solutions, and advantages to be solved by the present disclosure more clear, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help fully understand the embodiments of the present disclosure. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. In addition, for the sake of clarity and brevity, descriptions of known functions and configurations have been omitted.

[0233] It should be understood that references throughout this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment of the present disclosure. Therefore, the appearances of "in one embodiment" or "in an embodiment" throughout this specification do not necessarily refer to the same embodiment. Furthermore, these particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0234] In the various embodiments of the present disclosure, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

[0235] Additionally, the terms "system" and "network" are often used interchangeably herein.

[0236] The technical solution provided by the embodiment of the present disclosure can be applicable to a variety of systems, especially the fifth generation mobile communication technology (5G) system. For example, the applicable system can be a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (WCDMA) general packet radio service (GPRS) system, a long term evolution (LTE) system, a LTE frequency division duplex (FDD) system, a LTE time division duplex (TDD) system, an advanced long term evolution (LTE-A) system, a universal mobile telecommunication system (UMTS), a world-wide interoperability for microwave access (WiMAX) system, a 5G new air interface (NR) system, etc. These various systems all include terminals and network equipment. The system may also include core network parts, such as the Evolved Packet System (EPS), 5G system (5G system, 5GS), etc.

[0237] Network devices and terminal devices can each use one or more antennas for Multiple Input Multiple Output (MIMO) transmission. MIMO transmission can be single-user MIMO (SU-MIMO) or multi-user MIMO (MU-MIMO). Depending on the form and number of antenna combinations, MIMO transmission can be two-dimensional MIMO (2D-MIMO), three-dimensional MIMO (3D-MIMO), full-dimensional MIMO (FD-MIMO), or massive MIMO. It can also use diversity transmission, precoded transmission, or beamforming transmission.

[0238] In the embodiments of the present disclosure, the term "and / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0239] In the embodiments of the present disclosure, the term "plurality" refers to two or more than two, and other quantifiers are similar thereto.

[0240] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure and not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0241] The following is an introduction to the relevant technologies involved in this disclosure:

[0242] 1. Configuration

[0243] The network device performs measurement configuration on the UE that has established a Radio Resource Control (RRC) connection (RRC_CONNECTED), and the measurement configuration is provided through RRC dedicated signaling, such as the dedicated signaling being an RRC reconfiguration (RRC Reconfiguration) message or an RRC resume (RRC Resume) message.

[0244] The measurement configuration includes but is not limited to the following parameters:

[0245] 1) Measurement object (MO): The measurement object represents the frequency, time position, subcarrier spacing, etc. of the reference signal to be measured.

[0246] 2) Reporting configuration: indicates the configuration related to the terminal reporting measurement results.

[0247] Measurement reporting can be divided into event-triggered reporting and periodic reporting according to reporting evaluation criteria.

[0248] Event-triggered reporting is further divided into: event-triggered one-time reporting and event-triggered periodic reporting. In the event-triggered one-time reporting, the UE will trigger the sending of the measurement report only when the measurement event configured by the network device meets the threshold and lasts for a period of time (such as the trigger time (TTT)). The process ends after the measurement report is sent once. The reporting configuration corresponding to this criterion includes:

[0249] The trigger type is event triggered (eventTriggered);

[0250] The number of reports (reportAmount) is equal to 1;

[0251] The UE ignores the configured value of reportInterval.

[0252] Event-triggered periodic reporting is a combination of event-triggered reporting and periodic reporting. The UE will trigger the sending of measurement reports only when the measurement event configured by the network device enters the threshold and lasts for a period of time (such as TTT). After the report is triggered, the timer between multiple measurements and the counter for the number of measurements will be started until the number of reports reaches the requirement. The reporting configuration corresponding to this criterion includes:

[0253] The trigger type is eventTriggered;

[0254] reportAmount is greater than 1;

[0255] reportInterval is valid. For example, the network device sets the reporting cycle timer according to the configured reportInterval value.

[0256] After the network device completes the measurement configuration for periodic reporting, the UE will perform measurements at the corresponding frequency points according to the configuration and send measurement reports at the specified reporting period and interval. If the trigger type is periodic, when the maximum number of reports is reached, the UE will autonomously delete the corresponding measurement identifier in the measurement configuration variable. The reporting configuration corresponding to this criterion includes:

[0257] The trigger type is periodical;

[0258] reportAmount is greater than 1;

[0259] reportInterval is valid. For example, the network device sets the reporting cycle timer according to the configured reportInterval value.

[0260] Among them, reportInterval may be one of the range of {120ms,240ms,480ms,640ms,1024ms,2048ms,5120ms,10240ms,20480ms,40960ms,1min,6min,12min,30min}.

[0261] 3) Measurement identity (measId): Each measurement identity is mapped to a measurement object and a reporting configuration.

[0262] 2. Measurement results

[0263] The UE performs corresponding measurements according to the above measurement configuration, and periodically or triggers reporting of the measurement results. The measurement result first includes a measId, that is, the measurement object and reporting configuration corresponding to the measurement result are determined. The measurement result may also include: the measurement result of the serving cell and the measurement result of the neighboring cell. For the reporting of multiple neighboring cells, the measurement results of the multiple neighboring cells are first sorted, and then the cell ID (physCellId) and measurement results of the neighboring cells are reported, such as: Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), signal-to-noise and interference ratio (SINR), etc.

[0264] 3. Switch Execution

[0265] The UE reports the measurement results, and the source serving cell evaluates them to decide whether to trigger a handover. If a handover is triggered, the source serving cell first interacts with the target cell through an interface (handover preparation). The source serving cell then sends a handover command to the UE. After receiving the handover command, the UE begins the handover. During this process, if the signal between the UE and the source serving cell is poor, the UE may not be able to report the measurement results, or the UE may not be able to receive the handover command sent by the source serving cell. As a result, the UE may not be able to complete the handover, which means a handover failure may occur.

[0266] The embodiments of the present disclosure provide an information processing method, apparatus, terminal, and network device to address the problem of switching failures that are common in current switching mechanisms. The method and apparatus (or terminal or network device) are based on the same patent application concept. Since the principles for solving the problem are similar, the implementation of the method and apparatus (or terminal or network device) can refer to each other, and any repetitions will not be repeated.

[0267] As shown in FIG1 , an embodiment of the present disclosure provides an information processing method, comprising the following steps:

[0268] Step 11: The terminal determines an RRM measurement result associated with the first AI or ML model input.

[0269] In some embodiments, the RRM measurement result may be obtained by the terminal through measurement, for example, the RRM measurement result is obtained by the terminal through measurement and used as input to the first AI or ML model.

[0270] In some embodiments, the first AI or ML model includes: a first AI model, and / or, a first ML model.

[0271] In some embodiments, the RRM measurement result includes but is not limited to at least one of the following: RSRP, RSRQ, and SINR.

[0272] Step 12: Obtain first information output by a first AI or ML model based on the RRM measurement result.

[0273] In some embodiments, the first information is a prediction result (i.e., a result of predicting a future time) obtained by inputting an RRM measurement result obtained by the terminal into a first AI or ML model and inferring or outputting the result by the first AI or ML model. The first information includes but is not limited to at least one of the following parameters:

[0274] RRM prediction results; for example: RRM prediction results at one or more prediction time points, and / or, RRM prediction results at one or more prediction time periods, etc. The RRM prediction results include but are not limited to at least one of the following: RSRP, RSRQ, SINR.

[0275] Cell information of the predicted optimal cell; for example: cell information of the predicted optimal cell at one or more predicted time points, and / or, cell information of the predicted optimal cell in one or more predicted time periods, etc. The cell information includes but is not limited to: identification information of the predicted optimal cell, etc., and the embodiments of the present disclosure are not limited to this.

[0276] A first prediction result related to the occurrence of a predicted event; for example: a first prediction result of one or more prediction time points (i.e., the first prediction result can indicate the occurrence of a predicted event at one or more prediction time points), and / or, a first prediction result of one or more prediction time periods (i.e., the first prediction result can indicate the occurrence of a predicted event at one or more prediction time points), etc. The embodiments of the present disclosure are not limited thereto.

[0277] In some embodiments, the occurrence of the predicted event includes but is not limited to at least one of the following: satisfying the predicted event, not satisfying the predicted event, satisfying the predicted event and the triggering conditions for triggering reporting, satisfying the predicted event and not satisfying the triggering conditions for triggering reporting, etc. The embodiments of the present disclosure are not limited to this.

[0278] In some embodiments, the predicted event may adopt the same rules as the measurement event, such as RSRP being lower than the RSRP threshold, or RSRQ being lower than the RSRQ threshold, or other measurement events in addition to these, or the predicted event may also be different from the measurement event, such as setting different threshold values ​​corresponding to the predicted event and the measurement event, or the predicted event may also be a new event in addition to the measurement event, etc. The embodiments of the present disclosure are not limited to this.

[0279] In some embodiments, the terminal performs actual measurement to obtain actual measured quantities (such as measured RSRP values, RSRQ values, SINR values, etc.). The measurement event is a judgment rule for the actual measured quantity, such as a measurement event defined in a protocol.

[0280] For example, the functions of the first AI or ML model include but are not limited to at least one of the following:

[0281] Solution 1: The first AI or ML model takes as input the RRM measurement results (i.e., actual RRM measurement results) actually measured at one or more time points (already occurring time points), and outputs RRM prediction results for one or more predicted time points (or predicted time periods). That is, the first information includes the RRM prediction results.

[0282] Solution 2: The input of the first AI or ML model is the RRM measurement results (i.e., RRM actual measurement results) actually measured at one or more time points (time points that have already occurred), and the output is the cell information of the predicted optimal cell at one or more predicted time points (or predicted time periods); wherein, the optimal cells predicted by the first AI or ML model can be N, where N is a positive integer greater than or equal to 1.

[0283] Solution 3: The input of the first AI or ML model is the RRM measurement results (i.e., RRM actual measurement results) actually measured at one or more time points (time points that have already occurred), and the output is the first prediction results for one or more predicted time points (or predicted time periods).

[0284] It should be noted that the input of the first AI or ML model is the RRM measurement results (i.e., RRM actual measurement results) actually measured at one or more time points (time points that have already occurred), and the output can also be the RRM prediction results of one or more predicted time points (or predicted time periods) and the cell information of the predicted optimal cell; or the output can also be the RRM prediction results of one or more predicted time points (or predicted time periods) and the first prediction results; or the output can also be the cell information of the predicted optimal cell and the first prediction result of one or more predicted time points (or predicted time periods); or the output can also be the RRM prediction results of one or more predicted time points (or predicted time periods), the cell information of the predicted optimal cell and the first prediction result, etc. The embodiments of the present disclosure are not limited to this.

[0285] Step 13: The terminal sends second information to the network device based on the first information; wherein the second information includes at least one of the following parameters:

[0286] RRM prediction results;

[0287] Cell information of the predicted optimal cell; for example, the number of predicted optimal cells may be M, where M is a positive integer greater than or equal to 1. In some embodiments, M ≤ N, or M > N, and M may be configured by a network device or based on a protocol agreement, etc., and the embodiments of the present disclosure are not limited thereto.

[0288] The first prediction result is related to the occurrence of the predicted event.

[0289] In some embodiments, the second information may be the first information, that is, the second information may be a prediction result of the output of the first AI or ML model, or the second information may be calculated based on the first information.

[0290] In an embodiment of the present disclosure, the terminal obtains first information output by the first AI or ML model based on the RRM measurement result and the first AI or ML model reasoning, and sends second information to the network device based on the first information. The first information and / or the second information include at least one of the RRM prediction result, the cell information of the predicted optimal cell, and the first prediction result related to the occurrence of the predicted event, so that the network device can know the prediction result of a certain (or certain) moment or time period in the future at a certain (or certain) moment or time period, and perform corresponding processing in time to avoid wireless link failure, handover failure, or ping-pong effect after successful handover during the handover process, thereby solving the problem that the current handover mechanism is prone to handover failure.

[0291] In some embodiments, the terminal determines the second information by at least one of the following methods:

[0292] In the case where the first information includes an RRM prediction result, the terminal determines that the second information includes the RRM prediction result; for example, the terminal may report the RRM prediction result output by the first AI or ML model to the network device as the second information.

[0293] When the first information includes cell information of the predicted optimal cell, the terminal determines that the second information includes the cell information of the predicted optimal cell; for example, the terminal can report the cell information of the predicted optimal cell output by the first AI or ML model as the second information to the network device.

[0294] When the first information includes a first prediction result, the terminal determines that the second information includes the first prediction result; for example, the terminal can report the first prediction result output by the first AI or ML model as the second information to the network device.

[0295] In the case where the first information includes an RRM prediction result, the terminal determines the cell information of the predicted optimal cell and / or the first prediction result based on the RRM prediction result, and determines that the second information includes the cell information of the predicted optimal cell and / or the first prediction result; for example, the terminal may obtain the cell information of the predicted optimal cell and / or the first prediction result based on the RRM prediction result output by the first AI or ML model through reasoning or calculation, and report the cell information of the predicted optimal cell and / or the first prediction result as the second information to the network device. In some embodiments, the second information may also include the RRM prediction result, etc., but the embodiments of the present disclosure are not limited to this.

[0296] In the case where the first information includes cell information of the predicted optimal cell, the terminal determines the first prediction result based on the cell information of the predicted optimal cell, and determines that the second information includes the first prediction result. For example, the terminal may obtain the first prediction result through reasoning or calculation based on the cell information of the predicted optimal cell output by the first AI or ML model, and report the first prediction result as the second information to the network device. In some embodiments, the second information may also include cell information of the predicted optimal cell, etc., but the embodiments of the present disclosure are not limited to this.

[0297] It should be noted that the output of the first AI or ML model may also include: RRM prediction results and cell information of the predicted optimal cell. The terminal may report the RRM prediction results and the cell information of the predicted optimal cell as the second information to the network device, or based on the RRM prediction results and / or the cell information of the predicted optimal cell, infer and calculate the first prediction result as the second information, and report it to the network device (in some embodiments, the second information may also include: cell information of the predicted optimal cell and / or RRM measurement results), etc.

[0298] Alternatively, the output of the first AI or ML model may also include: RRM prediction results and first prediction results. The terminal may report the RRM prediction results and the first prediction results as second information to the network device, or based on the RRM prediction results and / or the first prediction results, infer and calculate the cell information of the predicted optimal cell as the second information, and report it to the network device (in some embodiments, the second information may also include the RRM prediction results and / or the first prediction results), etc.

[0299] Alternatively, the output of the first AI or ML model may also include: cell information of the predicted optimal cell and a first prediction result, and the terminal may report the cell information of the predicted optimal cell and the first prediction result as second information to the network device.

[0300] Alternatively, the output of the first AI or ML model may also include: RRM prediction results, cell information of the predicted optimal cell and the first prediction result. The terminal may report the RRM prediction results, cell information of the predicted optimal cell and the first prediction result as second information to a network device, etc. The embodiments of the present disclosure are not limited to this.

[0301] In some embodiments, the first information further includes at least one of the following parameters:

[0302] A timestamp corresponding to a prediction result output by the first AI or ML model; wherein the prediction result output by the first AI or ML model includes at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0303] Cell identification information corresponding to the RRM prediction result;

[0304] Beam identification information corresponding to the RRM prediction result.

[0305] For example, when the prediction result output by the first AI or ML model includes an RRM prediction result, the timestamp includes a timestamp corresponding to the RRM prediction result; when the prediction result output by the first AI or ML model includes cell information of the predicted optimal cell, the timestamp includes a timestamp corresponding to the cell information of the predicted optimal cell; when the prediction result output by the first AI or ML model includes a first prediction result, the timestamp includes a timestamp corresponding to the first prediction result.

[0306] For example, when the first AI or ML model adopts the above-mentioned solution 1, the input of the first AI or ML model includes but is not limited to at least one of the following: RRM measurement results, cell identification information corresponding to the RRM measurement results, beam identification information corresponding to the RRM measurement results, terminal location, terminal movement speed, terminal movement trajectory, etc. Correspondingly, the output of the first AI or ML model (i.e., the first information) may include at least one of the following: RRM prediction results, timestamp corresponding to the RRM prediction results, cell identification information corresponding to the RRM prediction results (i.e., cell ID), beam identification information corresponding to the RRM prediction results (such as beam identification), etc.

[0307] For another example: when the first AI or ML model adopts the above-mentioned solution 2, the input of the first AI or ML model includes but is not limited to at least one of the following: RRM measurement results, cell identification information corresponding to the RRM measurement results, beam identification information corresponding to the RRM measurement results, the position of the terminal, the movement speed of the terminal, the movement trajectory of the terminal, etc. Correspondingly, the output of the first AI or ML model (that is, the first information) may include at least one of the following: cell information of the predicted optimal cell (wherein the number of optimal cells may be a preset fixed value or agreed upon by the protocol or configured by the network device), and a timestamp corresponding to the cell information of the predicted optimal cell. In some embodiments, it may also include the RRM prediction result, the timestamp corresponding to the RRM prediction result, the cell identification information corresponding to the RRM prediction result, the beam identification information corresponding to the RRM prediction result, etc.

[0308] For another example: When the first AI or ML model adopts the above-mentioned solution 3, the input of the first AI or ML model includes but is not limited to at least one of the following: RRM measurement results, cell identification information corresponding to the RRM measurement results, beam identification information corresponding to the RRM measurement results, the position of the terminal, the movement speed of the terminal, the movement trajectory of the terminal, etc. Correspondingly, the output of the first AI or ML model (that is, the first information) may include at least one of the following: the first prediction result, the timestamp corresponding to the first prediction result. In some embodiments, it may also include: cell information of the predicted optimal cell, the timestamp corresponding to the cell information of the predicted optimal cell, RRM prediction results, the timestamp corresponding to the RRM prediction results, the cell identification information corresponding to the RRM prediction results, the beam identification information corresponding to the RRM prediction results, etc.

[0309] In some embodiments, the second information further includes at least one of the following parameters:

[0310] Identification information of the first AI or ML model; for example, the terminal can report the identification information of the first AI or ML model to the network device, so that the network device can know the AI ​​or ML model used for terminal-side reasoning.

[0311] Identification information of the AI ​​or ML function corresponding to the first AI or ML model; for example, the AI ​​or ML function may correspond to one or more AI or ML models (for example, the AI ​​or ML function implements at least one of the above-mentioned solutions 1, 2, and 3, or other solutions, etc.). The terminal may report the identification information of the AI ​​or ML function corresponding to the first AI or ML model to the network device, so that the network device can learn the AI ​​or ML function used for terminal-side inference.

[0312] The timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction result output by the first AI or ML model includes at least one of the RRM prediction result, the cell information of the predicted optimal cell, and the first prediction result; for example: the terminal can report the corresponding timestamp for each prediction result output by the first AI or ML model; or, the terminal can also only report the timestamps corresponding to some prediction results (which can be one or more).

[0313] The sequence number of the prediction result output by the first AI or ML model corresponding to the timestamp; for example, when the terminal reports the timestamp corresponding to some prediction results (which may be one or more), the sequence number can be used to indicate the prediction result output by the first AI or ML model at that timestamp. Alternatively, when the terminal reports the timestamp of the target prediction result output by the first AI or ML model (for example, the timestamp of the first prediction result), the sequence number can also be used to indicate the prediction result output by the first AI or ML model after the target prediction result, etc. The embodiments of the present disclosure are not limited to this.

[0314] The time interval for outputting prediction results by the first AI or ML model; for example: when the terminal reports the timestamp corresponding to each of the partial prediction results (which may be one or more) and the time interval, the network device determines the timestamp corresponding to each of the prediction results reported by the terminal based on the timestamp corresponding to each of the partial prediction results (which may be one or more) reported by the terminal and the time interval. Alternatively, the terminal reports the timestamp, sequence number and time interval corresponding to each of the partial prediction results (which may be one or more), and the network device determines the timestamp corresponding to each of the prediction results reported by the terminal based on the timestamp, sequence number and time interval corresponding to each of the partial prediction results (which may be one or more). Alternatively, if the terminal reports the timestamp corresponding to the first prediction result output by the first AI or ML model and only reports the corresponding sequence number for the subsequent prediction results, the network device can infer the timestamp corresponding to the other prediction results based on the timestamp corresponding to the first prediction result, the sequence numbers corresponding to the other prediction results and the time interval to reduce signaling overhead.

[0315] The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

[0316] In some embodiments, the triggering conditions for the event-triggered reporting can be determined based on the triggering conditions for the event-triggered measurement reporting, or can be different from the triggering conditions for the event-triggered measurement reporting (for example, defining new triggering conditions as triggering conditions for the event-triggered prediction reporting), etc. The embodiments of the present disclosure are not limited to this.

[0317] For example, the triggering conditions for the event to be reported include but are not limited to at least one of the following:

[0318] The AI ​​or ML model outputs a prediction;

[0319] At the predicted time point, there are cells and / or beams that meet the measurement reporting triggering conditions (such as event-triggered measurement reporting triggering conditions or other triggering conditions, etc.);

[0320] In the predicted time period, there are cells and / or beams that meet the triggering conditions for measurement reporting (such as the triggering conditions for event-triggered measurement reporting or other triggering conditions, etc.).

[0321] In some embodiments, the timestamp includes but is not limited to at least one of the following: a frame, a subframe, a time slot, a symbol, UTC, GPST, a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

[0322] In some embodiments, the first prediction result includes at least one of the following:

[0323] The second indication information is used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points; for example: for cell 1 and / or beam 1, the second indication information is used to indicate its first prediction result at N prediction time points, which can be indicated by a sequence of length N, such as sequence 001...11 can indicate that cell 1 and / or beam 1 does not meet the prediction event at the first and second prediction time points... cell 1 and / or beam 1 meets the prediction event at the third, N-1th and Nth prediction time points, etc. The embodiments of the present disclosure are not limited to this.

[0324] The third indication information is used to indicate the cells and / or beams that meet the predicted event at one or more predicted time points; for example: for predicted time point 1, when the third indication information is used to indicate the cells and / or beams that meet the predicted event, the third indication information may include the cell identifier and / or beam identifier that meets the predicted event, etc. The embodiments of the present disclosure are not limited to this.

[0325] The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event-triggered reporting within the first prediction time period. For example, for prediction time period 1, when the fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event-triggered reporting, the fourth indication information may include the cell identifier and / or beam identifier that meet the triggering conditions for event-triggered reporting, etc., but the embodiments of the present disclosure are not limited to this.

[0326] In some embodiments, the terminal determines the second information by at least one of the following methods:

[0327] In the case where the first prediction result includes second indication information, the terminal determines that the second information includes the second indication information; for example, the terminal can report the second indication information output by the first AI or ML model as the second information to the network device.

[0328] When the first prediction result includes third indication information, the terminal determines that the second information includes the third indication information; for example, the terminal can report the third indication information output by the first AI or ML model as the second information to the network device.

[0329] When the first prediction result includes fourth indication information, the terminal determines that the second information includes the fourth indication information; for example, the terminal can report the fourth indication information output by the first AI or ML model as the second information to the network device.

[0330] In the case where the first prediction result includes the second indication information, the terminal determines at least one of the first indication information, the third indication information, and the fourth indication information based on the second indication information, and determines that the second information includes at least one of the first indication information, the third indication information, and the fourth indication information; for example: the terminal can infer and calculate at least one of the first indication information, the third indication information, and the fourth indication information based on the second indication information output by the first AI or ML model, and report at least one of the first indication information, the third indication information, and the fourth indication information as the second information to the network device (in some embodiments, the second information may also include the second indication information at this time).

[0331] In the case where the first prediction result includes the third indication information, the terminal determines the first indication information and / or the fourth indication information based on the third indication information, and determines that the second information includes the first indication information and / or the fourth indication information; for example: the terminal can infer and calculate the first indication information and / or the fourth indication information based on the third indication information output by the first AI or ML model, and report the first indication information and / or the fourth indication information as the second information to the network device (in some embodiments, the second information may also include the third indication information at this time).

[0332] In the case where the first prediction result includes fourth indication information, the terminal determines the first indication information based on the fourth indication information, and determines that the second information includes the first indication information; for example: the terminal can infer and calculate the first indication information based on the fourth indication information output by the first AI or ML model, and report the first indication information as the second information to the network device (in some embodiments, the second information may also include the fourth indication information at this time).

[0333] In some embodiments, the method further comprises:

[0334] The terminal receives configuration information sent by the network device;

[0335] The terminal sending second information to the network device includes:

[0336] The terminal sends the second information to the network device according to the configuration information;

[0337] The configuration information includes at least one of the following:

[0338] The fifth indication information is used to indicate the parameters in the second information reported by the terminal; for example: the network device can indicate in the configuration information which parameter or parameters in the second information the terminal reports, or it can be understood that the network device expects or requests the terminal to report which parameter or parameters in the second information, such as: RRM measurement results, cell information of the predicted optimal cell, timestamp, cell identifier, beam identifier, one or more of the first prediction results, etc.

[0339] The sixth indication information is used to indicate whether the terminal reports the changing trend of the RRM prediction result; for example, the network device can indicate in the configuration information that the terminal needs to report the changing trend of the RRM prediction result, or inform the terminal that it does not need to report the changing trend of the RRM prediction result, etc.

[0340] The seventh indication information is used to indicate whether the terminal is allowed to determine whether to report the second information based on the first condition; for example: when the seventh indication information indicates that the terminal is allowed to determine whether to report the second information based on the first condition, the terminal can determine whether to report the second information based on the first condition (that is, determine whether the second information is invalid data based on the first condition); or when the seventh indication information indicates that the terminal is not allowed to determine whether to report the second information based on the first condition, the terminal does not need to determine whether the second information meets the first condition (that is, there is no need to determine whether the second information is invalid data).

[0341] Configuration information of the first condition.

[0342] It should be noted that, in addition to being configured by the network device, the first condition may also be agreed upon by a protocol, and the embodiments of the present disclosure are not limited thereto.

[0343] In some embodiments, the first condition includes at least one of the following:

[0344] At the first predicted time point, the second cell and / or the second beam meets the triggering conditions for event-triggered reporting, and at one or more predicted time points within the second predicted time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold; for example: the cell is predicted to meet the measurement event or meet the triggering conditions for event-triggered reporting at future time t2, but the signal quality is lower than the first threshold once or more times within the second predicted time period from t2 to t2+t3, then the terminal determines not to predict reporting. In some embodiments, the number of times the signal quality is lower than the first threshold can be configured by the network device or based on a protocol agreement, and the embodiments of the present disclosure are not limited thereto.

[0345] At a first predicted time point, the second cell meets the triggering conditions for event-triggered reporting, and within a second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell. For example, at a predicted future time t2, the cell meets the measurement event or meets the triggering conditions for event-triggered reporting, but within a second predicted time period from t2 to t2+t3, at least one of handover failure, radio link failure, and ping-pong effect occurs, then the terminal determines not to predict reporting. In some embodiments, the criteria for determining whether a handover failure occurs, whether a radio link failure occurs, whether a ping-pong effect occurs, or other criteria for not predicting reporting events in addition to the criteria may be configured by the network device or based on a protocol agreement, and the embodiments of the present disclosure are not limited thereto.

[0346] At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and there are one or more predicted time points within the second predicted time period at which the second cell and / or the second beam do not meet the predicted event; for example: when the output of the first AI and / or ML model is the satisfaction of the measurement event at one or more predicted time points, it is predicted that the cell meets the triggering condition for event triggering reporting at time T, but one or more situations in which the measurement event is not met occur within the second predicted time period from T to T+t1, then the UE does not need to perform predictive reporting; or, when the output of the first AI and / or ML model is the cell ID that meets the measurement event at one or more predicted time points, it is predicted that the cell meets the triggering condition for event triggering reporting at time T, but one or more situations in which the measurement event is not met occur within the second predicted time period from T to T+t1, then the UE does not need to perform predictive reporting. In some embodiments, the number of times the measurement event is not met can be configured by the network device side or can be based on a protocol agreement, and the embodiments of the present disclosure are not limited thereto.

[0347] The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

[0348] In some embodiments, the first threshold and / or the length of the second prediction time period may be agreed upon by a protocol or configured by a network device, but the embodiments of the present disclosure are not limited thereto.

[0349] In some embodiments, the method further comprises:

[0350] The terminal sends terminal capability information to the network device; wherein the terminal capability information includes at least one of the following:

[0351] The eighth indication information is used to indicate whether the terminal has the ability to determine the RRM prediction result; for example, if the first AI and / or ML model can output the RRM prediction result, the terminal determines that it has the ability to determine the RRM prediction result.

[0352] The ninth indication information is used to indicate whether the terminal has the ability to determine the predicted optimal cell; for example: the first AI and / or ML model can output the cell information of the predicted optimal cell, then the terminal determines that it has the ability to determine the predicted optimal cell; or, the first AI and / or ML model can output the RRM prediction result, and the terminal can infer and calculate the predicted optimal cell based on the RRM prediction result, then the terminal can also determine that it has the ability to determine the predicted optimal cell.

[0353] The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result; for example: if the first AI and / or ML model can output the first prediction result, then the terminal is determined to have the ability to determine the first prediction result; or, if the first AI and / or ML model can output the RRM prediction result and / or the cell information of the predicted optimal cell, and the terminal can infer and calculate the first prediction result based on the RRM prediction result and / or the cell information of the predicted optimal cell, then the terminal can also be determined to have the ability to determine the first prediction result.

[0354] In this embodiment, the terminal reports its capability information to the network device. The network device can configure corresponding configuration information for the terminal based on the capabilities of the terminal, such as: configuring which parameter or parameters in the second information to be reported by the terminal, or configuring whether the terminal reports the changing trend of the RRM prediction result, or configuring whether to allow the terminal to determine whether to report the second information based on the first condition, etc. The embodiments of the present disclosure are not limited to this.

[0355] In some embodiments, the method further comprises:

[0356] The terminal monitors the inference performance of the first AI or ML model and determines a performance monitoring result;

[0357] The terminal performs at least one of the following operations based on the performance monitoring result:

[0358] Sending the performance monitoring result to the network device;

[0359] Perform AI or ML model switching;

[0360] deactivating the first AI or ML model;

[0361] Sending a first decision result to the network device; wherein the first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model.

[0362] In this embodiment, the terminal can monitor the reasoning performance of the first AI or ML model and obtain corresponding detection results. For example: the terminal can detect the reasoning performance of the first AI or ML model based on the monitoring parameters agreed upon in the protocol or configured by the network device and obtain corresponding performance monitoring results. The terminal can report the performance monitoring result to the network device, and the network device will make a decision. Or the terminal can also make its own decision based on the performance monitoring result (for example, when the terminal determines that the performance is poor based on the performance monitoring result, it can execute AI or ML model switching and / or deactivate the first AI or ML model), and report the first decision result to the network device (in some embodiments, the terminal can report the performance monitoring result, or it may not report the performance monitoring result), etc. The embodiments of the present disclosure are not limited to this.

[0363] The terminal involved in the embodiments of the present disclosure may be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connection function, or other processing devices connected to a wireless modem. In different systems, the name of the terminal may also be different. For example, in a 5G system, the terminal may be called User Equipment (UE). A wireless terminal can communicate with one or more core networks (CN) via a radio access network (RAN). A wireless terminal can be a mobile terminal, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal. For example, it can be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges voice and / or data with a radio access network. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), and other devices. A wireless terminal may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal, an access terminal, a user terminal, a user agent, or a user device, but is not limited in the embodiments of the present disclosure.

[0364] As shown in FIG2 , an embodiment of the present disclosure provides an information processing method, comprising the following steps:

[0365] Step 21: The network device receives the second information sent by the terminal;

[0366] Step 22: The network device performs handover-related processing according to the second information;

[0367] The second information includes at least one of the following:

[0368] RRM prediction results;

[0369] Predicting cell information of the optimal cell;

[0370] The first prediction result is related to the occurrence of the predicted event.

[0371] In some embodiments, the second information further includes at least one of the following parameters:

[0372] identification information of the first AI or ML model;

[0373] identification information of the AI ​​or ML function corresponding to the first AI or ML model;

[0374] A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0375] the number of prediction results output by the first AI or ML model corresponding to the timestamp;

[0376] The time interval between the first AI or ML model outputting prediction results;

[0377] The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

[0378] In some embodiments, the timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, UTC, GPST, a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

[0379] In some embodiments, the first prediction result includes at least one of the following:

[0380] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0381] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0382] The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

[0383] In some embodiments, the information processing method further includes:

[0384] The network device sends configuration information to the terminal; wherein the configuration information includes at least one of the following:

[0385] fifth indication information, used to indicate the parameters in the second information reported by the terminal;

[0386] Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result;

[0387] Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition;

[0388] Configuration information of the first condition.

[0389] In some embodiments, the first condition includes at least one of the following:

[0390] At the first predicted time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more predicted time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold;

[0391] At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell;

[0392] At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event;

[0393] The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

[0394] In some embodiments, the information processing method further includes:

[0395] The network device receives terminal capability information sent by the terminal, wherein the terminal capability information includes at least one of the following:

[0396] Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result;

[0397] Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell;

[0398] The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

[0399] In some embodiments, the information processing method further includes at least one of the following:

[0400] The network device receives a first decision result sent by the terminal; wherein the first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model;

[0401] The network device receives a performance monitoring result of the inference performance of the first AI or ML model sent by the terminal, and sends decision indication information to the terminal based on the performance monitoring result;

[0402] The network device monitors the inference performance of the first AI or ML model, determines a performance monitoring result, and sends decision indication information to the terminal based on the performance monitoring result;

[0403] The decision indication information is used to indicate the switched AI or ML model and / or to deactivate the first AI or ML model.

[0404] It should be noted that the information processing method on the network device side of the embodiment of the present disclosure and the information processing method on the terminal side are based on the same inventive concept. The two embodiments can refer to each other and can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0405] The network device involved in the embodiments of the present disclosure may be a base station, which may include multiple cells providing services to terminals. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in an access network that communicates with a wireless terminal through one or more sectors on an air interface, or may be called another name. The network device may be used to interchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The network device may also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present disclosure may be a base transceiver station (BTS) in the Global System for Mobile communications (GSM) or code division multiple access (CDMA), a network device (NodeB) in wide-band code division multiple access (WCDMA), an evolutionary Node B (eNB or e-NodeB) in the long term evolution (LTE) system, a 5G base station (gNB) in the 5G network architecture (next generation system), a home evolved Node B (HeNB), a relay node, a femto, a pico, etc., and is not limited in the embodiments of the present disclosure. In some network structures, the network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be geographically separated.

[0406] As shown in FIG3 , the embodiment of the present disclosure provides an information processing method, comprising the following steps:

[0407] Step 31: The terminal sends RRM measurement results related to the first AI or ML model input to the network device.

[0408] In some embodiments, the terminal sends an RRM measurement result related to the first AI or ML model input to the network device, including:

[0409] The terminal receives the configuration information sent by the network device;

[0410] The terminal sends, to the network device, an RRM measurement result related to the first AI or ML model input according to the configuration information; wherein the configuration information includes at least one of the following:

[0411] The reporting period for the terminal to report RRM measurement results; for example, this reporting period is used to indicate that the terminal should report continuously in one or more periods. For example, the terminal can report continuously in the period t1-t2, but not in the period t2-t3. For example, the network device can also configure reportAmount and reportInterval. As an implementation method, the terminal can continuously report reportAmount number of measurement results at an interval of reportInterval within the reporting period.

[0412] Second threshold: In some embodiments, the second threshold may also be agreed upon by a protocol.

[0413] The third threshold: In some embodiments, the third threshold may also be agreed upon by protocol.

[0414] Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following:

[0415] The time interval after the terminal last reported the RRM measurement result is greater than or equal to the second threshold; for example, the time interval may be called the running time, which may be configured by the network device or based on a protocol agreement.

[0416] The speed of the terminal changes; for example, the terminal changes from slow to fast, or the current speed of the terminal changes from the speed in the previous period T by more than a fourth threshold, etc. The embodiments of the present disclosure are not limited thereto.

[0417] The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

[0418] As shown in FIG4 , the embodiment of the present disclosure provides an information processing method, comprising the following steps:

[0419] Step 41: The network device receives a radio resource management RRM measurement result related to the first AI or ML model input sent by the terminal;

[0420] Step 42: The network device obtains first information output by a first AI or ML model based on the RRM measurement result;

[0421] Step 43: The network device performs handover-related processing according to the first information;

[0422] The first information includes at least one of the following parameters:

[0423] RRM prediction results;

[0424] Predicting cell information of the optimal cell;

[0425] The first prediction result is related to the occurrence of the predicted event.

[0426] In this embodiment, the network device side uses a first AI or ML model to infer the RRM measurement results reported by the terminal to obtain a prediction result (i.e., first information), and performs handover-related processing based on the first information. This is similar to the various embodiments in which the terminal side obtains the first information. The two embodiments can refer to each other and can achieve the same technical effects. To avoid repetition, they are not further described here.

[0427] In some embodiments, the network device performs handover-related processing according to the first information, including at least one of the following:

[0428] In a case where the first information includes an RRM prediction result, the network device performs handover-related processing according to the RRM prediction result;

[0429] In a case where the first information includes cell information of a predicted optimal cell, the network device performs handover-related processing according to the cell information of the predicted optimal cell;

[0430] In a case where the first information includes a first prediction result, the network device performs handover-related processing according to the first prediction result;

[0431] In a case where the first information includes an RRM prediction result, the network device determines the cell information of the predicted optimal cell and / or the first prediction result according to the RRM prediction result, and performs handover-related processing according to the cell information of the predicted optimal cell and / or the first prediction result;

[0432] In a case where the first information includes cell information of a predicted optimal cell, the network device determines the first prediction result according to the cell information of the predicted optimal cell, and performs cell handover-related processing according to the first prediction result.

[0433] In some embodiments, the first prediction result includes at least one of the following:

[0434] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0435] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0436] The fourth indication information is used to indicate the cells and / or beams that meet the switching conditions within the first prediction time period.

[0437] In some embodiments, the switching condition can be determined based on a measurement event, or a trigger condition for an event-triggered terminal measurement report, or the switching condition can be that a measurement event is satisfied and the measurement event is satisfied within a period of time. The length of the period of time can be configured by the network device side or based on a protocol agreement, etc. The embodiments of the present disclosure are not limited to this.

[0438] In some embodiments, the network device performs handover-related processing according to the first information, including at least one of the following:

[0439] In a case where the first prediction result includes second indication information, the network device performs handover-related processing according to the second indication information;

[0440] In a case where the first prediction result includes third indication information, the network device performs handover-related processing according to the third indication information;

[0441] In a case where the first prediction result includes fourth indication information, the network device performs handover-related processing according to the fourth indication information;

[0442] In a case where the first prediction result includes second indication information, the network device determines at least one of the first indication information, the third indication information, and the fourth indication information according to the second indication information, and performs handover-related processing according to at least one of the first indication information, the third indication information, and the fourth indication information;

[0443] In a case where the first prediction result includes third indication information, the network device determines the first indication information and / or the fourth indication information according to the third indication information, and performs handover-related processing according to the first indication information and / or the fourth indication information;

[0444] In a case where the first prediction result includes fourth indication information, the network device determines the first indication information according to the fourth indication information, and performs handover-related processing according to the first indication information;

[0445] Among them, the first indication information is used to indicate the change trend of the RRM prediction result corresponding to the first cell and / or the first beam, and the first cell and / or the first beam meets the switching condition.

[0446] In some embodiments, before the network device receives the radio resource management RRM measurement result related to the first artificial intelligence AI or machine learning ML model input sent by the terminal, it also includes:

[0447] The network device sends configuration information to the terminal; wherein the configuration information includes at least one of the following:

[0448] The reporting period for the terminal to report RRM measurement results;

[0449] second threshold;

[0450] third threshold;

[0451] Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following:

[0452] The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold;

[0453] The speed of the terminal changes;

[0454] The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

[0455] In some embodiments, the information processing method further includes:

[0456] The network device monitors the inference performance of the first AI or ML model and determines a performance monitoring result;

[0457] The network device performs AI or ML model switching and / or deactivates the first AI or ML model based on the performance monitoring result.

[0458] The information processing method on the network device side in the embodiment of the present disclosure and the information processing method on the terminal side are based on the same inventive concept. The two embodiments can refer to each other and can achieve the same technical effects. To avoid repetition, they will not be described here.

[0459] The information processing method disclosed herein is described below with reference to specific embodiments:

[0460] Example 1-1: When the AI / ML model is inferred on the UE side, the input of the AI / ML model is the RRM measurement results (or RRM measurement results) actually measured at one or more time points, and the output is the RRM prediction results predicted at one or more time points.

[0461] Step 1: AI / ML model inference On the UE side, the input of the AI / ML model is the actual RRM measurement results measured at one or more historical time points. Optionally, one or more of the following can be input: cell ID, beam ID, UE location, UE movement speed, UE movement trajectory, etc. The output is the RRM prediction results at one or more predicted time points. Optionally, the cell ID and / or beam ID can also be output.

[0462] Step 2: The UE reports its capabilities. For example, the UE may report at least one of the following capability information:

[0463] Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result;

[0464] Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell;

[0465] The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

[0466] For example, if the output of the AI / ML model is a predicted RRM prediction result, and the UE only needs to report the RRM prediction result, the UE can directly report the RRM prediction result. However, if the configuration requires the UE to process the RRM prediction result before reporting it, the UE must be capable of processing the RRM prediction result. For example, based on the AI / ML model output, the UE calculates and determines whether any cells will meet the triggering conditions for event-triggered reporting in the future (when the predicted event configured by the network meets the threshold and persists for a period of time). That is, at time t1, the AI / ML model infers and outputs the RRM prediction result in the future from t1 to t1+T. Based on this RRM prediction result, the UE calculates whether any cells will meet the triggering conditions for event-triggered reporting in the time from t1 to t1+T. If a time t2 (t2>0 and less than or equal to T) within the time from t1 to t1+T meets the triggering conditions for event-triggered reporting, the UE reports the possible occurrence of an event-triggered reporting within the time from t1 to t1+T, or at time t2. This capability can be bundled with the AI / ML model on the UE side. When the output of the AI / ML model on the UE side is the RMM prediction result, the UE can be considered to have this capability. Correspondingly, when the output of the AI / ML model is the cell information of the predicted optimal cell or the terminal is able to calculate and determine the predicted optimal cell, the terminal can be considered to have the ability to determine the predicted optimal cell, or when the output of the AI / ML model is the first prediction result or the terminal is able to calculate and determine the first prediction result, the terminal can be considered to have the ability to determine the first prediction result. No further details will be given here.

[0467] Step 3: Since the AI / ML model inference is performed on the UE side, the network device configures the UE-side prediction reporting. The configuration on the network device includes but is not limited to one or more of the following:

[0468] (1) Predicted reporting configuration: The network can configure the UE to predict event triggering one-time reporting, predicted event triggering periodic reporting, and predicted periodic reporting. Predicted periodic reporting is to configure the UE to periodically predict reporting; predicted event triggering periodic reporting means that when the triggering conditions for event triggering reporting are met, the UE periodically predicts reporting; predicted event triggering one-time reporting means that when the triggering conditions for event triggering reporting are met, the UE predicts reporting. The triggering conditions for event-triggered reporting can be events specified in the relevant protocol (such as the triggering conditions for measurement reporting), or some new events can be defined. For example, the AI ​​or ML model outputs a prediction result (that is, the event triggers prediction reporting after the AI / ML model completes the inference once); when there are cells and / or beams that meet the triggering conditions for measurement reporting at the predicted time point or predicted time period (that is, it is predicted that there will be cells and / or beams that meet the triggering conditions for event trigger reporting in the future (the triggering conditions for event trigger reporting can be configured as the triggering conditions for measurement reporting specified in the relevant protocol), the UE triggers the prediction reporting, that is, the UE uses the AI / ML model to perform inference at time t1, and the predicted time output by the AI / ML model after inference is t1 to t1+T. The UE calculates based on the output of the AI / ML model that there is a time t1+t2 (t2 is greater than 0 and less than or equal to T) within the time t1 to t1+T that meets the triggering conditions for event trigger reporting. The UE can report in advance that the triggering conditions for event trigger reporting are met at time t1+t2;

[0469] (2) Auxiliary reporting information: When measurement reporting is triggered, the network device side can configure some auxiliary reporting information for the UE to facilitate the network device side's handover decision. The auxiliary reporting information includes but is not limited to one or more of the following:

[0470] a) Sixth indication information is used to indicate whether the UE reports a change trend of the RRM prediction result. The change trend of the RRM prediction result refers to a change trend of the RRM prediction result within the predicted time period T, including but not limited to one of the following: from low to high, from high to low but not lower than a threshold value, from high to low and then lower than a threshold value, or almost unchanged (for example, the difference between the maximum and minimum values ​​is less than a threshold value). The time period T and the threshold value may be configured by the network device, or may not be configured, or may be based on protocol agreement, etc. For example, time period T may default to time C to B. If the AI / ML model outputs the RRM prediction result for the predicted future time period A to B, and the UE calculates and processes that the RRM prediction result satisfies the triggering condition for event-triggered reporting at future time C (C being a time between A and B), the UE may report the trend of the RRM prediction result from time C to time B based on the RRM prediction result, thereby assisting the network device in making a handover decision. For example, if the configuration is to report upon prediction of meeting the triggering condition for event-triggered reporting, that is, if the UE determines, based on the prediction result, that a cell in the future will meet the triggering condition for event-triggered reporting, the UE predicts and reports the prediction result for the future time in advance, reports the predicted result, and reports the predicted trend of the RRM prediction result. If the trend changes from high to low and then falls below a certain threshold, the network device may choose not to switch to the cell, because switching to the cell may result in handover failure.

[0471] b) The seventh indication information is used to indicate whether the terminal is allowed to determine whether to report the second information based on the first condition, or whether the UE does not report invalid data, that is, whether the UE can decide not to predict and report based on the output of the AI / ML model and some criteria (i.e., the first condition). For example, when the configuration is configured as item (1) in step 3 and predicts that an event will trigger reporting in the future, the UE triggers the prediction reporting configuration, but the UE calculates that a cell meets the triggering condition for event triggering reporting at a certain time t1+t2 in the future based on the output of the AI / ML model, but the AI / ML model prediction result of the cell within the time from t1+t2 to t1+T meets the UE's non-reporting criterion, then the UE will not predict and report. The UE's non-reporting criterion can be:

[0472] i. At a first predicted time point, the second cell and / or the second beam meets the triggering condition for event-triggered reporting, and at one or more predicted time points within a second predicted time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to a first threshold. For example: the cell is predicted to meet the measurement reporting condition at a future time t2, and the signal quality falls below a certain threshold one or more times between t2 and t2+t3. The threshold and time t3 can be configured by the network device side, or can be fixed values, for example, t3 is equal to T-t2;

[0473] ii. At the first predicted time point, the second cell meets the triggering conditions for event-triggered reporting, and within the second predicted time period, at least one of a handover failure, a radio link failure, and a ping-pong effect occurs in the second cell. For example, at a predicted future time t2, the cell meets the measurement reporting conditions, and a handover failure, a radio link failure, or a ping-pong effect occurs between t2 and t2+t3. The handover failure, radio link failure, or ping-pong effect can be events configured by the network device side, or can be some defined fixed events.

[0474] Step 4: Inference of the AI / ML model: The UE inputs the RRM measurement results actually measured at one or more time points into the AI / ML model, which then infers and outputs them.

[0475] Step 5: The UE predicts and reports based on the output of the AI / ML model and the configuration of the network device. The content reported by the UE includes but is not limited to one or more of the following:

[0476] (1) Direct reporting of RRM prediction results. The content reported by the UE includes:

[0477] a) Model identification, i.e., the shared understanding of the UE’s AI / ML capabilities by both the UE and network equipment during AI / ML model identification.

[0478] b) RRM prediction results and / or corresponding timestamps at one or more predicted time points, where the timestamps include but are not limited to the following:

[0479] i. At least one of the frame, subframe, time slot, and symbol where the RRM prediction result is located;

[0480] ii. UTC time and / or GPS time of the RRM prediction result;

[0481] iii. The time interval between the output time of the RRM prediction result and the prediction reporting time configured by the network device;

[0482] It should be noted that: if the UE reports the RRM prediction results at multiple prediction time points, the UE may report the timestamps corresponding to all RRM prediction results; it may also be the timestamp corresponding to any RRM prediction result, for example, reporting the timestamp corresponding to the first RRM prediction result, because if the network device side knows the interval between the time points predicted by the AI / ML model, then reporting the timestamp of one RRM prediction result can deduce the time of other RRM prediction results. If the timestamp corresponding to a non-first RRM prediction result is reported, the UE may also need to report the number of the RRM prediction result among the multiple prediction results reported;

[0483] (2) The RRM prediction results are processed and reported. The UE calculates the top K optimal cells at one or more predicted time points based on the RRM prediction results output by the AI / ML model, and then reports the calculated and processed information. The content reported by the UE includes but is not limited to at least one of the following: model identifier; one or more optimal cell IDs predicted at one or more predicted time points; RRM prediction results and / or corresponding timestamps. K can be a fixed value or can be configured by the network device side. At the predicted time t output by the AI / ML model, the UE reports the cells with the largest RRM prediction results among the top K as the optimal cells based on the RRM prediction results. For example: K is 2, the AI / ML model outputs the RRM prediction result of 20.2 for cell 1, 10.2 for cell 2, and 19.2 for cell 3 at time t. The UE predicts that the optimal cells at the reported time point t are 1 and 3.

[0484] (3) The RRM prediction results are processed and reported. The UE calculates the satisfaction of the measurement events of the cell at one or more predicted time points based on the RRM prediction results output by the AI / ML model and the measurement events configured on the network device side, and then reports the calculated and processed information. The content reported by the UE includes but is not limited to at least one of the following: model identification; the occurrence of the predicted events of the cell and / or beam at one or more predicted time points; the RRM prediction results and / or the corresponding timestamps. For example: the AI / ML model outputs the RRM prediction results of cell 1 at the predicted future time points t1, t2, and t3. The UE determines whether cell 1 meets the predicted events at time points t1, t2, and t3 based on the predicted events configured on the network device side (the predicted event is a formula with the RRM prediction result as a variable), and then makes a prediction report.

[0485] (4) The RRM prediction results are processed and reported. The UE calculates the cell IDs that meet the measurement events at one or more predicted time points based on the RRM prediction results output by the AI / ML model and the measurement events configured on the network device side, and then reports the calculated and processed information. The content reported by the UE includes but is not limited to at least one of the following: model identification; cell IDs that meet the prediction events predicted at one or more predicted time points; RRM prediction results and / or corresponding timestamps. For example: the AI / ML model outputs the RRM prediction results of cells 1, 2, and 3 at the predicted future time point t1. The UE determines whether there are cells that meet the prediction events at time point t1 based on the prediction events configured on the network device side (the prediction event is a formula with the RRM prediction results as variables), and then makes a prediction report.

[0486] (5) The RRM prediction results are processed and reported. The UE calculates whether there are cells that meet the trigger conditions for event trigger reporting within the prediction time based on the RRM prediction results output by the AI / ML model (the UE only reports when the predicted event configured by the network device enters the threshold and lasts for a period of time). The calculated and processed information is then reported. The reporting content includes but is not limited to at least one of the following: model identifier; cell ID and / or corresponding timestamp of the cell that is predicted to meet the trigger conditions for event trigger reporting (for example, the timestamp can be the time when the trigger conditions are met); RRM prediction results and / or corresponding timestamp; change trend of the RRM prediction results of the cells that are predicted to meet the trigger conditions for event trigger reporting. For example: The AI / ML model outputs the RRM prediction results of cell 1 at the predicted future time points t1, t2, ...tm...tn. The UE determines, based on the prediction event configured on the network device side (the prediction event is a formula with the RRM prediction result as a variable), that cell 1 meets the prediction event at time point tm, and that the prediction event is met from tm to tm+TTT (that is, the trigger condition for event triggering reporting is met, when the prediction event configured by the network device enters the threshold and lasts for a period of time (TTT)), and then performs the prediction report.

[0487] Step 6: The network device receives the information reported by the UE and makes a handover decision.

[0488] Step 7: Monitoring of AI / ML models. Model monitoring can be performed on the UE side or on the network device side.

[0489] (1) If the model monitoring is on the UE side and the decision is made on the UE side, the UE side's behavior includes but is not limited to the following:

[0490] a) The network device side configures specific monitoring parameters for the UE. For example, if the UE monitors the difference between the RRM prediction result output by the AI / ML model and the actual measured RRM measurement result at the same time point, the network device side configures a threshold value for the difference for the UE. If the actual difference detected by the UE at a certain moment is greater than the threshold value, the UE considers that the performance of the AI / ML model is poor at this time. If the UE monitors the ratio of at least one of the switching failures, wireless link failures, or ping-pong effects within a period of time T, the network device side configures a threshold value for the ratio and time T for the UE. If the ratio of at least one of the switching failures, wireless link failures, or ping-pong effects within time T is greater than a certain threshold value, the UE considers that the performance of the AI / ML model is poor at this time. When the performance of the AI / ML model is poor, the UE makes a corresponding decision and reports the decision to the network device side. The decision and reporting on the UE side include but are not limited to:

[0491] i. Switch the AI / ML model and report the switched AI / ML model to the network device;

[0492] ii. Deactivate the currently used AI / ML model, revert to a state where the AI / ML model is not in use, and report the information that the AI / ML model is no longer in use to the network device;

[0493] b) The parameters configured on the network device side in a) can be fixed values ​​on the UE side (for example, based on protocol agreement), that is, no configuration is required on the network device side. The behavior of using fixed values ​​for monitoring on the UE side is the same as a). When the performance of the AI / ML model is poor, the UE makes corresponding decisions and reports the decision results to the network device side. The decision and reporting on the UE side are the same as above.

[0494] c) The parameters configured on the network device side in a) can be fixed values ​​on the UE side, that is, no configuration is required on the network device side, and the UE side knows the value. The behavior of using fixed values ​​for monitoring on the UE side is the same as a). When the performance of the AI / ML model is poor, the UE makes corresponding decisions and does not report it to the network device.

[0495] (2) If the model monitoring is on the UE side and the decision is on the network device side, the UE side's behavior includes but is not limited to the following:

[0496] a) Monitoring on the UE side is the same as a) or b) in (1). When the AI / ML model performance is poor, the UE reports the monitoring results to the network device side, which makes the decision. The content reported by the UE side includes but is not limited to:

[0497] i. Model identification and magnitude of differences and / or ratios;

[0498] ii. Model identification and the difference and / or ratio exceeding a threshold, for example: the reported information includes a parameter, and the presence of the parameter indicates that the difference and / or ratio exceeds the threshold;

[0499] iii. Model identifier and the range where the difference and / or ratio exceeds the threshold. For example, if the difference threshold is 30 and the actual difference is 32, the UE reports the model identifier and 2;

[0500] b) The UE side does not have the concept of parameters such as thresholds. The UE side monitors the difference or ratio, and then reports the model identifier and the size of the difference and / or ratio.

[0501] (3) If the model monitoring is on the network device side, the decision is made on the network device side.

[0502] a) The network device indicates the reporting configuration to the UE, instructing the UE to report the RRM measurement results and RRM prediction results;

[0503] b) The UE reports RRM prediction results at one or more time points and RRM measurement results at one or more time points.

[0504] c) The network equipment side monitors and makes decisions based on the reports from the UE side.

[0505] Example 1-2: When the AI / ML model is inferred on the network device side, the input of the AI / ML model is the RRM measurement results actually measured at one or more time points, and the output is the RRM prediction results predicted at one or more time points.

[0506] Step 1: Inference of the AI / ML model on the network device side. The input of the AI / ML model on the network device side is the actual RRM measurement results on the UE side. The network device side needs to configure measurement reporting for the UE. Specifically, it may include one or more of the following:

[0507] (1) Reuse relevant protocols to configure measurement reporting for UE;

[0508] (2) Configuring a new event for event-triggered reporting (i.e., a trigger condition for measurement reporting) for the UE, where the trigger condition includes at least one of the following:

[0509] The time interval after the terminal last reported the RRM measurement result is greater than or equal to the second threshold; for example, the time interval between the current running time and the last report by the UE is T, and the UE triggers the report. T can be configured by the network device side or a fixed value;

[0510] When the terminal speed changes (i.e., the UE running speed changes), the UE triggers a report;

[0511] When the signal quality of the cell where the UE resides deteriorates or falls below a certain threshold, the UE triggers a report;

[0512] (3) Configure the UE for periodic reporting, but define a new parameter (for example, define the reporting period for the terminal to report RRM measurement results). The new parameter is used in conjunction with the original parameters (reportAmount, reportInterval) to enable the UE to continuously report measurement information at multiple time points within the period. For example, after configuring reportAmount and reportInterval, you can configure a new parameter A (reporting period A). The UE uses parameter A as the period and continuously reports reportAmount number of measurement results at intervals of reportInterval within period A.

[0513] Step 2: The UE performs measurement reporting according to the measurement reporting configuration on the network device side;

[0514] Step 3: The network equipment side infers the AI / ML model based on the measurement information reported by the UE side;

[0515] Step 4: Monitoring of AI / ML models. Model monitoring can be done on the network device side:

[0516] a) The network device indicates the reporting configuration to the UE, so that the UE reports the RRM measurement results actually measured at one or more time points;

[0517] b) The UE reports RRM measurement results at one or more time points;

[0518] c) The network equipment side monitors and makes decisions based on the reports from the UE side;

[0519] Example 2-1: Inference of AI / ML Model On the UE side, the input of the AI / ML model is the RRM measurement results actually measured at one or more time points, and the output is the predicted optimal cell at one or more predicted time points.

[0520] Step 1: The input of the AI / ML model is the same as that of Example 1-1, and the output is the predicted optimal cell ID at one or more predicted time points. The number of optimal cells that can be output at a predicted time point can be fixed or the number configured by the network device. Optionally, the RRM prediction result and / or corresponding timestamp of the optimal cell can be output.

[0521] Step 2: The UE reports its capabilities. This step is consistent with step 2 of Example 1-1.

[0522] Step 3: Since the AI / ML model inference is performed on the UE side, the network device configures the UE-side prediction reporting. The configuration on the network device includes but is not limited to one or more of the following:

[0523] (1) Prediction reporting configuration, same as Example 1-1.

[0524] (2) Auxiliary reporting information:

[0525] a) Whether the UE reports the RRM prediction results of the best cell at one or more predicted time points;

[0526] b) Other contents are the same as those in Example 1-1.

[0527] Step 4: Inference of the AI / ML model. This step is consistent with step 4 in Example 1-1.

[0528] Step 5: The UE makes a prediction report based on the output of the AI / ML model and the configuration of the network device. The content reported by the UE includes but is not limited to one or more of the following:

[0529] (1) The UE directly reports the prediction results. The content reported by the UE includes but is not limited to one or more of the following:

[0530] a) Model identification;

[0531] b) One or more optimal cell IDs and / or optimal cell RRM prediction results and / or timestamps predicted at one or more prediction time points, where the timestamp is the same as in Example 1-1.

[0532] (2) The optimal cell prediction result is processed and reported. The UE calculates whether the predicted event of the cell at one or more predicted time points is satisfied based on the optimal cell output by the AI / ML model and the measurement event configured on the network device side, and then reports the calculated and processed information. The content reported by the UE is the same as (3) of step 5 of embodiment 1-1;

[0533] (3) The optimal cell prediction result is processed and reported. The UE calculates the cell IDs that meet the prediction event at one or more predicted time points based on the optimal cell output by the AI / ML model and the prediction event configured on the network device side, and then reports the calculated and processed information. The content reported by the UE is the same as (4) of step 5 of embodiment 1-1;

[0534] (4) The optimal cell prediction result is processed and reported. The UE calculates whether there is a cell that meets the triggering condition for event triggering reporting within the prediction time based on the optimal cell output by the AI / ML model and the predicted event configured on the network device side (the UE only reports the calculated and processed information when the predicted event configured by the network device enters the threshold and lasts for a period of time). The reporting content is the same as step 5 (5) of Example 1-1.

[0535] Step 6: The network device receives the information reported by the UE and makes a handover decision.

[0536] Step 7: Monitoring of AI / ML Models:

[0537] (1) If the model monitoring is on the UE side, the decision is made on the UE side:

[0538] a) is basically the same as Example 1-1, but the UE also monitors the accuracy of the predicted optimal cell. For example, the AI / ML model output predicts the optimal cells at three time points as 1 and 2, but the actual measured optimal cells at time points 1 and 2 are 1 and 2, and the optimal cell at time point 3 is 3, then the accuracy is 2 / 3. Compared with Example 1-1a), the difference is that the network device side also needs to configure the accuracy threshold on the UE side.

[0539] (2) If the model monitoring is on the UE side and the decision is on the network device side:

[0540] a) is basically the same as Example 1-1, but the UE will also monitor the accuracy of predicting the best cell. The difference compared to Example 1-1a) is that the network device side needs to configure the accuracy threshold for the UE side. In addition, the content reported by the UE also includes:

[0541] i. Model identification and the accuracy of predicting the optimal cell;

[0542] ii. The accuracy of the model identification and prediction of the optimal cell exceeds the threshold;

[0543] iii. Model identification and the range where the accuracy of the predicted optimal cell exceeds the threshold.

[0544] (3) If the model monitoring is on the network device side, the decision is made on the network device side:

[0545] a) The network device sends a report configuration instruction to the UE, instructing the UE to report the predicted result of the best cell and the best cell actually measured;

[0546] b) The UE reports according to the configuration on the network device side;

[0547] c) The network equipment side monitors and makes decisions based on the reports from the UE side.

[0548] Example 2-2: Inference of AI / ML Model On the network device side, the input of the AI / ML model is the RRM measurement results actually measured at one or more time points, and the output is the predicted optimal cell at one or more predicted time points.

[0549] The steps of this embodiment are basically the same as those of Embodiment 1-2, but the monitoring of the AI / ML model on the network device side is as follows:

[0550] a) The network device side will report the configuration instructions to the UE, so that the UE reports the actual measured RRM results at one or more time points or the best cell at one or more time points.

[0551] b) The UE performs measurement reporting according to the configuration of the network device side;

[0552] c) The network equipment side monitors and makes decisions based on the reports from the UE side.

[0553] Example 3-1: Inference of AI / ML Model On the UE side, the input of the AI / ML model is the RRM measurement results actually measured at one or more time points, and the output is the predicted occurrence of predicted events at one or more time points.

[0554] Step 1: The input of the AI / ML model is the same as in Example 1-1. The output includes but is not limited to one or more of the following:

[0555] (1) The occurrence of a predicted event for a cell at one or more predicted time points. For example, 1 represents that the cell and / or beam meets the predicted event, and 0 represents that the cell and / or beam does not meet the predicted event. The AI / ML model outputs the prediction results for one to three time points as 0, 0, and 1, meaning that time points 1 and 2 do not meet the predicted event, and time point 3 meets the predicted event. Optionally, at least one of the following items can be output: cell ID, beam ID, corresponding timestamp, and RRM prediction result.

[0556] (2) The cell IDs and / or beam IDs that satisfy the predicted event at one or more predicted time points. At one time point, zero or more cells may satisfy the predicted event. For example, the AI / ML model outputs prediction results of 1, 11, and 19 at time point 1, meaning that cells 1, 11, and 19 satisfy the predicted event at time point 1. Optionally, the corresponding timestamps and / or RRM prediction results may be output.

[0557] (3) The cell ID and / or beam ID that meets the triggering conditions for event triggering reporting within the predicted time. That is, the output is only when the cell meets the predicted event at time T1 and the cell meets the predicted event from T1 to T1+TTT. For example, if the AI / ML model outputs 19 at time point t, that is, cell 19 meets the predicted event from t-TTT to t. Optionally, the corresponding timestamp and / or RRM prediction result can be output;

[0558] Step 2: The UE reports its capabilities. This step is consistent with step 2 of Example 1-1.

[0559] Step 3: Since the AI / ML model is inferred on the UE side, the network device can control the use of the AI / ML model on the UE side and the reporting of the UE-side prediction information. The information configured on the network device side may include one or more of the following:

[0560] (1) Auxiliary reporting information: When triggering measurement reporting, the network device side can configure some auxiliary reporting information for the UE to facilitate the network device side to make handover decisions. The auxiliary reporting information can be:

[0561] a) Whether to report RRM prediction results and / or corresponding timestamps at one or more prediction time points, where the timestamps are the same as those in Example 1-1;

[0562] b) Whether to not report invalid data: The same as in Example 1-1, and a new UE non-reporting criterion (i.e., the first condition) may be added:

[0563] At the first predicted time point, the second cell and / or the second beam meet the trigger conditions for event trigger reporting, and there are one or more predicted time points within the second predicted time period when the second cell and / or the second beam do not meet the predicted event.

[0564] For example: If the output of the AI / ML model is the satisfaction of a predicted event at one or more predicted time points, and it is predicted that the cell will meet the event trigger report at time T, but one or more cases of not meeting the predicted event occur between T and T+t1, then the UE does not need to perform a prediction report. The number of times the predicted event is not met and the time t1 can be configured by the network device side or can be a fixed value.

[0565] For another example: If the output of the AI / ML model is the cell ID that meets the predicted quantity event at one or more predicted time points, and it is predicted that the cell meets the triggering condition for event trigger reporting at time T, but one or more situations in which the predicted event is not met occur within the time from T to T+t1, then the UE does not need to perform a prediction report. The number of times the predicted event is not met and the time t1 can be configured by the network device side or can be a fixed value.

[0566] c) Other contents are the same as those in Example 1-1.

[0567] Step 4: Inference of the AI / ML model. This step is consistent with step 4 in Example 1-1.

[0568] Step 5: The UE performs measurement reporting based on the output of the AI / ML model and the configuration of the network device (periodic trigger reporting, event trigger reporting). The content reported by the UE can be one or more of the following:

[0569] (1) If the AI / ML model outputs the occurrence of a predicted event in a cell at one or more predicted time points (corresponding to the output (1) of the AI / ML model), the UE directly reports the prediction result, and the report content includes:

[0570] a) Model identification;

[0571] b) the occurrence of the predicted event at one or more predicted time points and / or the RRM prediction result and / or the corresponding timestamp, where the timestamp is the same as in Example 1-1;

[0572] (2) If the AI / ML model outputs the cell IDs that satisfy the predicted event at one or more predicted time points (corresponding to the output (2) of the AI / ML model), the UE directly reports the prediction results, and the reported content includes:

[0573] a) Model identification;

[0574] b) IDs of cells that meet the predicted event at one or more time points and / or RRM prediction results and / or corresponding timestamps, where the timestamps are the same as those in Example 1-1;

[0575] (3) If the AI / ML model outputs a cell ID that satisfies the triggering condition for event triggering reporting within the predicted time (corresponding to the output (3) of the AI / ML model), the UE directly reports the prediction result, and the report content includes:

[0576] a) Model identification;

[0577] b) the ID of the cell that meets the triggering conditions for event triggering reporting and / or the RRM prediction result and / or the corresponding timestamp and / or the change trend of the RRM prediction result, where the timestamp is the same as in Example 1-1;

[0578] (4) If the output of the AI / ML model is the output (1) or (2) of the AI / ML model, the UE calculates whether there are cells that meet the trigger conditions for event trigger reporting within the prediction time based on the output of the AI / ML model and the predicted events configured on the network device side (the UE only reports when the predicted events configured on the network device enter the threshold and last for a period of time), and the content of the report is the same as (3).

[0579] Step 6: The network device receives the information reported by the UE and makes a handover decision.

[0580] Step 7: Monitoring of AI / ML Models:

[0581] (1) If the model monitoring is on the UE side, the decision is made on the UE side:

[0582] a) is basically the same as Example 1-1, but the UE also monitors the accuracy of the predicted cell's predicted event satisfaction, the accuracy of the predicted cell ID that satisfies the predicted event, and the difference between the predicted time when the event triggers reporting and the actual time when the event triggers reporting. Compared to Example 1-1a), the difference is that the network device side needs to configure the thresholds of the above monitoring contents on the UE side.

[0583] (2) If the model monitoring is on the UE side and the decision is on the network device side:

[0584] a) is basically the same as Example 1-1, but the UE will also monitor the accuracy of the predicted cell's predicted event satisfaction, the accuracy of the predicted cell ID that satisfies the predicted event, and the difference between the predicted time of triggering the event report and the actual time of triggering the report. Compared with Example 1-1a), the difference is that the network device side needs to configure the threshold of the above monitoring content on the UE side. In addition, the content reported by the UE also includes:

[0585] i. Model identification and the accuracy of the predicted event satisfaction of the cell / the accuracy of the predicted cell ID that satisfies the predicted event / the difference between the predicted time when the event triggers reporting and the actual time when the event triggers reporting;

[0586] ii. Model identification and the accuracy of the predicted event satisfaction of the cell / the accuracy of the predicted cell ID that satisfies the predicted event / whether the difference between the predicted time of triggering the event report and the actual time of triggering the event report exceeds the threshold;

[0587] iii. Model identification and the accuracy of the predicted event satisfaction of the cell / accuracy of the predicted cell ID that satisfies the predicted event / the range within which the difference between the predicted time for triggering the event report and the actual time for triggering the event report exceeds the threshold;

[0588] (3) If the model monitoring is on the network device side, the decision is made on the network device side:

[0589] a) The network device side indicates the reporting configuration to the UE, instructing the UE to report at least one of the following: the RRM measurement results actually measured at one or more time points, the predicted satisfaction of the predicted event of the cell, the actual satisfaction of the predicted event of the cell, the predicted ID of the cell that satisfies the predicted event, the actual ID of the cell that satisfies the predicted event, and the difference between the predicted time when the event triggers reporting and the actual time when the event triggers reporting;

[0590] b) UE reports according to the configuration on the network device side;

[0591] c) The network equipment monitors and makes decisions based on the reports from the UE:

[0592] (1) The accuracy of the predicted event satisfaction of the predicted cell, that is, the ratio of the predicted event satisfaction at one or more time points predicted by the AI / ML model output to the actual predicted event satisfaction at one or more time points. For example, if the AI / ML model outputs the predicted event satisfaction of all nine time points of cell 1 as 1, but the actual measured predicted event satisfaction at all eight time points of cell 1 is 1, and the measured time satisfaction at time point 9 is 0, then the accuracy is 8 / 9 and the error rate is 1 / 9;

[0593] (2) The accuracy of the predicted cell IDs that meet the prediction event, that is, the ratio of the cell IDs that meet the prediction event at one or more time points predicted by the AI / ML model to the cell IDs that meet the measurement event at one or more time points. For example, if the AI / ML model outputs the predicted cell IDs that meet the prediction event at three time points, all of them are 1, 2, and 3, but the actual measured cell IDs that meet the measurement event at time points 1 and 2 are all 1, 2, and 3, and the cell ID that meets the measurement event at time point 3 is 1, then the accuracy is 1 / 3, and the error rate is 2 / 3;

[0594] (3) The difference between the predicted time when the event is triggered and reported and the actual time when the event is triggered and reported, that is, the difference between the predicted time when the event is triggered and reported output by the AI / ML model and the actual time when the event is triggered and reported. For example, if the AI / ML model predicts that the event is triggered and reported at the 200th ms, but the actual measured time when the event is triggered and reported is the 201st ms, then the difference is 1 ms;

[0595] Example 3-2: Inference of AI / ML Model On the network device side, the input of the AI / ML model is the RRM measurement results actually measured at one or more time points, and the output is the optimal cell at one or more time points.

[0596] d) The steps of this embodiment are consistent with those of embodiment 1-2;

[0597] The disclosed embodiments propose a prediction method for time domain measurement using an AI / ML model inferred on the UE side or the network device side. When the AI / ML model is inferred on the UE side, the UE reports the prediction results for one or more future time points based on the output of the AI / ML model inference. When the network device side receives the information reported by the UE side, it promptly performs corresponding processing to avoid wireless link failure, handover failure, or ping-pong effect after successful handover during the handover process. When the AI / ML model is inferred on the network device side, the network device side uses the actual measurement report of the UE side as the input of the AI / ML model to perform AI / ML model inference and early handover to avoid wireless link failure, handover failure, or ping-pong effect after successful handover during the handover process. In addition, the AI / ML model can predict measurement information at one or more future time points, reducing the actual measurement on the UE side, that is, the UE side can reduce the actual measurement at one or more future time points.

[0598] The above embodiments have introduced the information processing method disclosed herein. The following embodiments will further illustrate the corresponding apparatus, terminal, and network equipment in conjunction with the accompanying drawings.

[0599] As shown in FIG5 , this embodiment provides an information processing device, including a memory 51, a transceiver 52, and a processor 53. The memory 51 is used to store computer programs; the transceiver 52 is used to send and receive data under the control of the processor 53. For example, the transceiver 52 is used to receive and send data under the control of the processor 53; the processor 53 is used to read the computer program in the memory 51 and perform the following operations:

[0600] Determining radio resource management (RRM) measurements associated with a first artificial intelligence (AI) or machine learning (ML) model input;

[0601] Obtaining first information output by a first AI or ML model based on the RRM measurement result;

[0602] Sending second information to the network device according to the first information;

[0603] The first information and / or the second information includes at least one of the following parameters:

[0604] RRM prediction results;

[0605] Predicting cell information of the optimal cell;

[0606] The first prediction result is related to the occurrence of the predicted event.

[0607] In some embodiments, the processor 53 is configured to read the computer program in the memory 51 and perform at least one of the following operations:

[0608] In a case where the first information includes an RRM prediction result, determining that the second information includes the RRM prediction result;

[0609] In a case where the first information includes cell information of a predicted optimal cell, determining that the second information includes the cell information of the predicted optimal cell;

[0610] In a case where the first information includes a first prediction result, determining that the second information includes the first prediction result;

[0611] In a case where the first information includes an RRM prediction result, determining, according to the RRM prediction result, the cell information of the predicted optimal cell and / or the first prediction result, and determining that the second information includes the cell information of the predicted optimal cell and / or the first prediction result;

[0612] In a case where the first information includes cell information of a predicted optimal cell, the first prediction result is determined based on the cell information of the predicted optimal cell, and the second information is determined to include the first prediction result.

[0613] In some embodiments, the first information further includes at least one of the following parameters:

[0614] A timestamp corresponding to a prediction result output by the first AI or ML model; wherein the prediction result output by the first AI or ML model includes at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0615] Cell identification information corresponding to the RRM prediction result;

[0616] Beam identification information corresponding to the RRM prediction result.

[0617] In some embodiments, the second information further includes at least one of the following parameters:

[0618] identification information of the first AI or ML model;

[0619] identification information of the AI ​​or ML function corresponding to the first AI or ML model;

[0620] A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0621] The sequence number of the prediction result output by the first AI or ML model corresponding to the timestamp;

[0622] The time interval between the first AI or ML model outputting prediction results;

[0623] The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

[0624] In some embodiments, the timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, a coordinated universal time UTC, a global positioning system time GPST, and a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

[0625] In some embodiments, the first prediction result includes at least one of the following:

[0626] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0627] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0628] The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

[0629] In some embodiments, the processor 53 is configured to read the computer program in the memory 51 and perform at least one of the following operations:

[0630] In a case where the first prediction result includes second indication information, determining that the second information includes the second indication information;

[0631] In a case where the first prediction result includes third indication information, determining that the second information includes the third indication information;

[0632] In a case where the first prediction result includes fourth indication information, determining that the second information includes the fourth indication information;

[0633] In a case where the first prediction result includes second indication information, determining at least one of the first indication information, the third indication information, and the fourth indication information according to the second indication information, and determining that the second information includes at least one of the first indication information, the third indication information, and the fourth indication information;

[0634] In a case where the first prediction result includes third indication information, determining the first indication information and / or the fourth indication information according to the third indication information, and determining that the second information includes the first indication information and / or the fourth indication information;

[0635] In a case where the first prediction result includes fourth indication information, the first indication information is determined according to the fourth indication information, and it is determined that the second information includes the first indication information.

[0636] In some embodiments, the processor 53 is configured to read the computer program in the memory 51 and perform the following operations:

[0637] Receive configuration information sent by network devices;

[0638] sending the second information to the network device according to the configuration information;

[0639] The configuration information includes at least one of the following:

[0640] fifth indication information, used to indicate the parameters in the second information reported by the terminal;

[0641] Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result;

[0642] Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition;

[0643] Configuration information of the first condition.

[0644] In some embodiments, the first condition includes at least one of the following:

[0645] At the first predicted time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more predicted time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold;

[0646] At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell;

[0647] At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event;

[0648] The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

[0649] In some embodiments, the processor 53 is configured to read the computer program in the memory 51 and perform the following operations:

[0650] Sending terminal capability information to a network device; wherein the terminal capability information includes at least one of the following:

[0651] Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result;

[0652] Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell;

[0653] The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

[0654] In some embodiments, the triggering conditions for the event triggering reporting include, but are not limited to, at least one of the following:

[0655] The AI ​​or ML model outputs a prediction;

[0656] At the predicted time point, there are cells and / or beams that meet the triggering conditions for measurement reporting;

[0657] In the predicted time period, there are cells and / or beams that meet the triggering conditions for measurement reporting.

[0658] In some embodiments, the processor 53 is configured to read the computer program in the memory 51 and perform the following operations:

[0659] monitoring the inference performance of the first AI or ML model and determining a performance monitoring result;

[0660] Based on the performance monitoring result, perform at least one of the following operations:

[0661] Sending the performance monitoring result to the network device;

[0662] Perform AI or ML model switching;

[0663] deactivating the first AI or ML model;

[0664] Sending a first decision result to the network device; wherein the first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model.

[0665] In FIG5 , the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 53 and various circuits of memory represented by memory 51. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 52 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. For different user devices, the user interface 54 may also be an interface capable of connecting external or internal devices as required, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0666] The processor 53 is responsible for managing the bus architecture and general processing, and the memory 51 can store data used by the processor 53 when performing operations.

[0667] Optionally, the processor 53 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD), and the processor may also adopt a multi-core architecture.

[0668] The processor calls the computer program stored in the memory to execute any of the methods provided by the embodiments of the present disclosure according to the obtained executable instructions. The processor and the memory can also be arranged physically separately.

[0669] It should be noted here that the above-mentioned device provided by the embodiment of the present disclosure can implement all the method steps implemented by the above-mentioned terminal-side information processing method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0670] As shown in FIG6 , an embodiment of the present disclosure provides a terminal 600 including:

[0671] A measurement unit 610 is configured to determine a radio resource management (RRM) measurement result associated with a first artificial intelligence (AI) or machine learning (ML) model input;

[0672] A first processing unit 620 is configured to obtain first information output by a first AI or ML model based on the RRM measurement result;

[0673] A first sending unit 630 is configured to send second information to a network device according to the first information;

[0674] The first information and / or the second information includes at least one of the following parameters:

[0675] RRM prediction results;

[0676] Predicting cell information of the optimal cell;

[0677] The first prediction result is related to the occurrence of the predicted event.

[0678] In some embodiments, the terminal 600 determines the second information by at least one of the following methods:

[0679] In a case where the first information includes an RRM prediction result, determining that the second information includes the RRM prediction result;

[0680] In a case where the first information includes cell information of a predicted optimal cell, determining that the second information includes the cell information of the predicted optimal cell;

[0681] In a case where the first information includes a first prediction result, determining that the second information includes the first prediction result;

[0682] In a case where the first information includes an RRM prediction result, determining, according to the RRM prediction result, the cell information of the predicted optimal cell and / or the first prediction result, and determining that the second information includes the cell information of the predicted optimal cell and / or the first prediction result;

[0683] In a case where the first information includes cell information of a predicted optimal cell, the first prediction result is determined based on the cell information of the predicted optimal cell, and the second information is determined to include the first prediction result.

[0684] In some embodiments, the first information further includes at least one of the following parameters:

[0685] A timestamp corresponding to a prediction result output by the first AI or ML model; wherein the prediction result output by the first AI or ML model includes at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0686] Cell identification information corresponding to the RRM prediction result;

[0687] Beam identification information corresponding to the RRM prediction result.

[0688] In some embodiments, the second information further includes at least one of the following parameters:

[0689] identification information of the first AI or ML model;

[0690] identification information of the AI ​​or ML function corresponding to the first AI or ML model;

[0691] A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0692] The sequence number of the prediction result output by the first AI or ML model corresponding to the timestamp;

[0693] The time interval between the first AI or ML model outputting prediction results;

[0694] The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

[0695] In some embodiments, the timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, a coordinated universal time UTC, a global positioning system time GPST, and a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

[0696] In some embodiments, the first prediction result includes at least one of the following:

[0697] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0698] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0699] The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

[0700] In some embodiments, the terminal 600 determines the second information by at least one of the following methods:

[0701] In a case where the first prediction result includes second indication information, determining that the second information includes the second indication information;

[0702] In a case where the first prediction result includes third indication information, determining that the second information includes the third indication information;

[0703] In a case where the first prediction result includes fourth indication information, determining that the second information includes the fourth indication information;

[0704] In a case where the first prediction result includes second indication information, determining at least one of the first indication information, the third indication information, and the fourth indication information according to the second indication information, and determining that the second information includes at least one of the first indication information, the third indication information, and the fourth indication information;

[0705] In a case where the first prediction result includes third indication information, determining the first indication information and / or the fourth indication information according to the third indication information, and determining that the second information includes the first indication information and / or the fourth indication information;

[0706] In a case where the first prediction result includes fourth indication information, the first indication information is determined according to the fourth indication information, and it is determined that the second information includes the first indication information.

[0707] In some embodiments, the terminal 600 further includes:

[0708] A receiving unit, configured to receive configuration information sent by a network device;

[0709] The first sending unit 630 is further configured to:

[0710] sending the second information to the network device according to the configuration information;

[0711] The configuration information includes at least one of the following:

[0712] fifth indication information, used to indicate the parameters in the second information reported by the terminal;

[0713] Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result;

[0714] Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition;

[0715] Configuration information of the first condition.

[0716] In some embodiments, the first condition includes at least one of the following:

[0717] At the first predicted time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more predicted time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold;

[0718] At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell;

[0719] At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event;

[0720] The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

[0721] In some embodiments, the terminal 600 further includes:

[0722] The second sending unit is configured to send the terminal capability information to the network device; wherein the terminal capability information includes at least one of the following:

[0723] Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result;

[0724] Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell;

[0725] The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

[0726] In some embodiments, the triggering conditions for the event triggering reporting include, but are not limited to, at least one of the following:

[0727] The AI ​​or ML model outputs a prediction;

[0728] At the predicted time point, there are cells and / or beams that meet the triggering conditions for measurement reporting;

[0729] In the predicted time period, there are cells and / or beams that meet the triggering conditions for measurement reporting.

[0730] In some embodiments, the terminal 600 further includes:

[0731] a detection unit, configured to monitor the inference performance of the first AI or ML model and determine a performance monitoring result;

[0732] The second processing unit is configured to perform at least one of the following operations based on the performance monitoring result:

[0733] Sending the performance monitoring result to the network device;

[0734] Perform AI or ML model switching;

[0735] deactivating the first AI or ML model;

[0736] Sending a first decision result to the network device; wherein the first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model.

[0737] It should be noted here that the above-mentioned terminal provided by the embodiment of the present disclosure can implement all the method steps implemented by the information processing embodiment on the above-mentioned terminal side, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0738] As shown in FIG7 , an embodiment of the present disclosure provides an information processing device, including a memory 71, a transceiver 72, and a processor 73. The memory 71 is used to store computer programs; the transceiver 72 is used to send and receive data under the control of the processor 73; for example, the transceiver 72 is used to receive and send data under the control of the processor 73; and the processor 73 is used to read the computer program in the memory 71 and perform the following operations:

[0739] receiving second information sent by the terminal;

[0740] performing handover-related processing according to the second information;

[0741] The second information includes at least one of the following:

[0742] Radio Resource Management RRM prediction results;

[0743] Predicting cell information of the optimal cell;

[0744] The first prediction result is related to the occurrence of the predicted event.

[0745] In some embodiments, the second information further includes at least one of the following parameters:

[0746] First, identification information of the artificial intelligence (AI) or machine learning (ML) model;

[0747] identification information of the AI ​​or ML function corresponding to the first AI or ML model;

[0748] A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0749] the number of prediction results output by the first AI or ML model corresponding to the timestamp;

[0750] The time interval between the first AI or ML model outputting prediction results;

[0751] The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

[0752] In some embodiments, the timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, a coordinated universal time UTC, a global positioning system time GPST, and a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

[0753] In some embodiments, the first prediction result includes at least one of the following:

[0754] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0755] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0756] The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

[0757] In some embodiments, the processor 73 is configured to read the computer program in the memory 71 and perform the following operations:

[0758] Sending configuration information to the terminal; wherein the configuration information includes at least one of the following:

[0759] fifth indication information, used to indicate the parameters in the second information reported by the terminal;

[0760] Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result;

[0761] Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition;

[0762] Configuration information of the first condition.

[0763] In some embodiments, the first condition includes at least one of the following:

[0764] At the first predicted time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more predicted time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold;

[0765] At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell;

[0766] At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event;

[0767] The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

[0768] In some embodiments, the processor 73 is configured to read the computer program in the memory 71 and perform the following operations:

[0769] Receive terminal capability information sent by the terminal; wherein the terminal capability information includes at least one of the following:

[0770] Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result;

[0771] Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell;

[0772] The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

[0773] In some embodiments, the processor 73 is configured to read the computer program in the memory 71 and perform at least one of the following operations:

[0774] Receiving a first decision result sent by the terminal; wherein the first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model;

[0775] receiving a performance monitoring result of the inference performance of the first AI or ML model sent by a terminal, and sending decision indication information to the terminal based on the performance monitoring result;

[0776] monitoring the inference performance of the first AI or ML model, determining a performance monitoring result, and sending decision indication information to the terminal based on the performance monitoring result;

[0777] The decision indication information is used to indicate the switched AI or ML model and / or to deactivate the first AI or ML model.

[0778] In FIG7 , the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 73 and various circuits of memory represented by memory 71. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 72 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. The processor 73 is responsible for managing the bus architecture and general processing, and the memory 71 may store data used by the processor 73 when performing operations.

[0779] The processor 73 may be a CPU, ASIC, FPGA or CPLD, and the processor may also adopt a multi-core architecture.

[0780] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned method embodiment and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0781] As shown in FIG8 , an embodiment of the present disclosure provides a network device 800, including:

[0782] A first receiving unit 810 is configured to receive second information sent by a terminal;

[0783] A first processing unit 820 is configured to perform handover-related processing according to the second information;

[0784] The second information includes at least one of the following:

[0785] Radio Resource Management RRM prediction results;

[0786] Predicting cell information of the optimal cell;

[0787] The first prediction result is related to the occurrence of the predicted event.

[0788] In some embodiments, the second information further includes at least one of the following parameters:

[0789] First, identification information of the artificial intelligence (AI) or machine learning (ML) model;

[0790] identification information of the AI ​​or ML function corresponding to the first AI or ML model;

[0791] A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result;

[0792] the number of prediction results output by the first AI or ML model corresponding to the timestamp;

[0793] The time interval between the first AI or ML model outputting prediction results;

[0794] The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

[0795] In some embodiments, the timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, a coordinated universal time UTC, a global positioning system time GPST, and a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

[0796] In some embodiments, the first prediction result includes at least one of the following:

[0797] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0798] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0799] The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

[0800] In some embodiments, the network device 800 further includes:

[0801] A sending unit, configured to send configuration information to the terminal; wherein the configuration information includes at least one of the following:

[0802] fifth indication information, used to indicate the parameters in the second information reported by the terminal;

[0803] Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result;

[0804] Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition;

[0805] Configuration information of the first condition.

[0806] In some embodiments, the first condition includes at least one of the following:

[0807] At the first predicted time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more predicted time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold;

[0808] At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell;

[0809] At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event;

[0810] The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

[0811] In some embodiments, the network device further includes:

[0812] The second receiving unit is configured to receive terminal capability information sent by the terminal, wherein the terminal capability information includes at least one of the following:

[0813] Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result;

[0814] Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell;

[0815] The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

[0816] In some embodiments, the network device further includes at least one of the following:

[0817] A third receiving unit is configured to receive a first decision result sent by the terminal; wherein the first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model;

[0818] a second processing unit, configured to receive a performance monitoring result of the inference performance of the first AI or ML model sent by the terminal, and send decision indication information to the terminal based on the performance monitoring result;

[0819] a monitoring unit, configured to monitor the inference performance of the first AI or ML model, determine a performance monitoring result, and send decision indication information to the terminal based on the performance monitoring result;

[0820] The decision indication information is used to indicate the switched AI or ML model and / or to deactivate the first AI or ML model.

[0821] It should be noted here that the above-mentioned network device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned network device side information processing method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0822] As shown in FIG9 , this embodiment provides an information processing device, including a memory 91, a transceiver 92, and a processor 93. The memory 91 is used to store computer programs; the transceiver 92 is used to send and receive data under the control of the processor 93. For example, the transceiver 92 is used to receive and send data under the control of the processor 93; the processor 93 is used to read the computer program in the memory 91 and perform the following operations:

[0823] Sending radio resource management (RRM) measurement results associated with the first artificial intelligence (AI) or machine learning (ML) model input to the network device.

[0824] In some embodiments, the processor 93 is configured to read the computer program in the memory 91 and perform the following operations:

[0825] receiving configuration information sent by the network device;

[0826] Sending, to the network device, RRM measurement results related to the first AI or ML model input according to the configuration information, wherein the configuration information includes at least one of the following:

[0827] The reporting period for the terminal to report RRM measurement results;

[0828] second threshold;

[0829] third threshold;

[0830] Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following:

[0831] The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold;

[0832] The speed of the terminal changes;

[0833] The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

[0834] In FIG9 , the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 93 and various circuits of memory represented by memory 91. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 92 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. For different user devices, the user interface 94 may also be an interface capable of connecting external or internal devices as required, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0835] The processor 93 is responsible for managing the bus architecture and general processing, and the memory 91 can store data used by the processor 93 when performing operations.

[0836] Optionally, the processor 93 may be a CPU, an ASIC, an FPGA or a CPLD, and the processor may also adopt a multi-core architecture.

[0837] The processor calls the computer program stored in the memory to execute any of the methods provided by the embodiments of the present disclosure according to the obtained executable instructions. The processor and the memory can also be arranged physically separately.

[0838] It should be noted here that the above-mentioned device provided by the embodiment of the present disclosure can implement all the method steps implemented by the above-mentioned terminal-side information processing method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0839] As shown in FIG10 , an embodiment of the present disclosure provides a terminal 1000, including:

[0840] The sending unit 1010 is configured to send a radio resource management (RRM) measurement result related to a first artificial intelligence (AI) or machine learning (ML) model input to a network device.

[0841] In some embodiments, the sending unit 1010 is further configured to:

[0842] receiving configuration information sent by the network device;

[0843] Sending, to the network device, RRM measurement results related to the first AI or ML model input according to the configuration information, wherein the configuration information includes at least one of the following:

[0844] The reporting period for the terminal to report RRM measurement results;

[0845] second threshold;

[0846] third threshold;

[0847] Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following:

[0848] The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold;

[0849] The speed of the terminal changes;

[0850] The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

[0851] It should be noted here that the above-mentioned terminal provided in the embodiment of the present disclosure can implement all the method steps implemented in the information processing method embodiment on the above-mentioned terminal side, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0852] As shown in FIG11 , an embodiment of the present disclosure provides an information processing device, including a memory 111, a transceiver 112, and a processor 113. The memory 111 is used to store computer programs; the transceiver 112 is used to send and receive data under the control of the processor 113; for example, the transceiver 112 is used to receive and send data under the control of the processor 113; and the processor 113 is used to read the computer program in the memory 111 and perform the following operations:

[0853] Receiving a radio resource management RRM measurement result related to a first artificial intelligence AI or machine learning ML model input sent by a terminal;

[0854] Obtaining first information output by a first AI or ML model based on the RRM measurement result;

[0855] performing handover-related processing according to the first information;

[0856] The first information includes at least one of the following parameters:

[0857] RRM prediction results;

[0858] Predicting cell information of the optimal cell;

[0859] The first prediction result is related to the occurrence of the predicted event.

[0860] In some embodiments, the processor 113 is configured to read the computer program in the memory 111 and perform at least one of the following operations:

[0861] In a case where the first information includes an RRM prediction result, performing handover-related processing according to the RRM prediction result;

[0862] In a case where the first information includes cell information of a predicted optimal cell, performing handover-related processing according to the cell information of the predicted optimal cell;

[0863] In a case where the first information includes a first prediction result, performing switching-related processing according to the first prediction result;

[0864] In a case where the first information includes an RRM prediction result, determining cell information of the predicted optimal cell and / or the first prediction result according to the RRM prediction result, and performing handover-related processing according to the cell information of the predicted optimal cell and / or the first prediction result;

[0865] In a case where the first information includes cell information of a predicted optimal cell, the first prediction result is determined based on the cell information of the predicted optimal cell, and cell handover related processing is performed based on the first prediction result.

[0866] In some embodiments, the first prediction result includes at least one of the following:

[0867] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0868] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0869] The fourth indication information is used to indicate the cells and / or beams that meet the switching conditions within the first prediction time period.

[0870] In some embodiments, the processor 113 is configured to read the computer program in the memory 111 and perform at least one of the following operations:

[0871] In a case where the first prediction result includes second indication information, performing handover-related processing according to the second indication information;

[0872] In a case where the first prediction result includes third indication information, performing handover-related processing according to the third indication information;

[0873] In a case where the first prediction result includes fourth indication information, performing switching-related processing according to the fourth indication information;

[0874] In a case where the first prediction result includes second indication information, determining at least one of the first indication information, the third indication information, and the fourth indication information according to the second indication information, and performing handover-related processing according to at least one of the first indication information, the third indication information, and the fourth indication information;

[0875] In a case where the first prediction result includes third indication information, determining first indication information and / or fourth indication information according to the third indication information, and performing handover-related processing according to the first indication information and / or the fourth indication information;

[0876] In a case where the first prediction result includes fourth indication information, determining first indication information according to the fourth indication information, and performing handover-related processing according to the first indication information;

[0877] Among them, the first indication information is used to indicate the change trend of the RRM prediction result corresponding to the first cell and / or the first beam, and the first cell and / or the first beam meets the switching condition.

[0878] In some embodiments, the processor 113 is configured to read the computer program in the memory 111 and perform the following operations:

[0879] Send configuration information to the terminal; wherein the configuration information includes at least one of the following:

[0880] The reporting period for the terminal to report RRM measurement results;

[0881] second threshold;

[0882] third threshold;

[0883] Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following:

[0884] The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold;

[0885] The speed of the terminal changes;

[0886] The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

[0887] In some embodiments, the processor 113 is configured to read the computer program in the memory 111 and perform the following operations:

[0888] monitoring the inference performance of the first AI or ML model and determining a performance monitoring result;

[0889] According to the performance monitoring result, perform AI or ML model switching and / or deactivate the first AI or ML model.

[0890] In FIG11 , the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 113 and various circuits of memory represented by memory 111. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 112 may be a plurality of components, i.e., a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, such as a wireless channel, a wired channel, an optical cable, or the like. The processor 113 is responsible for managing the bus architecture and general processing, and the memory 111 may store data used by the processor 113 when performing operations.

[0891] The processor 113 may be a CPU, an ASIC, an FPGA, or a CPLD, and the processor may also adopt a multi-core architecture.

[0892] It should be noted here that the above-mentioned device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned network device side information processing method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0893] As shown in FIG12 , an embodiment of the present disclosure provides a network device 1200, including:

[0894] The receiving unit 1210 is configured to receive a radio resource management (RRM) measurement result related to a first artificial intelligence (AI) or machine learning (ML) model input sent by a terminal;

[0895] an inference unit 1220, configured to obtain first information output by a first AI or ML model based on the RRM measurement result;

[0896] The processing unit 1230 is configured to perform handover-related processing according to the first information;

[0897] The first information includes at least one of the following parameters:

[0898] RRM prediction results;

[0899] Predicting cell information of the optimal cell;

[0900] The first prediction result is related to the occurrence of the predicted event.

[0901] In some embodiments, the processing unit 1230 is further configured to:

[0902] In a case where the first information includes an RRM prediction result, performing handover-related processing according to the RRM prediction result;

[0903] In a case where the first information includes cell information of a predicted optimal cell, performing handover-related processing according to the cell information of the predicted optimal cell;

[0904] In a case where the first information includes a first prediction result, performing switching-related processing according to the first prediction result;

[0905] In a case where the first information includes an RRM prediction result, determining cell information of the predicted optimal cell and / or the first prediction result according to the RRM prediction result, and performing handover-related processing according to the cell information of the predicted optimal cell and / or the first prediction result;

[0906] In a case where the first information includes cell information of a predicted optimal cell, the first prediction result is determined based on the cell information of the predicted optimal cell, and cell handover related processing is performed based on the first prediction result.

[0907] In some embodiments, the first prediction result includes at least one of the following:

[0908] Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points;

[0909] The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points;

[0910] The fourth indication information is used to indicate the cells and / or beams that meet the switching conditions within the first prediction time period.

[0911] In some embodiments, the processing unit 1230 is further configured to:

[0912] In a case where the first prediction result includes second indication information, performing handover-related processing according to the second indication information;

[0913] In a case where the first prediction result includes third indication information, performing handover-related processing according to the third indication information;

[0914] In a case where the first prediction result includes fourth indication information, performing switching-related processing according to the fourth indication information;

[0915] In a case where the first prediction result includes second indication information, determining at least one of the first indication information, the third indication information, and the fourth indication information according to the second indication information, and performing handover-related processing according to at least one of the first indication information, the third indication information, and the fourth indication information;

[0916] In a case where the first prediction result includes third indication information, determining first indication information and / or fourth indication information according to the third indication information, and performing handover-related processing according to the first indication information and / or the fourth indication information;

[0917] In a case where the first prediction result includes fourth indication information, determining first indication information according to the fourth indication information, and performing handover-related processing according to the first indication information;

[0918] Among them, the first indication information is used to indicate the change trend of the RRM prediction result corresponding to the first cell and / or the first beam, and the first cell and / or the first beam meets the switching condition.

[0919] In some embodiments, the network device 1200 further includes:

[0920] A sending unit, configured to send configuration information to the terminal; wherein the configuration information includes at least one of the following:

[0921] The reporting period for the terminal to report RRM measurement results;

[0922] second threshold;

[0923] third threshold;

[0924] Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following:

[0925] The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold;

[0926] The speed of the terminal changes;

[0927] The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

[0928] In some embodiments, the network device 1200 further includes:

[0929] a monitoring unit, configured to monitor the inference performance of the first AI or ML model and determine a performance monitoring result;

[0930] A decision-making unit is configured to execute AI or ML model switching and / or deactivate the first AI or ML model based on the performance monitoring result.

[0931] It should be noted here that the above-mentioned network device provided in the embodiment of the present disclosure can implement all the method steps implemented in the above-mentioned network device side information processing method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0932] It should be noted that the division of units in the embodiments of the present disclosure is schematic and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0933] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0934] An embodiment of the present disclosure also provides a processor-readable storage medium, which stores a computer program. The computer program is used to enable the processor to execute the steps of the above-mentioned information processing method on the terminal side or the network device side, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0935] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as compact discs (CD), digital video discs (DVD), Blu-ray discs (BD), high-definition versatile discs (HVD), etc.), and semiconductor memory (such as ROM, erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), non-volatile memory (NAND (Non-volatile Memory Device) FLASH), solid-state drives (SSD)), etc.

[0936] The embodiment of the present disclosure also provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, the various processes of the above-mentioned information processing method embodiment on the terminal side or the network device side are implemented, and the same technical effect can be achieved. To avoid repetition, they will not be repeated here.

[0937] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0938] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0939] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0940] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0941] In addition, it should be noted that, in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it will be understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0942] In addition, it should be noted that, in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it will be understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0943] It should be noted that it should be understood that the division of the above modules is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. Moreover, these modules can all be implemented in the form of software called by a processing element; or they can all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, a module can be a separately established processing element, or it can be integrated into a chip of the above-mentioned device. In addition, it can also be stored in the memory of the above-mentioned device in the form of program code, and called by a processing element of the above-mentioned device to perform the functions of the above-mentioned module. The implementation of other modules is similar. In addition, these modules can all or partly be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0944] For example, each module, unit, sub-unit or sub-module can be one or more integrated circuits configured to implement the above method, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented by scheduling program code through a processing element, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0945] The terms "first," "second," and the like in the specification and claims of the present disclosure are used to distinguish similar objects and are not necessarily 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 the present disclosure described herein may be implemented in a sequence other than that illustrated or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units need not be limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or devices. In addition, the use of "and / or" in the specification and claims to indicate at least one of the connected objects, for example, A and / or B and / or C, means that seven situations are included: A alone, B alone, C alone, both A and B present, both B and C present, both A and C present, and all A, B, and C present. Similarly, the use of "at least one of A and B" in the specification and claims should be understood to mean "A alone, B alone, or both A and B present."

[0946] Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include these modifications and variations.

Claims

1. An information processing method, comprising: The terminal determines a radio resource management RRM measurement result related to a first artificial intelligence AI or machine learning ML model input; The terminal obtains, according to the RRM measurement result, first information output by a first AI or ML model; The terminal sends second information to the network device according to the first information; The first information and / or the second information includes at least one of the following parameters: RRM prediction results; Predicting cell information of the optimal cell; The first prediction result is related to the occurrence of the predicted event.

2. The information processing method according to claim 1, wherein: The terminal determines the second information by at least one of the following methods: In a case where the first information includes an RRM prediction result, the terminal determines that the second information includes the RRM prediction result; In a case where the first information includes cell information of a predicted optimal cell, the terminal determines that the second information includes the cell information of the predicted optimal cell; In a case where the first information includes a first prediction result, the terminal determines that the second information includes the first prediction result; In a case where the first information includes an RRM prediction result, the terminal determines, according to the RRM prediction result, the cell information of the predicted optimal cell and / or the first prediction result, and determines that the second information includes the cell information of the predicted optimal cell and / or the first prediction result; In a case where the first information includes cell information of a predicted optimal cell, the terminal determines the first prediction result according to the cell information of the predicted optimal cell, and determines that the second information includes the first prediction result.

3. The information processing method according to claim 1, wherein: The first information further includes at least one of the following parameters: A timestamp corresponding to a prediction result output by the first AI or ML model; wherein the prediction result output by the first AI or ML model includes at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result; Cell identification information corresponding to the RRM prediction result; Beam identification information corresponding to the RRM prediction result.

4. The information processing method according to claim 1, wherein: The second information further includes at least one of the following parameters: identification information of the first AI or ML model; identification information of the AI ​​or ML function corresponding to the first AI or ML model; A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result; The sequence number of the prediction result output by the first AI or ML model corresponding to the timestamp; The time interval between the first AI or ML model outputting prediction results; The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

5. The information processing method according to claim 3 or 4, wherein: The timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, a coordinated universal time UTC, a global positioning system time GPST, and a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

6. The information processing method according to any one of claims 1 to 4, wherein: The first prediction result includes at least one of the following: Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points; The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points; The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

7. The information processing method according to claim 6, wherein: The terminal determines the second information by at least one of the following methods: In a case where the first prediction result includes second indication information, the terminal determines that the second information includes the second indication information; In a case where the first prediction result includes third indication information, the terminal determines that the second information includes the third indication information; In a case where the first prediction result includes fourth indication information, the terminal determines that the second information includes the fourth indication information; In a case where the first prediction result includes second indication information, the terminal determines, based on the second indication information, at least one of the first indication information, the third indication information, and the fourth indication information, and determines that the second information includes at least one of the first indication information, the third indication information, and the fourth indication information; In a case where the first prediction result includes third indication information, the terminal determines the first indication information and / or the fourth indication information according to the third indication information, and determines that the second information includes the first indication information and / or the fourth indication information; In a case where the first prediction result includes fourth indication information, the terminal determines the first indication information according to the fourth indication information, and determines that the second information includes the first indication information.

8. The information processing method according to any one of claims 1 to 4, further comprising: The terminal receives configuration information sent by the network device; The terminal sending second information to the network device includes: The terminal sends the second information to the network device according to the configuration information; The configuration information includes at least one of the following: fifth indication information, used to indicate the parameters in the second information reported by the terminal; Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result; Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition; Configuration information of the first condition.

9. The information processing method according to claim 8, wherein: The first condition includes at least one of the following: At the first prediction time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more prediction time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold; At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell; At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event; The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

10. The information processing method according to claim 8, further comprising: The terminal sends terminal capability information to the network device; wherein the terminal capability information includes at least one of the following: Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result; Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell; The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

11. The information processing method according to claim 4, 6 or 10, wherein: The trigger conditions for triggering the reporting of the event include but are not limited to at least one of the following: The AI ​​or ML model outputs a prediction; At the predicted time point, there are cells and / or beams that meet the triggering conditions for measurement reporting; In the predicted time period, there are cells and / or beams that meet the triggering conditions for measurement reporting.

12. The information processing method according to any one of claims 1 to 4, further comprising: The terminal monitors the inference performance of the first AI or ML model and determines a performance monitoring result; The terminal performs at least one of the following operations based on the performance monitoring result: Sending the performance monitoring result to the network device; Perform AI or ML model switching; Deactivating the first AI or ML model; Sending a first decision result to the network device; wherein the first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model.

13. An information processing method, comprising: The network device receives the second information sent by the terminal; The network device performs handover-related processing according to the second information; The second information includes at least one of the following: Radio Resource Management RRM prediction results; Predicting cell information of the optimal cell; The first prediction result is related to the occurrence of the predicted event.

14. The information processing method according to claim 13, wherein: The second information further includes at least one of the following parameters: First, identification information of the artificial intelligence (AI) or machine learning (ML) model; identification information of the AI ​​or ML function corresponding to the first AI or ML model; A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result; the number of prediction results output by the first AI or ML model corresponding to the timestamp; The time interval between the first AI or ML model outputting prediction results; The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

15. The information processing method according to claim 14, wherein: The timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, a coordinated universal time UTC, a global positioning system time GPST, and a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

16. The information processing method according to claim 13 or 14, wherein: The first prediction result includes at least one of the following: Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points; The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points; The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

17. The information processing method according to claim 13 or 14, further comprising: The network device sends configuration information to the terminal; wherein the configuration information includes at least one of the following: fifth indication information, used to indicate the parameters in the second information reported by the terminal; Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result; Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition; Configuration information of the first condition.

18. The information processing method according to claim 17, wherein: The first condition includes at least one of the following: At the first prediction time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more prediction time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold; At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell; At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event; The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

19. The information processing method according to claim 17, further comprising: The network device receives terminal capability information sent by the terminal, wherein the terminal capability information includes at least one of the following: Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result; Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell; The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

20. The information processing method according to claim 13 or 14, further comprising at least one of the following: The network device receives a first decision result sent by the terminal; wherein, The first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model; The network device receives a performance monitoring result of the inference performance of the first AI or ML model sent by the terminal, and sends decision indication information to the terminal based on the performance monitoring result; The network device monitors the inference performance of the first AI or ML model, determines a performance monitoring result, and sends decision indication information to the terminal based on the performance monitoring result; The decision indication information is used to indicate the switched AI or ML model and / or to deactivate the first AI or ML model.

21. An information processing method, comprising: The terminal sends a radio resource management RRM measurement result related to the first artificial intelligence AI or machine learning ML model input to the network device.

22. The information processing method according to claim 21, wherein: The terminal sends a radio resource management RRM measurement result related to the first artificial intelligence AI or machine learning ML model input to the network device, including: The terminal receives the configuration information sent by the network device; The terminal sends, to the network device, an RRM measurement result related to the first AI or ML model input according to the configuration information; wherein the configuration information includes at least one of the following: The reporting period for the terminal to report RRM measurement results; second threshold; third threshold; Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following: The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold; The speed of the terminal changes; The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

23. An information processing method, comprising: The network device receives a radio resource management RRM measurement result related to the first artificial intelligence AI or machine learning ML model input sent by the terminal; The network device obtains first information output by a first AI or ML model according to the RRM measurement result; The network device performs handover-related processing according to the first information; The first information includes at least one of the following parameters: RRM prediction results; Predicting cell information of the optimal cell; The first prediction result is related to the occurrence of the predicted event.

24. The information processing method according to claim 23, wherein: The network device performs handover-related processing according to the first information, including at least one of the following: In a case where the first information includes an RRM prediction result, the network device performs handover-related processing according to the RRM prediction result; In a case where the first information includes cell information of a predicted optimal cell, the network device performs handover-related processing according to the cell information of the predicted optimal cell; In a case where the first information includes a first prediction result, the network device performs handover-related processing according to the first prediction result; In a case where the first information includes an RRM prediction result, the network device determines the cell information of the predicted optimal cell and / or the first prediction result according to the RRM prediction result, and performs handover-related processing according to the cell information of the predicted optimal cell and / or the first prediction result; In a case where the first information includes cell information of a predicted optimal cell, the network device determines the first prediction result according to the cell information of the predicted optimal cell, and performs cell handover-related processing according to the first prediction result.

25. The information processing method according to claim 23 or 24, wherein: The first prediction result includes at least one of the following: Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points; The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points; The fourth indication information is used to indicate the cells and / or beams that meet the switching conditions within the first prediction time period.

26. The information processing method according to claim 25, wherein: The network device performs handover-related processing according to the first information, including at least one of the following: In a case where the first prediction result includes second indication information, the network device performs handover-related processing according to the second indication information; In a case where the first prediction result includes third indication information, the network device performs handover-related processing according to the third indication information; In a case where the first prediction result includes fourth indication information, the network device performs handover-related processing according to the fourth indication information; In a case where the first prediction result includes second indication information, the network device determines at least one of the first indication information, the third indication information, and the fourth indication information according to the second indication information, and performs handover-related processing according to at least one of the first indication information, the third indication information, and the fourth indication information; In a case where the first prediction result includes third indication information, the network device determines the first indication information and / or the fourth indication information according to the third indication information, and performs handover-related processing according to the first indication information and / or the fourth indication information; In a case where the first prediction result includes fourth indication information, the network device determines the first indication information according to the fourth indication information, and performs handover-related processing according to the first indication information; Among them, the first indication information is used to indicate the change trend of the RRM prediction result corresponding to the first cell and / or the first beam, and the first cell and / or the first beam meets the switching condition.

27. The information processing method according to claim 23, wherein: Before the network device receives the radio resource management RRM measurement result related to the first artificial intelligence AI or machine learning ML model input sent by the terminal, the method further includes: The network device sends configuration information to the terminal; wherein the configuration information includes at least one of the following: The reporting period for the terminal to report RRM measurement results; second threshold; third threshold; Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following: The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold; The speed of the terminal changes; The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

28. The information processing method according to claim 23, further comprising: The network device monitors the inference performance of the first AI or ML model and determines a performance monitoring result; The network device performs AI or ML model switching and / or deactivates the first AI or ML model based on the performance monitoring result.

29. An information processing device comprising a memory, a transceiver, and a processor; in, The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: Determining radio resource management (RRM) measurements associated with a first artificial intelligence (AI) or machine learning (ML) model input; Obtaining first information output by a first AI or ML model based on the RRM measurement result; Sending second information to the network device according to the first information; The first information and / or the second information includes at least one of the following parameters: RRM prediction results; Predicting cell information of the optimal cell; The first prediction result is related to the occurrence of the predicted event.

30. The information processing apparatus according to claim 29, wherein: The processor is configured to read the computer program in the memory and perform at least one of the following operations: In a case where the first information includes an RRM prediction result, the terminal determines that the second information includes the RRM prediction result; In a case where the first information includes cell information of a predicted optimal cell, the terminal determines that the second information includes the cell information of the predicted optimal cell; In a case where the first information includes a first prediction result, the terminal determines that the second information includes the first prediction result; In a case where the first information includes an RRM prediction result, the terminal determines, according to the RRM prediction result, the cell information of the predicted optimal cell and / or the first prediction result, and determines that the second information includes the cell information of the predicted optimal cell and / or the first prediction result; In a case where the first information includes cell information of a predicted optimal cell, the terminal determines the first prediction result according to the cell information of the predicted optimal cell, and determines that the second information includes the first prediction result.

31. The information processing device according to claim 29, wherein: The first information further includes at least one of the following parameters: A timestamp corresponding to a prediction result output by the first AI or ML model; wherein the prediction result output by the first AI or ML model includes at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result; Cell identification information corresponding to the RRM prediction result; Beam identification information corresponding to the RRM prediction result.

32. The information processing apparatus according to claim 29, wherein: The second information further includes at least one of the following parameters: identification information of the first AI or ML model; identification information of the AI ​​or ML function corresponding to the first AI or ML model; A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result; The sequence number of the prediction result output by the first AI or ML model corresponding to the timestamp; The time interval between the first AI or ML model outputting prediction results; The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

33. The information processing apparatus according to claim 31 or 32, wherein: The timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, a coordinated universal time UTC, a global positioning system time GPST, and a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

34. The information processing apparatus according to any one of claims 29 to 32, wherein: The first prediction result includes at least one of the following: Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points; The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points; The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

35. The information processing apparatus according to claim 33, wherein: The processor is configured to read the computer program in the memory and perform at least one of the following operations: In a case where the first prediction result includes second indication information, the terminal determines that the second information includes the second indication information; In a case where the first prediction result includes third indication information, the terminal determines that the second information includes the third indication information; In a case where the first prediction result includes fourth indication information, the terminal determines that the second information includes the fourth indication information; In a case where the first prediction result includes second indication information, the terminal determines, based on the second indication information, at least one of the first indication information, the third indication information, and the fourth indication information, and determines that the second information includes at least one of the first indication information, the third indication information, and the fourth indication information; In a case where the first prediction result includes third indication information, the terminal determines the first indication information and / or the fourth indication information according to the third indication information, and determines that the second information includes the first indication information and / or the fourth indication information; In a case where the first prediction result includes fourth indication information, the terminal determines the first indication information according to the fourth indication information, and determines that the second information includes the first indication information.

36. The information processing device according to any one of claims 29 to 32, wherein the processor is configured to read the computer program in the memory and perform the following operations: The terminal receives configuration information sent by the network device; The terminal sending second information to the network device includes: The terminal sends the second information to the network device according to the configuration information; The configuration information includes at least one of the following: fifth indication information, used to indicate the parameters in the second information reported by the terminal; Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result; Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition; Configuration information of the first condition.

37. The information processing apparatus according to claim 36, wherein: The first condition includes at least one of the following: At the first prediction time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more prediction time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold; At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell; At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event; The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

38. The information processing device according to claim 36, wherein the processor is configured to read the computer program in the memory and perform the following operations: The terminal sends terminal capability information to the network device; wherein, The terminal capability information includes at least one of the following: Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result; Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell; The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

39. The information processing apparatus according to claim 32, 34 or 38, wherein: The trigger conditions for triggering the reporting of the event include but are not limited to at least one of the following: The AI ​​or ML model outputs a prediction; At the predicted time point, there are cells and / or beams that meet the triggering conditions for measurement reporting; In the predicted time period, there are cells and / or beams that meet the triggering conditions for measurement reporting.

40. The information processing device according to any one of claims 29 to 32, wherein the processor is configured to read the computer program in the memory and perform the following operations: The terminal monitors the inference performance of the first AI or ML model and determines a performance monitoring result; The terminal performs at least one of the following operations based on the performance monitoring result: Sending the performance monitoring result to the network device; Perform AI or ML model switching; Deactivating the first AI or ML model; Sending a first decision result to the network device; wherein, The first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model.

41. A terminal comprising: a measurement unit, configured to determine a radio resource management (RRM) measurement result associated with a first artificial intelligence (AI) or machine learning (ML) model input; a first processing unit, configured to obtain first information output by a first AI or ML model based on the RRM measurement result; A first sending unit, configured to send second information to a network device according to the first information; The first information and / or the second information includes at least one of the following parameters: RRM prediction results; Predicting cell information of the optimal cell; The first prediction result is related to the occurrence of the predicted event.

42. An information processing device comprising a memory, a transceiver, and a processor; in, The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: receiving second information sent by the terminal; performing handover-related processing according to the second information; The second information includes at least one of the following: Radio Resource Management RRM prediction results; Predicting cell information of the optimal cell; The first prediction result is related to the occurrence of the predicted event.

43. The information processing apparatus according to claim 42, wherein: The second information further includes at least one of the following parameters: First, identification information of the artificial intelligence (AI) or machine learning (ML) model; identification information of the AI ​​or ML function corresponding to the first AI or ML model; A timestamp corresponding to one or more prediction results output by the first AI or ML model; wherein the prediction results output by the first AI or ML model include at least one of an RRM prediction result, cell information of a predicted optimal cell, and the first prediction result; the number of prediction results output by the first AI or ML model corresponding to the timestamp; The time interval between the first AI or ML model outputting prediction results; The first indication information is used to indicate the changing trend of the RRM prediction results corresponding to the first cell and / or the first beam; wherein, the first cell and / or the first beam meet the triggering conditions for event triggering reporting.

44. The information processing apparatus according to claim 43, wherein: The timestamp includes at least one of the following: a frame, a subframe, a time slot, a symbol, a coordinated universal time UTC, a global positioning system time GPST, and a time interval between the time when the first AI or ML model outputs the prediction result and the reporting time configured by the network device.

45. The information processing apparatus according to claim 42 or 43, wherein: The first prediction result includes at least one of the following: Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points; The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points; The fourth indication information is used to indicate the cells and / or beams that meet the triggering conditions for event triggering reporting within the first prediction time period.

46. ​​The information processing device according to claim 42 or 43, wherein the processor is configured to read the computer program in the memory and perform the following operations: The network device sends configuration information to the terminal; wherein, The configuration information includes at least one of the following: fifth indication information, used to indicate the parameters in the second information reported by the terminal; Sixth indication information, used to instruct the terminal whether to report the change trend of the RRM prediction result; Seventh indication information, used to indicate whether to allow the terminal to determine whether to report the second information based on the first condition; Configuration information of the first condition.

47. The information processing apparatus according to claim 46, wherein: The first condition includes at least one of the following: At the first prediction time point, the second cell and / or the second beam meets the triggering condition of the event triggered reporting, and at one or more prediction time points within the second prediction time period, the RRM prediction result corresponding to the second cell and / or the second beam is less than or equal to the first threshold; At the first predicted time point, the second cell meets the triggering condition for event triggering reporting, and within the second predicted time period, at least one of handover failure, radio link failure, and ping-pong effect occurs in the second cell; At the first predicted time point, the second cell and / or the second beam meets the triggering condition for event triggering reporting, and at one or more predicted time points within the second predicted time period, the second cell and / or the second beam does not meet the predicted event; The first predicted time point is the start time of the second predicted time period, or the first predicted time point is before the start time of the second predicted time period.

48. The information processing device according to claim 46, wherein the processor is configured to read the computer program in the memory and perform the following operations: The network device receives the terminal capability information sent by the terminal; wherein, The terminal capability information includes at least one of the following: Eighth indication information, used to indicate whether the terminal has the ability to determine the RRM prediction result; Ninth indication information, used to indicate whether the terminal has the ability to determine the predicted optimal cell; The tenth indication information is used to indicate whether the terminal has the ability to determine the first prediction result.

49. The information processing device according to claim 42 or 43, wherein the processor is configured to read the computer program in the memory and perform at least one of the following operations: The network device receives a first decision result sent by the terminal; wherein, The first decision result is used to indicate the switched AI or ML model, and / or the first decision result is used to indicate deactivation of the first AI or ML model; The network device receives a performance monitoring result of the inference performance of the first AI or ML model sent by the terminal, and sends decision indication information to the terminal based on the performance monitoring result; The network device monitors the inference performance of the first AI or ML model, determines a performance monitoring result, and sends decision indication information to the terminal based on the performance monitoring result; The decision indication information is used to indicate the switched AI or ML model and / or to deactivate the first AI or ML model.

50. A network device comprising: A first receiving unit, configured to receive second information sent by a terminal; a first processing unit, configured to perform handover-related processing according to the second information; The second information includes at least one of the following: Radio Resource Management RRM prediction results; Predicting cell information of the optimal cell; The first prediction result is related to the occurrence of the predicted event.

51. An information processing device comprising a memory, a transceiver, and a processor; in, The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: Sending radio resource management (RRM) measurement results associated with the first artificial intelligence (AI) or machine learning (ML) model input to the network device.

52. The information processing apparatus according to claim 51, wherein: The processor is configured to read the computer program in the memory and perform the following operations: The terminal receives the configuration information sent by the network device; The terminal sends, to the network device, an RRM measurement result related to the first AI or ML model input according to the configuration information; wherein the configuration information includes at least one of the following: The reporting period for the terminal to report RRM measurement results; second threshold; third threshold; Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following: The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold; The speed of the terminal changes; The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

53. A terminal comprising: A sending unit is used to send a radio resource management RRM measurement result related to the first artificial intelligence AI or machine learning ML model input to the network device.

54. An information processing device comprising a memory, a transceiver, and a processor; in, The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: Receiving a radio resource management RRM measurement result related to a first artificial intelligence AI or machine learning ML model input sent by a terminal; Obtaining first information output by a first AI or ML model based on the RRM measurement result; performing handover-related processing according to the first information; The first information includes at least one of the following parameters: RRM prediction results; Predicting cell information of the optimal cell; The first prediction result is related to the occurrence of the predicted event.

55. The information processing apparatus according to claim 54, wherein: The processor is configured to read the computer program in the memory and perform at least one of the following operations: In a case where the first information includes an RRM prediction result, the network device performs handover-related processing according to the RRM prediction result; In a case where the first information includes cell information of a predicted optimal cell, the network device performs handover-related processing according to the cell information of the predicted optimal cell; In a case where the first information includes a first prediction result, the network device performs handover-related processing according to the first prediction result; In a case where the first information includes an RRM prediction result, the network device determines the cell information of the predicted optimal cell and / or the first prediction result according to the RRM prediction result, and performs handover-related processing according to the cell information of the predicted optimal cell and / or the first prediction result; In a case where the first information includes cell information of a predicted optimal cell, the network device determines the first prediction result according to the cell information of the predicted optimal cell, and performs cell handover-related processing according to the first prediction result.

56. The information processing apparatus according to claim 54 or 55, wherein: The first prediction result includes at least one of the following: Second indication information, used to indicate whether the cell and / or beam meets the prediction event at one or more prediction time points; The third indication information is used to indicate the cells and / or beams that meet the prediction event at one or more predicted time points; The fourth indication information is used to indicate the cells and / or beams that meet the switching conditions within the first prediction time period.

57. The information processing apparatus according to claim 56, wherein: The processor is configured to read the computer program in the memory and perform at least one of the following operations: In a case where the first prediction result includes second indication information, the network device performs handover-related processing according to the second indication information; In a case where the first prediction result includes third indication information, the network device performs handover-related processing according to the third indication information; In a case where the first prediction result includes fourth indication information, the network device performs handover-related processing according to the fourth indication information; In a case where the first prediction result includes second indication information, the network device determines at least one of the first indication information, the third indication information, and the fourth indication information according to the second indication information, and performs handover-related processing according to at least one of the first indication information, the third indication information, and the fourth indication information; In a case where the first prediction result includes third indication information, the network device determines the first indication information and / or the fourth indication information according to the third indication information, and performs handover-related processing according to the first indication information and / or the fourth indication information; In a case where the first prediction result includes fourth indication information, the network device determines the first indication information according to the fourth indication information, and performs handover-related processing according to the first indication information; Among them, the first indication information is used to indicate the change trend of the RRM prediction result corresponding to the first cell and / or the first beam, and the first cell and / or the first beam meets the switching condition.

58. The information processing apparatus according to claim 54, wherein: The processor is configured to read the computer program in the memory and perform the following operations: The network device sends configuration information to the terminal; wherein the configuration information includes at least one of the following: The reporting period for the terminal to report RRM measurement results; second threshold; third threshold; Trigger conditions for measurement reporting; wherein the trigger conditions include at least one of the following: The time interval that has passed since the terminal last reported the RRM measurement result is greater than or equal to the second threshold; The speed of the terminal changes; The signal quality of the cell where the terminal is camped is less than or equal to the third threshold.

59. The information processing device according to claim 54, wherein the processor is configured to read the computer program in the memory and perform the following operations: The network device monitors the inference performance of the first AI or ML model and determines a performance monitoring result; The network device performs AI or ML model switching and / or deactivates the first AI or ML model based on the performance monitoring result.

60. A network device comprising: A receiving unit, configured to receive a radio resource management (RRM) measurement result related to a first artificial intelligence (AI) or machine learning (ML) model input sent by a terminal; an inference unit, configured to obtain first information output by a first AI or ML model based on the RRM measurement result; a processing unit, configured to perform handover-related processing according to the first information; The first information includes at least one of the following parameters: RRM prediction results; Predicting cell information of the optimal cell; The first prediction result is related to the occurrence of the predicted event.

61. A processor-readable storage medium storing a computer program, wherein the computer program is configured to cause the processor to execute the steps of the information processing method according to any one of claims 1 to 28.

62. A computer program product comprising computer instructions, which, when executed by a processor, implement the steps of the information processing method according to any one of claims 1 to 28.

Images