Communication method, communication device and system

Abstract

The invention provides a communication method, a communication device and a communication system. In the method, a second network device can receive an abnormal event report recorded by a terminal under the condition that an abnormal event occurs, the abnormal event report comprises an AI use indication, the second network device can determine that occurrence of the abnormal event is related to AI information according to the AI use indication, and then the second network device can determine that the occurrence of the abnormal event is related to the AI information according to the abnormal event report and the AI information. According to the method, the abnormal event is analyzed, and the improvement is made in a targeted manner according to the analysis result, so that the network performance is improved.

Description

Technical Field

[0001] This application relates to the field of communications, and more particularly to a communication method, communication device, and system. Background Technology

[0002] In mobile communication systems, such as 5G, the radio access network (RAN) introduces artificial intelligence (AI) mobility use cases. For example, a terminal can send predictive information output by its AI model to the network, which can then make relevant decisions based on this information. However, based on these decisions, the terminal may experience abnormal events, such as radio link failure (RLF), handover failure (HOF), radio resource control (RRC) connection reestablishment rejection (RCEF), random access (RA) failure, and so on.

[0003] However, the network side is currently unable to accurately pinpoint the root cause of this abnormal event, and therefore cannot make targeted improvements, resulting in impaired network performance. Summary of the Invention

[0004] This application provides a communication method, communication device, and system to accurately locate the root cause of abnormal events, and then make targeted improvements to enhance network performance.

[0005] In a first aspect, a communication method is provided, which can be applied to a second network device. For example, it can be executed by the second network device, or by components configured in the second network device (such as a processor, chip, chip system, etc.), or by a logic module or software capable of implementing all or part of the functions of the second network device. This application does not limit this approach.

[0006] The method includes: receiving an abnormal event report, the abnormal event report being a report recorded by the terminal when an abnormal event occurs, the abnormal event report including an AI use indication, the AI ​​use indication being used to indicate that the occurrence of the abnormal event is related to AI information; and analyzing the abnormal event based on the abnormal event report and the AI ​​information.

[0007] Among them, the second network device is the network device that serves the second cell, which is the cell where the terminal is currently located.

[0008] Based on the above scheme, the second network device can receive abnormal event reports from the terminal. These reports record abnormal events occurring on the terminal and include AI usage instructions. Based on these instructions, the second network device can determine that the abnormal event is related to AI information. Therefore, it can analyze the abnormal events occurring on the terminal based on the abnormal event reports and AI information. In this way, the network side (such as the second network device) performs abnormal event analysis based on the reports and AI information, and makes targeted improvements based on the analysis results, thereby improving network performance.

[0009] In conjunction with the first aspect, in some implementations of the first aspect, the abnormal event report also includes the identifier of the cell that received or used the AI ​​information.

[0010] The aforementioned communities that receive or use AI information can also be called communities that store AI information.

[0011] In one possible design, the anomaly report includes an AI use flag that contains instructions on AI use. Optionally, the AI ​​use flag may also include an identifier of the cell receiving or using the AI ​​information.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: obtaining the AI ​​information based on the AI ​​usage instruction.

[0013] When the cell receiving or using AI information is the second cell, the second network device can obtain AI information locally based on the AI ​​usage instruction.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, the cell receiving or using the AI ​​information is a first cell, and obtaining the AI ​​information includes: sending a request message to a first network device, the first network device being a network device serving the first cell, the request message being used to request the AI ​​information; and receiving the AI ​​information from the first network device.

[0015] When the cell receiving or using AI information is the first cell, the second network device can request the AI ​​information from the first network device based on the AI ​​usage instruction.

[0016] Optionally, the request message includes the identifier of the terminal and / or the identifier of the AI ​​model, wherein the AI ​​model is the model that generates the AI ​​information.

[0017] Since the first network device may receive or use AI information from multiple terminals, the request message includes the terminal identifier and / or the AI ​​model identifier, so that the first network device can find the corresponding AI information based on the terminal identifier and / or the AI ​​model identifier.

[0018] In conjunction with the first aspect, in some implementations of the first aspect, before receiving the abnormal event report, the method further includes: receiving a handover request, the handover request being used to request the terminal to be switched to the second cell, the handover request carrying the AI ​​usage indication; and sending a handover request acknowledge, the handover request acknowledge carrying the AI ​​usage indication.

[0019] In one possible design, the aforementioned switch request response may carry an RRC reconfiguration message container, which includes an AI usage instruction.

[0020] Secondly, a communication method is provided, which can be applied to a terminal. For example, it can be executed by the terminal itself, or by components configured in the terminal (such as processors, chips, chip systems, etc.), or by logic modules or software capable of implementing all or part of the functions of the terminal. This application does not limit this aspect.

[0021] The method includes: receiving an AI usage instruction from a fourth network device, the AI ​​usage instruction indicating that AI information sent by the terminal is used by the fourth network device; performing RRC reconstruction in a third cell in the event of an abnormal event occurring in the terminal; and sending the AI ​​usage instruction to a third network device, the third network device being a network device serving the third cell.

[0022] The terminal may experience an abnormal event after switching from the first cell to the second cell, and the fourth network device may be the first network device serving the first cell; the terminal may also experience an abnormal event during the process of switching from the second cell to another cell, such as a handover failure, and the fourth network device may be the second network device serving the second cell. This application does not limit this.

[0023] Based on the above scheme, the terminal can receive an AI usage instruction from the fourth network device. This AI usage instruction is used to indicate that the AI ​​information sent by the terminal is used by the fourth network device. In this case, if an abnormal event occurs in the terminal and it is rebuilt from its current cell to the third cell, the terminal can send the AI ​​usage instruction to the third network device serving the third cell. This makes it easier for the network side to determine that the occurrence of the abnormal event is related to the AI ​​information, and then to perform abnormal event analysis based on the abnormal event report and AI information. Based on the analysis results, targeted improvements can be made to improve network performance.

[0024] In conjunction with the second aspect, in some implementations of the second aspect, receiving the AI ​​usage instruction from the fourth network device includes: receiving a handover command from the fourth network device, the handover command carrying the AI ​​usage instruction.

[0025] In one possible design, the aforementioned switching command may carry an RRC reconfiguration message container, which includes the aforementioned AI usage instruction.

[0026] In conjunction with the second aspect, in some implementations of the second aspect, sending the AI ​​usage instruction to the third network device includes: sending a first message to the third network device, the first message including an anomaly event reporting availability indication and the AI ​​usage instruction, the anomaly event reporting availability indication indicating that an anomaly event report is available, the anomaly event report being a report recorded in the event of an anomaly event occurring on the terminal.

[0027] The above-mentioned abnormal event report availability indication is used to indicate that an abnormal event report is available, or in other words, the abnormal event report availability indication is used to indicate that the terminal has recorded an abnormal event report and that the abnormal event report can be obtained by a third network device.

[0028] In conjunction with the second aspect, in some implementations of the second aspect, sending the AI ​​usage instruction to the third network device includes: sending an abnormal event report to the third network device, the abnormal event report being a report recorded when an abnormal event occurs at the terminal, the abnormal event report including the AI ​​usage instruction.

[0029] In conjunction with the second aspect, in some implementations of the second aspect, the anomaly report includes the identifier of the cell that received or used the AI ​​information.

[0030] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes, before receiving the AI ​​usage instruction from the fourth network device, sending the AI ​​information to the fourth network device.

[0031] When a terminal predicts that an abnormal event is about to occur, it can send the AI ​​information to a fourth network device to assist the fourth network device in making relevant decisions.

[0032] Thirdly, a communication method is provided that can be applied to a fourth network device. For example, it can be executed by the fourth network device itself, or by components configured in the fourth network device (such as processors, chips, chip systems, etc.), or by logic modules or software capable of implementing all or part of the functions of the fourth network device. This application does not limit this approach.

[0033] The method includes: receiving AI information from a terminal; and sending an AI usage instruction to the terminal, the AI ​​usage instruction indicating that the AI ​​information sent by the terminal is used.

[0034] In other words, the fourth network device is a network device that receives or uses AI information.

[0035] Based on the above scheme, the fourth network device can receive AI information from the terminal and send an AI usage instruction to the terminal. This AI usage instruction is used to instruct the fourth network device to use the AI ​​information sent by the terminal. In this way, when an abnormal event occurs at the terminal, the network side can determine that the occurrence of the abnormal event is related to the AI ​​information based on the AI ​​usage instruction. Then, based on the abnormal event report and the AI ​​information, the network can perform abnormal event analysis and make targeted improvements based on the analysis results, thereby improving network performance.

[0036] In conjunction with the third aspect, in some implementations of the third aspect, the aforementioned fourth network device is the first network device, and the step of sending the AI ​​usage instruction to the terminal includes: sending a handover request, the handover request being used to request the terminal to be switched to a second cell, the handover request carrying the AI ​​usage instruction; receiving a handover request response, the handover request response carrying the AI ​​usage instruction; and sending a handover command to the terminal, the handover command carrying the AI ​​usage instruction.

[0037] After the first network device makes a decision to switch the terminal from the first cell to the second cell based on AI information, it can send AI usage instructions to the second network device and the terminal.

[0038] In one possible design, the aforementioned switching command may carry an RRC reconfiguration message container, which includes the aforementioned AI usage instructions.

[0039] In conjunction with the third aspect, in some implementations of the third aspect, sending the AI ​​usage instruction to the terminal includes: sending a switching command to the terminal, wherein the switching command carries the AI ​​usage instruction.

[0040] Unlike the switching command described above that carries an RRC reconfiguration message container, this switching command can directly carry AI usage instructions without needing to do so through an RRC reconfiguration message container. This switching command can be an AI-based switching command.

[0041] In conjunction with the third aspect, in some implementations of the third aspect, the method further includes: receiving a request message, the request message being used to request the AI ​​information; and sending the AI ​​information.

[0042] Fourthly, a communication method is provided, which can be applied to a third network device. For example, it can be executed by the third network device itself, or by components configured in the third network device (such as processors, chips, chip systems, etc.), or by logic modules or software capable of implementing all or part of the functions of the third network device. This application does not limit this aspect.

[0043] The method includes: receiving an AI usage instruction from a terminal, the AI ​​usage instruction being sent in the event of an abnormal event occurring on the terminal, the AI ​​usage instruction being used to indicate that the occurrence of the abnormal event is related to AI information; and sending the AI ​​usage instruction.

[0044] Based on the above scheme, the third network device can receive AI usage instructions from the terminal. These instructions indicate that the abnormal event occurring at the terminal is related to AI information. The third network device can then send these instructions to the network device in the cell where the abnormal event occurred (such as the aforementioned fourth network device). In this way, the network side can determine that the abnormal event is related to AI information based on the AI ​​usage instructions. Furthermore, it can perform abnormal event analysis based on the abnormal event report and AI information, and make targeted improvements based on the analysis results, thereby enhancing network performance.

[0045] In conjunction with the fourth aspect, in some implementations of the fourth aspect, receiving the AI ​​usage instruction from the terminal includes: receiving a first message from the terminal, the first message including an abnormal event report availability indication and the AI ​​usage instruction, the abnormal event report availability indication indicating that a first abnormal event report is available, the first abnormal event report being a report recorded when the abnormal event occurs on the terminal.

[0046] The above-mentioned abnormal event report availability indication is used to indicate that an abnormal event report is available, or in other words, the abnormal event report availability indication is used to indicate that the terminal has recorded an abnormal event report and that the abnormal event report can be obtained by a third network device.

[0047] In conjunction with the fourth aspect, in some implementations of the fourth aspect, receiving the AI ​​usage instruction from the terminal includes: receiving a first abnormal event report from the terminal, the first abnormal event report being a report recorded when the abnormal event occurs on the terminal, the first abnormal event report including the AI ​​usage instruction.

[0048] In one possible design, the terminal can record an AI usage flag in the first abnormal event report, which includes the aforementioned AI usage indication.

[0049] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the first anomaly report also includes the identifier of the cell that received or used the AI ​​information.

[0050] The signage for the residential area has already been detailed in the first part, which can be found in the relevant description there. It will not be repeated here.

[0051] In conjunction with the fourth aspect, in some implementations of the fourth aspect, sending the AI ​​usage instruction includes: sending a second abnormal event report, the second abnormal event report being obtained based on the first abnormal event report, and the second abnormal event report including the AI ​​usage instruction.

[0052] The first abnormal event report is an abnormal event report sent by the terminal to the third network device, and the second abnormal event report is an abnormal event report sent out by the third network device. The second abnormal event report is derived from the first abnormal event report, and the second abnormal event report may be the same as or different from the first abnormal event report; this application does not impose any limitation on this.

[0053] The aforementioned second anomaly report includes AI usage instructions, so that the device receiving the second anomaly report (such as the fourth network device) can infer from the AI ​​usage instructions that the occurrence of the anomaly is related to AI information, thereby obtaining AI information and performing anomaly analysis.

[0054] Fifthly, a communication method is provided, which can be applied to a second network device. For example, it can be executed by the second network device, or by components configured in the second network device (such as a processor, chip, chip system, etc.), or by a logic module or software capable of implementing all or part of the functions of the second network device. This application does not limit this aspect.

[0055] The method includes: receiving an abnormal event report, wherein the abnormal event report is a report recorded when an abnormal event occurs on the terminal, the occurrence of the abnormal event is related to AI information, and the abnormal event report includes the AI ​​information; and performing abnormal event analysis based on the abnormal event report.

[0056] Based on the above scheme, the second network device can receive abnormal event reports from the terminal. These abnormal event reports are used to record abnormal events of the terminal and include AI information. Based on this AI information, the network side (such as the second network device) can infer that the occurrence of the abnormal event is related to the AI ​​information. Then, based on the abnormal event reports including AI information, the abnormal events that occurred on the terminal can be analyzed, and targeted improvements can be made based on the analysis results, thereby improving network performance.

[0057] In conjunction with the fifth aspect, in some implementations of the fifth aspect, before receiving the abnormal event report, the method further includes: receiving a handover request, the handover request being used to request the terminal to be handed over to the second cell, the handover request carrying an AI usage indication, the AI ​​usage indication being used to indicate that the AI ​​information sent by the terminal is used; and sending a handover request response, the handover request response carrying the AI ​​usage indication.

[0058] For a more detailed explanation of the various possible implementations of the fifth aspect, please refer to the relevant explanation of the first aspect, which will not be repeated here.

[0059] Sixthly, a communication method is provided, which can be applied to a terminal, for example, executed by the terminal itself, or executed by components configured in the terminal (such as processors, chips, chip systems, etc.), or implemented by logic modules or software capable of realizing all or part of the functions of the terminal. This application does not limit this aspect.

[0060] The method includes: receiving an AI usage instruction from a fourth network device, the AI ​​usage instruction indicating that AI information sent by the terminal is used by the fourth network device; recording an abnormal event report in the event of an abnormal event occurring at the terminal, the abnormal event report including AI information; and sending the abnormal event report to a third network device, the third network device being a network device serving a third cell, the third cell being the cell where the terminal performs RRC reconstruction.

[0061] Based on the above scheme, the terminal can receive an AI usage instruction from a fourth network device. This instruction indicates that the AI ​​information sent by the terminal is used by the fourth network device. In this case, when an abnormal event occurs in the terminal's current cell and the terminal rebuilds from the current cell to a third cell, the terminal can send the recorded abnormal event report to the third network device serving the third cell. Based on this AI information, the network side can infer that the occurrence of the abnormal event is related to the AI ​​information. Then, it can perform abnormal event analysis based on the abnormal event report including the AI ​​information and make targeted improvements based on the analysis results, thereby improving network performance.

[0062] In conjunction with the sixth aspect, in some implementations of the sixth aspect, receiving the AI ​​usage instruction from the fourth network device includes: receiving a switching command from the fourth network device, the switching command carrying the AI ​​usage instruction.

[0063] In conjunction with the sixth aspect, in some implementations of the sixth aspect, before receiving the AI ​​usage instruction from the fourth network device, the method further includes: sending some or all of the information in the AI ​​information to the fourth network device.

[0064] For a more detailed explanation of the various possible implementations of the sixth aspect, please refer to the relevant explanation of the second aspect, which will not be repeated here.

[0065] In a seventh aspect, a communication method is provided, which can be applied to a fourth network device. For example, it can be executed by the fourth network device, or by a component configured in the fourth network device (such as a processor, chip, chip system, etc.), or by a logic module or software capable of implementing all or part of the functions of the fourth network device. This application does not limit this aspect.

[0066] The method includes: receiving some or all of the AI ​​information from a terminal; and sending an AI usage instruction to the terminal, the AI ​​usage instruction indicating that the AI ​​information sent by the terminal is used.

[0067] Based on the above scheme, the fourth network device can receive some or all of the AI ​​information from the terminal and can send an AI usage instruction to the terminal. This AI usage instruction is used to instruct the fourth network device to use the AI ​​information sent by the terminal. In this way, when an abnormal event occurs at the terminal, the network side can infer that the occurrence of the abnormal event is related to the AI ​​information based on the AI ​​usage instruction. Then, based on the abnormal event report including the AI ​​information, abnormal event analysis can be performed, and targeted improvements can be made based on the analysis results, thereby improving network performance.

[0068] In conjunction with the seventh aspect, in some implementations of the seventh aspect, the aforementioned fourth network device is the first network device, and the step of sending the AI ​​usage instruction to the terminal includes: sending a handover request, the handover request being used to request the terminal to be switched to a second cell, the handover request carrying the AI ​​usage instruction; receiving a handover request response, the handover request response carrying the AI ​​usage instruction; and sending a handover command to the terminal, the handover command carrying the AI ​​usage instruction.

[0069] In conjunction with the seventh aspect, in some implementations of the seventh aspect, sending the AI ​​usage instruction to the terminal includes: sending a switching command to the terminal, wherein the switching command carries the AI ​​usage instruction.

[0070] For a more detailed explanation of the various possible implementations of the seventh aspect, please refer to the relevant explanation of the third aspect, which will not be repeated here.

[0071] Eighthly, a communication method is provided, which can be applied to a third network device, for example, executed by the third network device, or executed by a component configured in the third network device (such as a processor, chip, chip system, etc.), or implemented by a logic module or software capable of implementing all or part of the functions of the third network device. This application does not limit this aspect.

[0072] The method includes: receiving an abnormal event report from a terminal, the abnormal event report being a report recorded when an abnormal event occurs on the terminal, the occurrence of the abnormal event being related to AI information, and the abnormal event report including the AI ​​information; and sending the abnormal event report.

[0073] Based on the above scheme, the third network device can receive abnormal event reports from terminals. These reports are recorded when an abnormal event occurs at the terminal and include AI information. The third network device can then send these reports to the network devices in the cell where the terminal was located at the time of the abnormal event (such as the aforementioned fourth network device). This facilitates the network side in determining whether the occurrence of the abnormal event is related to AI information. Furthermore, based on the abnormal event reports including AI information, abnormal event analysis can be performed, and targeted improvements can be made based on the analysis results, thereby improving network performance.

[0074] In conjunction with aspects one through eight, in some implementations, the AI ​​information includes predicted anomalous events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

[0075] In conjunction with aspects one through eight, in some implementations, the abnormal event is: wireless link failure, handover failure, or random access failure.

[0076] A ninth aspect provides a communication apparatus capable of implementing the communication methods described in the first to eighth aspects and any possible implementations thereof. The apparatus includes one or more corresponding functional units or modules for performing the described methods. The functional units or modules included in the apparatus can be implemented in software and / or hardware.

[0077] In a tenth aspect, a communication apparatus is provided, comprising at least one processor, the at least one processor being configured to execute the communication methods described in the first to eighth aspects and any possible implementation thereof.

[0078] Optionally, the apparatus may further include a memory for storing instructions and data. The memory is coupled to the processor, which, when executing the instructions stored in the memory, can implement the methods described in the foregoing aspects.

[0079] Optionally, the device may further include a communication interface for communicating with other devices. For example, the communication interface may be a transceiver, circuit, bus, module, or other type of communication interface.

[0080] Eleventhly, a chip system is provided, the chip system including at least one processor for supporting the implementation of the functions involved in the first to eighth aspects and any possible implementation of the first to eighth aspects, such as receiving or processing data and / or information involved in the above methods.

[0081] In one possible design, the chip system also includes a memory for storing program instructions and data, which may be located within or outside the processor.

[0082] In one possible design, the chip system further includes an interface circuit and / or a power supply circuit, wherein the interface circuit is used to transmit data and the power supply circuit is used to supply power to the chip system.

[0083] The chip system can consist of chips or include chips and other discrete components.

[0084] In a twelfth aspect, a communication system is provided, which includes one or more of the aforementioned terminal, first network device, second network device or third network device.

[0085] In a thirteenth aspect, a computer-readable storage medium is provided, including a computer program that, when run on a computer, causes the computer to implement the methods of the first to eighth aspects and any possible implementation of the first to eighth aspects.

[0086] In a fourteenth aspect, a computer program product is provided, the computer program product comprising: a computer program (also referred to as code or instructions), which, when run, causes a computer to perform the methods of the first to eighth aspects and any possible implementation thereof.

[0087] It should be understood that aspects nine to fourteen of this application correspond to the technical solutions of aspects one to eight of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be repeated here. Attached Figure Description

[0088] Figure 1 This is a schematic diagram of a communication system provided in an embodiment of this application;

[0089] Figure 2 This is a schematic diagram of the application architecture in the AI ​​scenario provided in the embodiments of this application;

[0090] Figure 3 This is a schematic diagram of the architecture of the CU-DU provided in the embodiments of this application;

[0091] Figure 4 This is a schematic diagram of the open RAN architecture provided in the embodiments of this application;

[0092] Figure 5 This is a schematic flowchart of a communication method provided in an embodiment of this application;

[0093] Figure 6 This is a schematic flowchart illustrating the AI ​​usage instruction sending provided in the embodiments of this application;

[0094] Figure 7 This is a schematic flowchart illustrating yet another communication method provided in an embodiment of this application;

[0095] Figure 8 This is a schematic flowchart illustrating yet another communication method provided in an embodiment of this application;

[0096] Figure 9 This is a schematic block diagram of the communication device provided in the embodiments of this application;

[0097] Figure 10 This is another schematic block diagram of the communication device provided in the embodiments of this application. Detailed Implementation

[0098] The technical solution provided in this application will now be described with reference to the accompanying drawings.

[0099] To facilitate understanding of the embodiments of this application, the following points will be explained first:

[0100] First, in this application, the indication includes explicit indication (also known as direct indication) and implicit indication (also known as indirect indication). Explicit indication information A means including information A; implicit indication information A means indicating information A through the correspondence between information A and information B, and direct indication information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured; or it can refer to indicating information A through information B and preset rules.

[0101] Second, in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates an "or" relationship between the preceding and following related objects, but it does not exclude the possibility of indicating an "and" relationship; the specific meaning can be understood in context. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c; a and b; a and c; b and c; or a and b and c. Here, a, b, and c can be single or multiple.

[0102] Third, the use of prefixes such as "first," "second," and "third" in this application is solely for the purpose of distinguishing different things belonging to the same category and does not constrain the order, size, or quantity of the things. For example, "first network device," "second network device," and "third network device" are simply different network devices, and there is no relationship of size or priority among them. Similarly, "first cell," "second cell," and "third cell" are simply different cells, and there is no relationship of size or priority among them.

[0103] Fourth, in this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to a second network device" can be understood as the destination of the information being the second network device, which may include direct transmission via the air interface or indirect transmission via the air interface by other units or modules. "Receive information from a third network device" can be understood as the source of the information being the third network device, which may include direct reception from the third network device via the air interface or indirect reception from the third network device via the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0104] In other words, sending and receiving can occur between devices, such as between a terminal and a network device; or they can occur within a device, such as between components, modules, chips, software modules, or hardware modules within a device via a bus, wiring, or interface.

[0105] Fifth, in the embodiments of this application, "when," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a time, nor do they require the device to make a judgment action when it is implemented, nor do they mean that there are other limitations.

[0106] Sixth, in this application, the words "example," "exemplarily," "for example," or "such as" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "example," "exemplarily," "for example," or "such as" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "example," "exemplarily," "for example," or "such as" is intended to present the relevant concepts in a specific manner.

[0107] The technical solutions provided in this application can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, sidelink (SL) communication systems, non-terrestrial network (NTN) systems such as drones, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication systems, 5th generation (5G) mobile communication systems, or new radio access technology (NR). Among these, 5G mobile communication systems can include non-standalone (NSA) and / or standalone (SA) networking. The technical solutions provided in this application can also be applied to future communication systems, such as 6th generation (6G) mobile communication systems. This application does not limit these applications.

[0108] Figure 1 This is a schematic diagram of the architecture of a communication system applicable to the communication method provided in this application. Figure 1 A schematic diagram of a possible, non-limiting system architecture is shown. (e.g.) Figure 1 As shown, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (e.g., ...). Figure 1 110a and 110b (collectively referred to as 110) and at least one terminal (such as Figure 1 RAN 100, denoted as RAN 120a-120j, is collectively referred to as RAN 120. RAN 100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 1 (Not shown in the image). Terminal 120 is connected to RAN node 110 wirelessly. RAN node 110 is connected to core network 200 wirelessly or via wired connection. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0109] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems (such as 6G mobile communication systems). RAN 100 can also be an open access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (Wi-Fi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0110] RAN node 110, sometimes also referred to as access network equipment, RAN entity, or access node, is part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative, for example... Figure 1 Network element 120i can be a helicopter or a drone, and it can be configured as a mobile base station. For terminals 120j that access RAN 100 through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes referred to as communication devices, for example... Figure 1 Network elements 110a and 110b can be understood as communication devices with base station functions, while network elements 120a-120j can be understood as communication devices with terminal functions.

[0111] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), an evolved Node B (eNB), a radio network controller (RNC), a Node B (NB) transmission reception point (TRP), a base station controller (BSC), a base transceiver station (BTS), an integrated access and backhaul (IAB), a next-generation NodeB (gNB), a next-generation base station in a 6th generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a wireless fidelity (Wi-Fi) system, etc. A RAN node can also be a macro base station (such as...). Figure 1 110a), micro base stations or indoor stations (such as Figure 1 In CRAN scenarios, RAN nodes can be 110b), relay nodes or donor nodes, or wireless controllers. Optionally, RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, in vehicle-to-everything (V2X) technology, the access network equipment can be a roadside unit (RSU).

[0112] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0113] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an O-RAN system, CU can also be called O-CU (Open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0114] A terminal can also be called a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality (VR), augmented reality (AR), industrial control, autonomous driving, transportation safety, remote medical care, smart grid, smart furniture, smart office, smart wearables, smart transportation, and smart cities. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, smart home devices, etc.

[0115] In the embodiments of this application, the terminal and network device can be hardware devices, or software functions running on dedicated hardware, or software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal and network device.

[0116] Figure 2 A schematic diagram of the application architecture applicable to this application in an AI scenario is shown. For example... Figure 2 As shown, the AI ​​module can be deployed on the network side or the terminal side. RAN nodes can include CUs and DUs; this application does not limit the number of CUs and DUs, for example... Figure 2 The diagram illustrates two CUs and two DUs. One CU can connect to one DU, or one CU can connect to multiple DUs. The interfaces between CUs are Xn interfaces, between CUs and DUs are F1 interfaces, and between DUs and the terminal are air interfaces. This application architecture diagram can be applied to 4G systems, 5G systems, 6G systems, NTN systems, or future mobile communication systems, without limitation.

[0117] Figure 3 A schematic diagram of the CU-DU architecture is shown. Figure 3As shown, the CU can include CU-CP and CU-UP. The CU and DU can be segmented according to the protocol stack. One possible approach is to deploy the RRC and Packet Data Convergence Protocol (PDCP) layers on the CU-CP; deploy the Service Data Adaptation Protocol (SDAP) and PDCP layers on the CU-CP; and deploy the remaining Radio Link Control (RLC), Media Access Control (MAC), and Physical (PHY) layers on the DU. This application does not completely limit the above protocol stack segmentation method; other segmentation methods are also possible.

[0118] Among them, the interface between CU-CP and CU-UP is E1, the interface between CU-CP and DU is F1-C, the interface between CU-CP and the core network is NG, and the interface between CU-UP and DU is F1-U.

[0119] Among them, CU-CP is mainly responsible for control plane functions; PDCP-C is mainly responsible for encryption and decryption of control plane data, integrity protection, and data transmission; SDAP is mainly responsible for processing core network data and mapping traffic to bearers; CU-UP is mainly responsible for user plane functions; and PDCP-U is mainly responsible for data plane encryption and decryption, integrity protection, header compression, sequence number maintenance, and data transmission.

[0120] Figure 4 A schematic diagram of the open RAN architecture is shown. (For example...) Figure 4 As shown, this open RAN architecture can include terminals and O-RAN. O-RAN includes a non-real-time radio intelligent controller (Non-RT RIC), a near-real-time radio intelligent controller (Near-RT RIC), and O-RAN nodes. O-RAN nodes can include CUs (CU-CP and CU-UP), DUs, and RUs, etc.

[0121] Near real-time RICs can be used for model training and inference. For example, a near real-time RIC can obtain network-side and / or terminal-side information from O-RAN nodes (such as CU-CP, CU-UP, DU, or RU), which can be used as training data or inference data. A near real-time RIC can deliver inference results to O-RAN nodes and / or terminals; for example, a near real-time RIC can deliver inference results to a DU, which then forwards them to an RU.

[0122] Non-real-time RICs can be used for model training and inference. For example, a non-real-time RIC can obtain network-side and / or terminal-side information from O-RAN nodes (e.g., CU, CU-CP, CU-UP, DU, or RU), which can be used as training data or inference data. A non-real-time RIC can deliver inference results to RAN nodes and / or terminals; for example, a non-real-time RIC can deliver inference results to a DU, which then forwards them to an RU.

[0123] To better understand the methods provided in the embodiments of this application, the terms involved in this application will be briefly explained below.

[0124] 1. RAN AI

[0125] AI, a technology proposed in the 1950s, is a method of performing complex calculations by simulating the human brain. With advancements in data storage and computing power, AI has found increasing applications. 3GPP, through working groups such as RAN3 and RAN1, has designed several basic application scenarios for AI on the RAN side.

[0126] For example, in a mobility optimization scenario, the network side collects historical mobility path information of the terminal and combines it with the terminal's measurement information to predict the terminal's future mobility path. Based on the predicted mobility path, the network side can determine in advance whether the terminal needs to hand over, and send handover configuration in advance and notify the target cell to prepare access resources, thereby reducing the latency of the terminal during the handover process and lowering the probability of handover or access failure.

[0127] 2. AI mobility

[0128] In existing L3 (RRC layer) handover mechanisms, handover is triggered and executed based on reported historical measurement results and / or measurement events, making it inherently a passive approach. This may work well between macrocells when terminal mobility is low. However, for existing or future services (e.g., XR), problems may arise when terminal mobility is high or between high-density microcells. Furthermore, this passive approach can lead to more unforeseen events such as handover failures, radio link failures, ping-pong phenomena, throughput loss, premature or late handovers, etc. To improve handover robustness, conditional handover was introduced in release 16 (R16). To reduce downtime from frequent handovers between small cells, lower-layer triggered mobility (LTM) handover (HO) was introduced in release 18 (R18). However, these two mechanisms are insufficient as they remain passive designs. Mechanisms based on AI or machine learning (ML) algorithms have the potential to achieve proactive solutions.

[0129] In Release 18 (R18), research on RAN1 AI use cases includes spatial and temporal beam prediction. Temporal prediction within the serving cell primarily involves predicting the optimal or top-K beams or beam pairs in the temporal domain to improve user throughput. Predicting the optimal or top-K beams or beam pairs within a set of beams by measuring a smaller set of beams helps reduce remote station (RS) signaling overhead, measurement workload, and terminal power consumption. Much of the work in RAN1 can be reused, such as in LTM HO studies, by extending L1 beam measurements from the serving cell to neighboring cells. Since L3 measurements are based on filtering of L1 (physical layer) measurements, research on AI or ML for the air interface can be applied to mobility; for example, temporal prediction can also be used to predict beam or cell variation, thereby avoiding unintended events (e.g., radio link failures or brief handovers).

[0130] In RAN3, research and normative work on mobility enhancement are based on network-side information, such as inter-cell handovers and historical dwell times, to predict terminal trajectories in a single hop, thereby predicting potential candidates. In Release 19 (R19), RAN3 will further investigate multi-hop trajectories of terminals, and the predicted terminal trajectories can, to some extent, help in the study of AI / ML mobility over the air interface.

[0131] Currently, based on the progress made in RAN1 and RAN3 and assumptions about terminal trajectories, it is feasible to predict radio resource management (RRM) measurements and / or events, as well as candidate target cells, on the terminal side. On the network side, statistical information based on measurement reports from terminals and / or neighboring nodes can also be used for intelligent prediction, if needed. If the network has access to some predictive information, proactive measures can be taken to improve handover and / or RRM performance, enabling better decision-making or avoiding unforeseen events.

[0132] R19 can introduce the topic of AI mobility, which will focus on enhancing air mobility in RRC-connected mode by following the existing mobility framework, meaning that handover decisions are always made on the network side. Mobility use cases will primarily focus on independent NR primary cell (PCell) changes. For network-triggered L3 handovers, both terminal-side and network (NW) AI or ML models can assist in mobility research. Research content related to AI or ML-assisted mobility may include:

[0133] AI or ML-based RRM measurement and event prediction;

[0134] Cell-level measurement prediction, including intra-frequency and inter-frequency, inter-cell beam-level measurement prediction for L3 mobility (terminal-side and network-side models), such as reference signal receiving power (RSRP), received signal strength indicator (RSSI), reference signal receiving quality (RSRQ), and signal to interference plus noise ratio (SINR);

[0135] Abnormal event prediction (terminal-side model);

[0136] Predicting measurement events (terminal-side model);

[0137] The need / benefits of researching any other terminal-aided information in the network-side model;

[0138] The evaluation of AI / ML-assisted mobility benefits should consider key performance indicators (KPIs) of HO performance (e.g., ping-pong HO, HOF / RLF, dwell time, handover interruption, prediction accuracy, and measurement reduction) and complexity trade-offs.

[0139] Potential AI mobility-specific enhancements should be based on the general framework of R19 RAN1 AI (e.g., product lifecycle management (LCM), performance monitoring, etc.);

[0140] Assess testability, interoperability, and the impact on RRM requirements and performance.

[0141] 3. Self-organizing network (SON) report

[0142] The primary goal of SON is to introduce intelligence and adaptation into networks, reducing capital and operating expenditures and improving network performance in areas such as capacity, coverage, spectrum efficiency, and the services / experience provided. It is categorized according to the phases of the network lifecycle (planning, deployment, maintenance, and optimization):

[0143] Self-configuration: Enables automatic connection and automatic initial parameter configuration, such as physical cell identifier (PCI) self-configuration and automatic neighbor relations (ANR) functions;

[0144] Self-healing: By monitoring and analyzing error data and alarm information, the network autonomously detects faults and isolates and recovers them in a timely manner;

[0145] Self-optimization: Enables the self-adjustment and optimization of network parameters, such as transmit power, handover threshold, and cell-specific offset.

[0146] 3GPP defines a series of intelligent SON application scenarios, such as load balancing, mobility optimization, random access channel (RACH) optimization, coverage and capacity optimization, etc. The basic implementation logic is that the network side sends configuration information to the terminal, the terminal records the information in the SON report based on the configuration, and sends it to the network side. The network side analyzes problems based on the SON report, automatically tunes and optimizes the network. SON reports include: RLF report, HOF report, RCEF report, successful handover report (SHR), RA report, terminal (such as user equipment (UE)) historical information (UHI) report, or mobility history report (MHR), etc. Among these, mobility optimization aims to detect and correct the following problems:

[0147] 1) Intra-system or inter-system mobility issues cause connection failures. Problem detection is based on RLF and RCEF reports, and scenarios can include: Handover too late (intra-system and inter-system): The handover command is sent too late, and the terminal rebuilds in another cell; Handover too early (intra-system and inter-system): The handover command is sent too early, and the terminal cannot access the target cell or fails shortly after a successful handover, causing the terminal to rebuild in the source cell; Handover to the wrong cell: The terminal cannot access the target cell or fails shortly after a successful handover, causing the terminal to rebuild in a new cell.

[0148] 2) Unnecessary inter-system handovers. Inter-system handovers from NR to the evolved-universal mobile telecommunications system (E-UTRAN) occur too early. Without radio link failures, unnecessary handover reports are sent from the LTE system to the NR system via the S1 or N2 interface.

[0149] 3) Inter-system handover ping-pong. When a terminal switches from a source system (e.g., a 5G system, 5GS) to a different system (e.g., an evolved packet system, EPS), it switches back to the source system within a limited time, provided the source system is sufficient to provide services to the terminal. This event occurs multiple times. Ping-pong situations are assessed based on the UHI (Unified Information Hierarchy) in the handover requirement (HO), and potential ping-pong situations are transmitted through a handover report (HO report).

[0150] In mobile communication systems, such as 5G, the RAN (Radio Route) introduces AI mobility use cases. Terminals can send predictions from their AI models to the network, allowing the network to make relevant decisions. However, based on these decisions, terminals may experience abnormal events. Terminals can generate SON (Service Message) reports and send them to the network, which can then analyze the cause of the abnormal event. However, currently, the network cannot analyze the SON report to determine whether the abnormal event is related to the terminal's AI usage, such as whether it's related to inaccurate AI predictions. Therefore, it's impossible to accurately pinpoint the root cause of the abnormal event and make targeted improvements.

[0151] In view of this, this application proposes a communication method in which a terminal can send an AI usage instruction to the network side. This AI usage instruction indicates that the occurrence of an abnormal event of the terminal is related to AI information. In this way, the network side can obtain AI information based on the AI ​​usage instruction, perform abnormal event analysis based on the AI ​​information and abnormal event reports, and make targeted improvements based on the analysis results, thereby improving network performance.

[0152] The method provided in this application will now be described in detail with reference to the accompanying drawings. It should be understood that the technical solution of this application can be applied to, for example... Figure 1 The communication system shown.

[0153] In the embodiments illustrated in the following figures, the various processes are described using the interaction between a terminal and a network device, and between network devices, as examples. However, this should not constitute any limitation on the subject of this application. For example, the terminal can also be replaced by components configured in the terminal, such as chips, chip systems, or other modules that can be used to implement some or all of the terminal's functions; the network device can also be replaced by components configured in the network device, such as chips, chip systems, or other modules that can be used to implement some or all of the network device's functions.

[0154] The method provided in this application will now be described in detail with reference to the accompanying drawings.

[0155] Figure 5 A communication method 500 provided in an embodiment of this application is illustrated. The method 500 includes steps 510 to 5100. The various steps in method 500 are described in detail below.

[0156] In step 510, the terminal sends AI information to the fourth network device. Correspondingly, the fourth network device receives the AI ​​information from the terminal.

[0157] The aforementioned AI information may include AI prediction information, AI decisions, and information about the AI ​​model, which is the model that generates the AI ​​information. In this embodiment, the AI ​​model can refer to a terminal-side AI model, which can be deployed inside the terminal or outside the terminal, such as an AI model deployed on a host or cloud server in an over-the-top (OTT) system.

[0158] The AI ​​prediction information mentioned above may include predicted anomalous events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information from the AI ​​model.

[0159] The predicted measurement information may include the future time corresponding to the predicted measurement information, the measurement object, and the predicted measurement result. The predicted measurement result may include the recommended (or predicted) candidate cell identifier, the predicted synchronization signal block (SSB) identifier, RSRP, RSRQ, RSSI, or SINR.

[0160] The measurement objects include one or more of the following: the cell where the terminal is located, the neighboring cells of the cell where the terminal is located, or other cells.

[0161] The candidate cells recommended above can be the best cells predicted by the terminal, or cells recommended in order of priority from the cell list.

[0162] The information for the aforementioned AI model may include: an AI model identifier, an AI business identifier, or an AI function identifier. The AI ​​model identifier indicates the AI ​​model, the AI ​​business identifier indicates the AI ​​business, and the AI ​​function identifier indicates the AI ​​function.

[0163] The aforementioned fourth network device is a network device used to manage the cell where the terminal is located, or in other words, a network device that serves the cell where the terminal is located.

[0164] The first possible scenario is that the terminal is in the first cell, and the fourth network device can be a network device serving the first cell; for ease of distinction and explanation, it will be referred to as the first network device. In this case, the fourth network device and the second network device in the diagram are different network devices. The terminal uses an AI model to predict that an abnormal event will occur to it in the first cell, and can send AI prediction information (i.e., an example of AI information) to the first network device. The first network device can make a decision based on this AI prediction information, which may include reallocating radio resources to the terminal or switching the terminal to another cell in advance.

[0165] For example, the first network device can switch a terminal from a first cell to a second cell based on the AI ​​prediction information. Furthermore, the first network device can also store the AI ​​prediction information locally.

[0166] The second possible scenario is that the terminal is in the second cell, and the fourth network device can be a network device serving the second cell; for ease of distinction and explanation, it will be referred to as the second network device. In this case, the fourth network device and the second network device in the diagram are the same network device. The terminal uses an AI model to predict that an abnormal event will occur in the second cell and can send AI prediction information to the second network device. The second network device can then make a decision based on this AI prediction information, which may include reallocating radio resources to the terminal or switching the terminal to another cell in advance.

[0167] For example, the second network device can switch the terminal from the second cell to another cell, such as the first cell, based on the AI ​​prediction information, without limitation. Furthermore, the second network device can also store the AI ​​prediction information locally.

[0168] In addition to the two possible scenarios listed above, the terminal may also use AI models to make predictions and output AI decisions. In this case, the AI ​​information mentioned above can be considered an AI decision. For the sake of brevity, other possible information included in AI information will not be discussed further here.

[0169] In step 520, the fourth network device sends an AI usage instruction to the terminal, which indicates that the AI ​​information sent by the terminal is being used by the fourth network device. Correspondingly, the terminal receives the AI ​​usage instruction from the fourth network device.

[0170] The aforementioned AI usage instruction is used to instruct the AI ​​information sent by the terminal to be used by a fourth network device. For example, the AI ​​information includes AI prediction information, and the aforementioned AI usage instruction is used to instruct the AI ​​prediction information sent by the terminal to be used by a fourth network device; in other words, the AI ​​usage instruction can be used to instruct the decision made by the fourth network device to be determined based on the AI ​​prediction information.

[0171] Taking the two possible scenarios above as examples again. In the first possible scenario, the fourth network device can be the first network device serving the first cell. The first network device sends an AI usage instruction to the terminal. This AI usage instruction is used to instruct the first network device to use the AI ​​information sent by the terminal. In other words, the AI ​​usage instruction is used to instruct the first network device to make a decision to switch the terminal from the first cell to the second cell based on the AI ​​information sent by the terminal.

[0172] One possible way for the first network device to send the AI ​​usage instruction to the terminal is as follows: the first network device sends a handover request to the second network device, which carries the AI ​​usage instruction; the second network device sends a handover request response to the first network device, which carries an RRC reconfiguration message container, including the AI ​​usage instruction; the first network device then sends a handover command to the terminal, which carries the RRC reconfiguration message container. Since the first network device directly forwards the RRC reconfiguration message container from the second network device to the terminal without modifying it, the RRC reconfiguration message container received by the terminal includes the AI ​​usage instruction. Thus, the terminal receives the AI ​​usage instruction.

[0173] It should be understood that the above example of the first network device sending an AI usage instruction to the terminal, combining the handover request, handover request response, and handover command, is merely an example. For example, the handover request can be replaced by a context establishment request, the handover request response can be replaced by a context request response, and the handover command can be replaced by a context establishment command; there are no limitations.

[0174] Another possible way for the first network device to send AI usage instructions to the terminal is by sending an AI-based handover command to the terminal, which carries the AI ​​usage instructions.

[0175] The switching commands mentioned in the two methods of sending AI usage instructions described above are different. In the first method, the switching command is obtained by carrying an RRC reconfiguration message container from the second network device within it; the first network device does not modify the information in this RRC reconfiguration message container. In the second method, the switching command is generated by the first network device adding the AI ​​usage instruction to it. This switching command can be understood as a newly defined switching command, for example, it could be called an AI-based switching command.

[0176] In the second possible scenario described above, the fourth network device may be a second network device serving the second cell. The second network device sends an AI usage instruction to the terminal. This AI usage instruction is used to instruct the second network device to use the AI ​​information sent by the terminal. In other words, the decision of the second network device to switch the terminal from the second cell to another cell is determined based on the AI ​​information sent by the terminal.

[0177] It should be understood that the second network device sends AI usage instructions to the terminal in a similar manner to the first network device, and will not be described again here.

[0178] In step 530, the terminal performs RRC reconstruction in the third cell in the event of an abnormal event.

[0179] The terminal may experience an abnormal event in the second cell after handing over from the first cell, such as RLF or RA failure; it may also experience an abnormal event during the handover from the second cell to another cell, or in other words, an abnormal event may occur before the terminal hands over to another cell, such as HOF.

[0180] In the event of an abnormal event, the terminal can perform RRC reconstruction in another cell. For ease of distinction and explanation, this embodiment assumes that the terminal performs RRC reconstruction in a third cell. The process of the terminal performing RRC reconstruction in a third cell can be found in existing technologies and will not be described in detail here.

[0181] In step 540, the terminal sends an AI usage instruction to the third network device. Correspondingly, the third network device receives the AI ​​usage instruction from the terminal.

[0182] The aforementioned third network device serves the third cell. After the third cell completes RRC reconstruction, the terminal can send the AI ​​usage instruction to the third network device. This AI usage instruction can be used to indicate that the AI ​​information sent by the terminal is being used. Since an abnormal event occurs on the terminal after the AI ​​information is used, in other words, the occurrence of the abnormal event is related to the AI ​​information. Therefore, it can also be said that the AI ​​usage instruction can be used to indicate that the occurrence of the terminal's abnormal event is related to the AI ​​information.

[0183] Optionally, the method further includes step 550, whereby the terminal sends a first abnormal event report to the third network device. Correspondingly, the third network device receives the first abnormal event report from the terminal.

[0184] The terminal can record the abnormal event and obtain a first abnormal event report in the event of an abnormal event. The terminal can send the first abnormal event report to the third network device after the third cell completes RRC reconstruction.

[0185] The specific implementation methods of steps 540 and 550 will be discussed in the following text. Figure 6 The following will be used to illustrate (a) and (b) in the text, but will not be elaborated on here.

[0186] In step 560, the third network device sends a second abnormal event report to the second network device. Correspondingly, the second network device receives the second abnormal event report from the third network device.

[0187] The third network device can send a second abnormal event report to the second network device based on the received first abnormal event report, so that the second network device can analyze the abnormal event.

[0188] The second abnormal event report may be the same as or different from the first abnormal event report, and this application does not limit this.

[0189] In this embodiment, the second abnormal event report may include an AI usage instruction, so that the second network device can obtain AI information based on the AI ​​usage instruction and then perform abnormal event analysis.

[0190] In step 570, the second network device analyzes the abnormal event based on the second abnormal event report and AI information.

[0191] The aforementioned second network device can analyze abnormal events occurring at the terminal based on the second abnormal event report and AI information, and can obtain abnormal event analysis results. These abnormal event analysis results may include one or more of the following: the type of abnormal event that occurred, the time when the abnormal event occurred, and AI information or AI model information.

[0192] Optionally, the method further includes step 580, in which the second network device sends the anomaly analysis results to the fourth network device. Correspondingly, the fourth network device receives the anomaly analysis results from the second network device.

[0193] As described in step 510, the fourth network device can be either the first network device serving the first cell or the second network device serving the second cell. It is understood that when the fourth network device and the second network device are the same device, step 580 can be omitted.

[0194] Optionally, the method further includes step 590, whereby the fourth network device adjusts parameters based on the abnormal event analysis results.

[0195] As described in step 510, the fourth network device can be either the first network device serving the first cell or the second network device serving the second cell, without limitation.

[0196] For example, the fourth network device can increase the credibility threshold of AI information sent by the terminal (i.e., an example of parameter adjustment). For instance, if the fourth network device originally instructed the terminal to send AI information with a credibility greater than 90%, the fourth network device can now instruct the terminal to send AI information with a credibility greater than 95%.

[0197] For example, the fourth network device can reduce the use of AI information sent by the terminal in subsequent decisions, that is, reduce the weight of AI information sent by the terminal (i.e., another example of parameter adjustment).

[0198] For example, the fourth network device can instruct the terminal to adjust some or all of the parameters of the AI ​​model (i.e., an example of parameter adjustment). The fourth network device can instruct the terminal to update the AI ​​model, or the fourth network device can update the AI ​​model on the terminal side, or the fourth network device can re-deploy the AI ​​model to the terminal side (i.e., re-deploy the parameters of the AI ​​model), or the fourth network device can disable the AI ​​model on the terminal side.

[0199] For example, when the abnormal event that occurs at the terminal is HOF, the fourth network device can modify the legacy handover parameters (such as the handover threshold).

[0200] Optionally, prior to step 570, the method further includes step 5100, whereby the second network device obtains AI information based on AI usage instructions.

[0201] The aforementioned second network device can determine that the occurrence of an abnormal event of the terminal is related to AI information based on the AI ​​usage instructions included in the second abnormal event report, and then obtain AI information based on the AI ​​usage instructions.

[0202] As described in step 510, the terminal sends the AI ​​information to the fourth network device. This AI information is used by the fourth network device, which may be the first network device serving the first cell or the second network device serving the second cell. Therefore, the second network device may obtain the AI ​​information from the first network device or from its local storage.

[0203] The following provides several possible implementations of how a second network device obtains AI information from a first network device.

[0204] In one possible implementation, the second network device sends a request message to the first network device, requesting the first network device to send AI information to the second network device. In response to the request message, the first network device sends the AI ​​information to the second network device.

[0205] In another possible implementation, the third network device sends a request message to the first network device, requesting the first network device to send AI information to the second network device. In response to this request message, the first network device sends the AI ​​information to the second network device.

[0206] In another possible implementation, the third network device sends a request message to the first network device, requesting the first network device to send AI information to the third network device. In response to this request message, the first network device sends the AI ​​information to the third network device. The third network device then sends the AI ​​information from the first network device to the second network device.

[0207] Optionally, the request message may include a terminal identifier and / or an AI model identifier. For example, when there are one or more terminals within the service range of the first network device, the terminal identifier and / or the AI ​​model identifier may be used by the first network device to index AI information.

[0208] Accordingly, the first network device can send the terminal identifier and / or the identifier of the AI ​​model while sending AI information.

[0209] As another possible implementation, the first network device can send AI usage instructions and AI information to the second network device. Since the AI ​​information is sent to the second network device along with the AI ​​usage instructions when the first network device sends the AI ​​usage instructions, there is no need for the second network device or the third network device to request the first network device to send the AI ​​information.

[0210] Taking the second possible scenario in step 510 as an example, when the second cell receives or uses AI information, the second network device can obtain the AI ​​information by obtaining the AI ​​information locally according to the AI ​​usage instructions.

[0211] Based on the above scheme, the terminal can send AI information to a fourth network device, enabling the fourth network device to make decisions based on this AI information. When the fourth network device makes a decision based on the AI ​​information, it can send an AI usage instruction to the terminal, indicating the use of that AI information. In the event of an anomaly, the terminal can send this AI usage instruction to a third network device, allowing the network side to determine whether the anomaly is related to the AI ​​information. Based on the anomaly report and the AI ​​information, the network can then analyze the anomaly and make targeted improvements to enhance network performance.

[0212] Figure 6 (a) and (b) show two possible implementations of steps 540 and 550 in method 500. Figure 6 The specific implementation shown in (a) includes steps 5401a, 5402a and 550a. Figure 6 The specific implementation shown in (b) includes steps 5401b, 5402b and 550b.

[0213] Figure 6 The specific steps in (a) are as follows:

[0214] In step 5401a, the terminal sends a first abnormal event report availability indication to the third network device, the first abnormal event report availability indication indicating that a first abnormal event report is available. Correspondingly, the third network device receives the first abnormal event report availability indication from the terminal.

[0215] The aforementioned first abnormal event report availability indication is used to indicate that the first abnormal event report is available, or in other words, the first abnormal event report availability indication can be used to indicate that the terminal has recorded the first abnormal event report, and that the first abnormal event report can be obtained by the third network device.

[0216] In step 5402a, the third network device sends a request message to the terminal, which requests a first abnormal event report. Correspondingly, the terminal receives the request message from the third network device.

[0217] In step 550a, the terminal sends a first abnormal event report to the third network device. This first abnormal event report is a report recorded when an abnormal event occurs on the terminal. The first abnormal event report is related to AI information and includes AI usage instructions. Correspondingly, the third network device receives the first abnormal event report from the terminal.

[0218] In one possible design, the terminal can record an AI usage flag in the first abnormal event report, which includes the aforementioned AI usage indication.

[0219] Optionally, the aforementioned first anomaly report may also include the identifier of the cell that received or used the AI ​​information. In one possible design, the identifier of the cell that received or used the AI ​​information may also be included in the AI ​​usage flag.

[0220] As described above, the first anomaly report may also include the identifier of the cell that received or used the AI ​​information. Correspondingly, the second anomaly report in step 560 also includes the identifier of the cell that received or used the AI ​​information.

[0221] Figure 6 The specific steps in (b) are as follows:

[0222] In step 5401b, the terminal sends a first message to the third network device, the first message including a first abnormal event report availability indication and an AI usage indication. Correspondingly, the third network device receives the first message from the terminal.

[0223] The available instructions for reporting the first abnormal event have been detailed in step 5401a above, and can be found in the relevant description of 5401a. They will not be repeated here.

[0224] In step 5402b, the third network device sends a request message to the terminal, which requests a first abnormal event report. Correspondingly, the terminal receives the request message from the third network device.

[0225] In step 550b, the terminal sends a first abnormal event report to the third network device. This first abnormal event report is a report recorded when an abnormal event occurs on the terminal, and it is related to AI information. Correspondingly, the third network device receives the first abnormal event report from the terminal.

[0226] The identification of the cell that received or used AI information in the first abnormal event report has been described in detail in step 550a above. Please refer to the relevant description in 550a. It will not be repeated here.

[0227] The above text combined Figure 6 (a) and (b) illustrate two possible implementations of a terminal sending an AI usage instruction to a third network device, but this should not be construed as limiting the scope of this application. For example, the terminal may also send the AI ​​usage instruction to the third network device via additional signaling.

[0228] Figure 7 A schematic flowchart of a communication method 700 provided in another embodiment of this application is shown. Figure 7 The communication method 700 shown is based on Figure 5 and Figure 6 The illustrated process is based on the implementation flow of network devices deployed with a distributed architecture. The following description focuses on steps that differ from those in methods 500 and 600. Explanations of steps identical to those in methods 500 and 600, as well as the same terminology, can be found in the relevant descriptions of methods 500 and 600 above, and will not be repeated here. Furthermore, for clarity, information carried in signaling is enclosed in parentheses in the diagram.

[0229] Figure 7 The method 700 shown includes steps 701 to 717. The individual steps in method 700 are described in detail below.

[0230] In step 701, the terminal predicts, based on an AI model, that an abnormal event (e.g., an RLF event) is about to occur in the first cell.

[0231] In step 702, the terminal sends AI information to the CU of the first network device via the RU and DU of the first network device. Correspondingly, the CU of the first network device receives the AI ​​information from the terminal.

[0232] In step 703, the first network device generates a decision based on AI information, which includes switching the terminal to the second cell.

[0233] In step 704, the CU of the first network device sends a handover request to the CU of the second network device. This handover request requests the terminal to be handed over to the second cell. The handover request carries an AI usage indication, which indicates that the AI ​​information sent by the terminal is being used by the first network device. Correspondingly, the CU of the second network device receives the handover request from the CU of the first network device.

[0234] In step 705, the CU of the second network device sends a handover request response to the CU of the first network device. This handover request response carries an RRC reconfiguration message container, which includes an AI usage indication. Correspondingly, the CU of the first network device receives the handover request response from the CU of the second network device.

[0235] In step 706, the CU of the first network device sends a handover command to the terminal via the DU and RU of the first network device. This handover command is used to hand over the terminal from the first cell to the second cell. The handover command may carry an RRC reconfiguration message container, which includes an AI usage instruction. Correspondingly, the terminal receives the handover command from the CU of the first network device.

[0236] Steps 704 to 706 above are one possible implementation of step 520 in method 500. There may be other possible implementations, which will not be elaborated here.

[0237] In step 707, an abnormal event (e.g., a short-term RLF event) occurred in the second cell, and the terminal rebuilt to the third cell.

[0238] In step 708, the terminal records a first abnormal event report (e.g., a first RLF report), which includes an AI usage instruction.

[0239] In one possible design, the first RLF report includes an AI usage flag, which includes an AI usage instruction.

[0240] Optionally, the first RLF report includes an identifier of the cell that receives or uses AI information. In one possible design, the identifier of the cell that receives or uses AI information may also be included in the aforementioned AI usage flag.

[0241] In step 709, the terminal sends a first RLF report availability indication to the CU of the third network device via the RU and DU of the third network device. This first RLF report availability indication is used to indicate that a first RLF report is available. Correspondingly, the CU of the third network device receives the first RLF report availability indication from the terminal.

[0242] In step 710, the CU of the third network device sends a request message to the terminal via the DU and RU of the third network device. This request message is used to request the terminal's first RLF report. Correspondingly, the terminal receives the request message from the CU of the third network device.

[0243] In step 711, the terminal sends a first RLF report to the CU of the third network device via the RU and DU of the third network device. Correspondingly, the CU of the third network device receives the first RLF report from the terminal.

[0244] In step 712, the CU of the third network device sends a second abnormal event report (e.g., a second RLF report) to the CU of the second network device. Correspondingly, the CU of the second network device receives the second RLF report from the CU of the third network device.

[0245] The second RLF report may be the same as or different from the first RLF report mentioned above, and this application does not limit this.

[0246] In this embodiment, the second RLF report may include an AI usage indication, enabling the second network device to obtain AI information based on the AI ​​usage indication and then perform anomaly analysis. As mentioned earlier, the first RLF report may include the identifier of the cell receiving or using AI information. Correspondingly, the second RLF report may include the identifier of the cell receiving or using AI information.

[0247] In step 713, the CU of the second network device sends a request message to the CU of the first network device, which requests AI information. Correspondingly, the CU of the first network device receives the request message from the CU of the second network device.

[0248] In step 714, the CU of the first network device sends AI information to the CU of the second network device. Correspondingly, the CU of the second network device receives the AI ​​information from the CU of the first network device.

[0249] In step 715, the CU of the second network device analyzes the RLF event based on the second RLF report and AI information.

[0250] In step 716, the CU of the second network device sends the RLF event analysis result to the CU of the first network device. Correspondingly, the CU of the first network device receives the RLF event analysis result from the CU of the second network device.

[0251] In step 717, the CU of the first network device adjusts its parameters based on the RLF event analysis results.

[0252] Based on the above scheme, the terminal can send AI information to the first network device serving the first cell. The first network device can then make a handover decision to switch the terminal from the first cell to the second cell based on this AI information. It can also send an AI usage instruction to the terminal, indicating that the handover decision is related to the AI ​​information. If an abnormal event (such as an RLF event) occurs after the terminal switches from the first cell to the second cell and reconnects to the third cell, the terminal first sends a first abnormal event report (such as a first RLF report) including the AI ​​usage instruction to the third network device. The third network device then sends a second abnormal event report (such as a second RLF report) including the AI ​​usage instruction to the second network device serving the second cell. Furthermore, the second network device can analyze the abnormal event based on the second abnormal event report and the AI ​​information, and send the analysis results to the first network device so that the first network device can make targeted improvements (such as parameter adjustments) based on the analysis results, thereby improving network performance.

[0253] Figure 8 This application illustrates yet another communication method 800 provided in an embodiment of the present application. The method 800 includes steps 810 to 8100. The various steps of method 800 are described in detail below.

[0254] In step 810, the terminal sends the first AI information to the fourth network device. Correspondingly, the fourth network device receives the first AI information from the terminal.

[0255] In this embodiment, for ease of distinction and explanation, the AI ​​information sent by the terminal to the fourth network device is denoted as the first AI information, and the AI ​​information output by the terminal-side AI model is denoted as the second AI information. The first AI information may be part or all of the information in the second AI information. In other words, the first AI information may be the same as the second AI information, or it may be a subset of the second AI information, or the second AI information may include the first AI information. The fourth network device and the AI ​​information (i.e., the second AI information in this embodiment) have been described in detail in step 510 of method 500, which can be referred to in the relevant description in method 500, and will not be repeated here.

[0256] For example, the second AI information may include predicted anomalous events, predicted measurement information, identifiers of recommended candidate cells, or information about the AI ​​model, while the first AI information may include predicted anomalous events but not other information.

[0257] The difference from step 510 of method 500 is that, in the first possible scenario, when the terminal is in the first cell, the terminal can send the first AI information to the first network device. Furthermore, the terminal can also locally store the second AI information.

[0258] The second possibility is that, when the terminal is in the second cell, it can send the first AI information to the second network device. Furthermore, the terminal can also store the second AI information locally.

[0259] In step 820, the fourth network device sends an AI usage instruction to the terminal, which indicates that the first AI information sent by the terminal is used by the fourth network device. Correspondingly, the terminal receives the AI ​​usage instruction from the fourth network device.

[0260] The possible ways in which AI usage instructions may be sent have been detailed in step 520 of method 500, which can be found in the relevant description in method 500, and will not be repeated here.

[0261] In step 830, the terminal performs RRC reconstruction in the third cell in the event of an abnormal event.

[0262] The process of reconstructing RRC in the third cell when an abnormal event occurs has been detailed in step 530 of method 500. Please refer to the relevant description in method 500. It will not be repeated here.

[0263] In step 840, the terminal sends an abnormal event reporting availability indication to the third network device, which indicates that abnormal event reporting is available. Correspondingly, the third network device receives the abnormal event reporting availability indication from the terminal.

[0264] The above-mentioned abnormal event report availability indication is used to indicate that an abnormal event report is available, or in other words, the abnormal event report availability indication is used to indicate that the terminal has recorded an abnormal event report and that the abnormal event report can be obtained by a third network device.

[0265] In step 850, the third network device sends a request message to the terminal, which requests an abnormal event report. Correspondingly, the terminal receives the request message from the third network device.

[0266] In step 860, the terminal sends an abnormal event report to the third network device. This abnormal event report is a report recorded when an abnormal event occurs on the terminal, and the occurrence of the abnormal event is related to the first AI information. The abnormal event report includes the second AI information. Correspondingly, the third network device receives the abnormal event report from the terminal.

[0267] In step 870, the third network device sends an abnormal event report to the second network device. Correspondingly, the second network device receives the abnormal event report from the third network device.

[0268] In step 880, the second network device analyzes the abnormal events based on the abnormal event report.

[0269] It should be understood that, since the anomaly report includes second AI information, the second network device combines AI information with its anomaly analysis when performing analysis based on the anomaly report.

[0270] The aforementioned second network device can analyze abnormal events occurring at the terminal based on the second abnormal event report and AI information, and can obtain abnormal event analysis results.

[0271] The information that the results of the abnormal event analysis may include has been detailed in step 570 of method 500. Please refer to the relevant description in method 500. It will not be repeated here.

[0272] Optionally, the method further includes step 890, in which the second network device sends the anomaly analysis results to the fourth network device. Correspondingly, the fourth network device receives the anomaly analysis results from the second network device.

[0273] Optionally, the method further includes step 8100, whereby the fourth network device adjusts parameters based on the abnormal event analysis results.

[0274] The parameter adjustment of the fourth network device based on the abnormal event analysis results has been described in detail in step 590 of method 500. Please refer to the relevant description in method 500. It will not be repeated here.

[0275] Optionally, prior to step 830, the method further includes: the terminal sending second AI information to the second network device. Correspondingly, the second network device receives the second AI information from the terminal.

[0276] In one possible approach, the terminal is located in the first cell, and the fourth network device can be a network device serving the first cell. The first network device can make a decision based on some or all of the information in the second AI information sent by the terminal (i.e., the first AI information) (e.g., switching the terminal from the first cell to the second cell). It can also send an AI usage instruction to the terminal, which can be used to indicate that the decision of the first network device is related to the first AI information. When the terminal accesses or switches to the second cell, it can send the second AI information to the second network device serving the second cell. In this way, the terminal does not need to store the second AI information locally for a long time.

[0277] Based on the above scheme, the terminal can send part or all of the AI ​​information to the fourth network device, enabling the fourth network device to make decisions based on the AI ​​information. Simultaneously, it can store the AI ​​information locally. When the fourth network device makes a decision based on the AI ​​information, it can send an AI usage instruction to the terminal, indicating the use of that AI information. In the event of an anomaly, the terminal can send the locally stored AI information to the third network device. This allows the network side to determine whether the anomaly is related to the AI ​​information based on the AI ​​usage instruction. Furthermore, based on the anomaly report and the AI ​​information, the network can analyze the anomaly and make targeted improvements based on the analysis results, thereby enhancing network performance.

[0278] It should be understood that Figure 8 The illustrated process can also be applied to systems with network devices deployed in a distributed architecture. Specific implementation methods can be combined with... Figure 7 and Figure 8 For the sake of brevity, this article will not go into detail about how it was obtained.

[0279] It should also be understood that Figures 5 to 8 The processes shown are merely examples and should not be construed as limiting the scope of this application. In other embodiments, these processes may include more or fewer steps.

[0280] It should also be understood that the sequence number of each process does not imply 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 this application.

[0281] The communication method provided in the embodiments of this application has been described in detail above with reference to the accompanying drawings. The apparatus provided in the embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0282] Figures 9 to 10 The diagram illustrates possible communication devices provided for embodiments of this application. These communication devices can be used to implement the functions of the terminal or network device in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0283] This application provides a communication device such as Figure 9 As shown, the communication device 900 includes a communication unit 910 and a processing unit 920. The communication unit 910 can be used to perform receiving or sending actions, while the processing unit 920 can be used to perform actions other than receiving and sending, such as generating information or messages, processing received information or messages, etc.

[0284] One possible design is that the communication device 900 is used to achieve the above. Figures 5 to 8The method embodiments shown illustrate the function of the second network device in any one of the embodiments. For example, the communication device can be the second network device, a component configured in the second network device (such as a chip, chip system, processor, etc.), or a logic module or software capable of implementing some or all of the functions of the second network device.

[0285] For example, when the communication device 900 is used to implement the function of the second network device in method 500, the communication unit 910 is used to receive an abnormal event report, which is a report recorded by the terminal when an abnormal event occurs. The abnormal event report includes an AI usage instruction, which is used to indicate that the occurrence of the abnormal event is related to AI information. The processing unit 920 is used to analyze the abnormal event based on the abnormal event report and the AI ​​information.

[0286] Optionally, the anomaly report may also include the identifier of the cell that received or used the AI ​​information.

[0287] Optionally, the processing unit 920 is also configured to acquire the AI ​​information based on the AI ​​usage instruction.

[0288] Optionally, the cell receiving or using the AI ​​information is a first cell, and the communication unit 910 is further configured to send a request message to a first network device, the first network device being a network device serving the first cell, the request message being used to request the AI ​​information; and to receive the AI ​​information from the first network device.

[0289] Optionally, the request message includes the identifier of the terminal and / or the identifier of the AI ​​model, wherein the AI ​​model is the model that generates the AI ​​information.

[0290] Optionally, the AI ​​information includes predicted anomalous events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

[0291] Optionally, the communication unit 910 is further configured to receive a handover request, the handover request being used to request the terminal to be switched to the second cell, the handover request carrying the AI ​​usage indication; and to send a handover request response, the handover request response carrying the AI ​​usage indication.

[0292] Optionally, the abnormal event is: wireless link failure, handover failure, or random access failure.

[0293] For example, when the communication device 900 is used to implement the function of the second network device in method 800, the communication unit 910 is used to receive an abnormal event report, which is a report recorded when an abnormal event occurs at the terminal, and the occurrence of the abnormal event is related to AI information, and the abnormal event report includes the AI ​​information; the processing unit 920 is used to perform abnormal event analysis based on the abnormal event report.

[0294] Optionally, the communication unit 910 is further configured to receive a handover request, the handover request being used to request the terminal to be switched to the second cell, the handover request carrying an AI usage indication, the AI ​​usage indication being used to indicate that the AI ​​information sent by the terminal is used; and to send a handover request response, the handover request response carrying the AI ​​usage indication.

[0295] Optionally, the AI ​​information includes predicted anomalous events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

[0296] Optionally, the abnormal event is: wireless link failure, handover failure, or random access failure.

[0297] Another possible design is that the communication device 900 is used to implement the above. Figures 5 to 8 The terminal functions in any of the embodiments of the method shown. For example, the communication device can be a terminal, a component configured in the terminal (such as a chip, chip system, processor, etc.), or a logic module or software capable of implementing some or all of the terminal's functions.

[0298] For example, when the communication device 900 is used to implement the functions of the terminal in method 500, the communication unit 910 is used to receive an AI usage instruction from a fourth network device, the AI ​​usage instruction being used to indicate that the AI ​​information sent by the terminal is used by the fourth network device; the processing unit 920 is used to perform Radio Resource Control (RRC) reconstruction in the third cell in the event of an abnormal event occurring in the terminal; the communication unit 910 is used to send the AI ​​usage instruction to the third network device, the third network device being a network device serving the third cell.

[0299] Optionally, the communication unit 910 is also configured to receive a switching command from the fourth network device, the switching command carrying the AI ​​usage instruction.

[0300] Optionally, the communication unit 910 is further configured to send a first message to the third network device, the first message including an abnormal event report availability indication and the AI ​​usage indication, the abnormal event report availability indication indicating that an abnormal event report is available, the abnormal event report being a report recorded in the event of an abnormal event occurring on the terminal.

[0301] Optionally, the communication unit 910 is further configured to send an abnormal event report to the third network device, the abnormal event report being a report recorded in the event of an abnormal event occurring on the terminal, the abnormal event report including the AI ​​usage instruction.

[0302] Optionally, the abnormal event report includes the identifier of the cell that received or used the AI ​​information.

[0303] Optionally, the communication unit 910 is also used to send the AI ​​information to the fourth network device.

[0304] Optionally, the AI ​​information includes predicted anomalous events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

[0305] Optionally, the abnormal event is: wireless link failure, handover failure, or random access failure.

[0306] For example, when the communication device 900 is used to implement the terminal function in method 800, the communication unit 910 is used to receive an AI usage instruction from a fourth network device, the AI ​​usage instruction being used to indicate that the AI ​​information sent by the terminal is used by the fourth network device; the processing unit 920 is used to record an abnormal event report when an abnormal event occurs at the terminal, the abnormal event report including AI information; the communication unit 910 is used to send the abnormal event report to a third network device, the third network device being a network device serving a third cell, the third cell being the cell where the terminal performs Radio Resource Control (RRC) reconstruction.

[0307] Optionally, the communication unit 910 is also configured to receive a switching command from the fourth network device, the switching command carrying the AI ​​usage instruction.

[0308] Optionally, the communication unit 910 is also used to send some or all of the information in the AI ​​information to the fourth network device.

[0309] Optionally, the AI ​​information includes predicted anomalous events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

[0310] Optionally, the abnormal event is: wireless link failure, handover failure, or random access failure.

[0311] Another possible design is that the communication device 900 is used to implement the above. Figures 5 to 8 The method embodiments shown illustrate the function of the first network device in any one of the embodiments. For example, the communication device may be the first network device, a component configured in the first network device (such as a chip, chip system, processor, etc.), or a logic module or software capable of implementing some or all of the functions of the first network device.

[0312] For example, when the communication device 900 is used to implement the function of the first network device in method 500, the communication unit 910 is used to receive AI information from the terminal; and is used to send an AI usage instruction to the terminal, the AI ​​usage instruction being used to indicate that the AI ​​information sent by the terminal is used.

[0313] Optionally, the communication unit 910 is further configured to send a handover request, the handover request being used to request the terminal to be switched to a second cell, the handover request carrying the AI ​​usage indication; and to receive a handover request response, the handover request response carrying the AI ​​usage indication; and to send a handover command to the terminal, the handover command carrying the AI ​​usage indication.

[0314] Optionally, the communication unit 910 is also configured to send a switching command to the terminal, the switching command carrying the AI ​​usage instruction.

[0315] Optionally, the communication unit 910 is further configured to receive a request message, the request message being used to request the AI ​​information; and to send the AI ​​information.

[0316] Optionally, the request message includes a terminal identifier and / or an identifier of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

[0317] Optionally, the AI ​​information includes predicted anomalous events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

[0318] Optionally, the abnormal event is: wireless link failure, handover failure, or random access failure.

[0319] For example, when the communication device 900 is used to implement the function of the first network device in method 800, the communication unit 910 is used to receive part or all of the information in the AI ​​information from the terminal; and is used to send an AI usage instruction to the terminal, the AI ​​usage instruction being used to indicate that the AI ​​information sent by the terminal is used.

[0320] Optionally, the communication unit 910 is further configured to send a handover request, the handover request being used to request the terminal to be switched to a second cell, the handover request carrying the AI ​​usage indication; and to receive a handover request response, the handover request response carrying the AI ​​usage indication; and to send a handover command to the terminal, the handover command carrying the AI ​​usage indication.

[0321] Optionally, the communication unit 910 is also configured to send a switching command to the terminal, the switching command carrying the AI ​​usage instruction.

[0322] Optionally, the AI ​​information includes predicted anomalous events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

[0323] Optionally, the abnormal event is: wireless link failure, handover failure, or random access failure.

[0324] Another possible design is that the communication device 900 is used to implement the above. Figures 5 to 8 The method embodiments shown illustrate the function of the third network device in any one of the embodiments. For example, the communication device may be a third network device, a component configured in the third network device (such as a chip, chip system, processor, etc.), or a logic module or software capable of implementing some or all of the functions of the third network device.

[0325] For example, when the communication device 900 is used to implement the function of the third network device in method 500, the communication unit 910 is used to receive an AI usage instruction from the terminal, the AI ​​usage instruction being sent in the event of an abnormal event occurring on the terminal, the AI ​​usage instruction being used to indicate that the occurrence of the abnormal event is related to AI information; and is used to send the AI ​​usage instruction.

[0326] Optionally, the communication unit 910 is further configured to receive a first message from the terminal, the first message including an abnormal event report availability indication and the AI ​​usage indication, the abnormal event report availability indication indicating that a first abnormal event report is available, the first abnormal event report being a report recorded when the abnormal event occurs on the terminal.

[0327] Optionally, the communication unit 910 is further configured to receive a first abnormal event report from the terminal, the first abnormal event report being a report recorded when the abnormal event occurs on the terminal, the first abnormal event report including the AI ​​usage instruction.

[0328] Optionally, the first anomaly report may also include the identifier of the cell that received or used the AI ​​information.

[0329] Optionally, the communication unit 910 is further configured to send a second abnormal event report, the second abnormal event report being obtained based on the first abnormal event report, and the second abnormal event report including the AI ​​usage instruction.

[0330] Optionally, the AI ​​information includes predicted anomalous events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

[0331] Optionally, the abnormal event is: wireless link failure, handover failure, or random access failure.

[0332] For example, when the communication device 900 is used to implement the function of the third network device in method 800, the communication unit 910 is used to receive an abnormal event report from the terminal, the abnormal event report being a report recorded when an abnormal event occurs at the terminal, the occurrence of the abnormal event being related to AI information, the abnormal event report including the AI ​​information; and is used to send the abnormal event report.

[0333] Optionally, the AI ​​information includes predicted anomalous events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

[0334] Optionally, the abnormal event is: wireless link failure, handover failure, or random access failure.

[0335] It should also be understood that the communication unit 910 in the communication device 900 can also be called a transceiver unit. The communication unit 910 may include a transmitting module but not a receiving module. Alternatively, the communication unit 910 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme performed by the communication device 900 includes both transmitting and receiving actions. The receiving module can be used to perform the receiving action in the above-described scheme, and the transmitting module can be used to perform the transmitting action in the above-described scheme.

[0336] It is understood that the division of units in the above-described device is merely a logical functional division. Each function can correspond to a functional unit, or two or more functions can be integrated into one functional unit. In actual implementation, all or some units can be integrated into a single physical entity, or they can be distributed across different physical entities. Furthermore, the aforementioned functional units can be implemented in hardware, software, or a combination of both. Whether a function is executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0337] Another communication device provided in this application is such as Figure 10 As shown, the communication device 1000 includes at least one processor 1010. The at least one processor 1010 can be used to execute computer programs or instructions stored in memory to achieve... Figures 5 to 8 The steps executed by the terminal or by the network device (such as a first network device serving a first cell, a second network device serving a second cell, or a third network device serving a third cell) in any of the embodiments of the method shown.

[0338] Optionally, the communication device 1000 may further include at least one memory 1020 for storing instructions executed by the processor 1010, or storing input data required by the processor 1010 to execute instructions, or storing data generated after the processor 1010 executes instructions. The at least one processor 1010 and the at least one memory 1020 may be configured separately. For example, each memory may be connected to one or more processors, enabling the connected processors to read information from, store, and / or write information to the memory. Alternatively, the at least one processor 1010 and the at least one memory 1020 may be integrated together; for example, one or more memories may be integrated into a single processor.

[0339] Optionally, the communication device 1000 further includes an interface circuit 1030 for transmitting data and / or signaling. The at least one processor 1010 and the interface circuit 1030 are coupled to each other. It is understood that the interface circuit 1030 can be a transceiver, input / output circuit, bus, module, pin, or other type of communication interface, wherein the input circuit in the input / output circuit can be used for receiving, and the output interface can be used for transmitting.

[0340] Optionally, the communication device 1000 further includes a power supply circuit 1040, which can be used to supply power to the communication device 1000.

[0341] When the communication device 1000 is used to implement Figures 5 to 8 When the method is performed in any of the embodiments shown in the method examples, the processor 1010 is used to execute the functions of the processing unit, and the interface circuit 1020 is used to execute the functions of the receiving unit and / or the transmitting unit. Whether the interface circuit 1020 is used for transmitting or receiving depends on whether the communication device 1000 is performing a transmitting or receiving action in the execution scheme.

[0342] It is understood that when the communication device 1000 is a communication device (e.g., a terminal or network device), the interface circuit 1020 can be a transceiver, specifically including a transmitter and a receiver, with the transmitter used to send signals and the receiver used to receive signals. When the communication device 1000 is a chip used in a communication device, the interface circuit 1020 can be an input / output circuit, a bus, a module, a pin, or other type of communication interface, wherein the input circuit in the input / output circuit can be used for receiving, and the output interface can be used for sending.

[0343] It should be understood that Figure 10 In the communication device 1000 shown, the processor 1010 may correspond to the processing unit 920 in the aforementioned communication device 900, and the interface circuit 1020 may correspond to the communication unit 910 in the aforementioned communication device 900.

[0344] It should also be understood that the coupling in the embodiments of this application is an indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, used for information interaction between devices, units, or modules. The embodiments of this application do not limit the specific connection medium between the at least one processor 1010, at least one memory 1020, interface circuit 1030, and power supply circuit 1040. The embodiments of this application in... Figure 10 The processor 1010, memory 1020, interface circuit 1030, and power supply circuit 1040 are connected via a bus 1050. The bus 1050... Figure 10 The connections between other components are shown in bold lines only and are not intended to be limiting. The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0345] It is understood that the processor in the embodiments of this application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0346] The memory in this application embodiment can be volatile memory or non-volatile memory, or it can include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0347] This application also provides a communication system, which includes the aforementioned network equipment and terminal.

[0348] This application also provides a computer program product comprising: a computer program (also referred to as code or instructions), which, when executed, causes the computer to perform actions such as... Figures 5 to 8 The methods executed by the terminal, the first network device, the second network device, or the third network device in the illustrated embodiments.

[0349] This application also provides a computer-readable storage medium storing a computer program (also referred to as code or instructions). When the computer program is executed, it causes the computer to perform actions such as... Figures 5 to 8 The methods executed by the terminal, the first network device, the second network device, or the third network device in the illustrated embodiments.

[0350] The terms “unit”, “module”, etc., used in this specification may be used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution.

[0351] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. In the several embodiments provided in this application, it should be understood that the disclosed apparatus, devices, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0352] The unit described as a separate component may or may not be physically separate. The component shown as a unit may or may not be a physical unit; that is, it may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0353] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0354] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. This computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0355] If this function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0356] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, The method is applied to a second network device, which is a network device serving a second cell, where the terminal is located. Receive abnormal event reports, which are reports recorded by the terminal when an abnormal event occurs. The abnormal event reports include artificial intelligence (AI) usage instructions, which are used to indicate that the occurrence of the abnormal event is related to AI information. The abnormal event is analyzed based on the abnormal event report and the AI ​​information.

2. The method according to claim 1, characterized in that, The abnormal event report also includes the identifier of the cell that received or used the AI ​​information.

3. The method according to claim 1 or 2, characterized in that, The method further includes: obtaining the AI ​​information based on the AI ​​usage instruction.

4. The method according to claim 3, characterized in that, The cell that receives or uses the AI ​​information is the first cell, and the acquisition of the AI ​​information includes: A request message is sent to a first network device, which is a network device serving the first cell, and the request message is used to request the AI ​​information; Receive the AI ​​information from the first network device.

5. The method according to claim 4, characterized in that, The request message includes the identifier of the terminal and / or the identifier of the AI ​​model, wherein the AI ​​model is the model that generates the AI ​​information.

6. The method according to any one of claims 1 to 5, characterized in that, Before receiving the abnormal event report, the method further includes: Receive a handover request, the handover request being used to request that the terminal be switched to the second cell, the handover request carrying the AI ​​usage instruction; Send a switching request response, which carries the AI ​​usage instruction.

7. A communication method, characterized in that, Applied to a terminal, the method includes: Receive an AI usage instruction from a fourth network device, the AI ​​usage instruction being used to indicate that the AI ​​information sent by the terminal is used by the fourth network device; In the event of an abnormal event occurring at the terminal, Radio Resource Control (RRC) reconstruction is performed in the third cell. The AI ​​usage instruction is sent to a third network device, which is a network device serving the third cell.

8. The method according to claim 7, characterized in that, The receipt of AI usage instructions from the fourth network device includes: Receive a switching command from the fourth network device, the switching command carrying the AI ​​usage indication.

9. The method according to claim 7, characterized in that, Sending the AI ​​usage instruction to the third network device includes: Send a first message to the third network device. The first message includes an abnormal event report availability indication and an AI usage indication. The abnormal event report availability indication is used to indicate that an abnormal event report is available. The abnormal event report is a report recorded when an abnormal event occurs on the terminal.

10. The method according to claim 7, characterized in that, Sending the AI ​​usage instruction to the third network device includes: Send an abnormal event report to the third network device. The abnormal event report is a report recorded when an abnormal event occurs on the terminal. The abnormal event report includes the AI ​​usage instruction.

11. The method according to claim 9 or 10, characterized in that, The abnormal event report includes the identifier of the cell that received or used the AI ​​information.

12. The method according to any one of claims 7 to 11, characterized in that, Prior to receiving the AI ​​usage instruction from the fourth network device, the method further includes: The AI ​​information is sent to the fourth network device.

13. A communication method, characterized in that, Applied to a first network device, wherein the first network device is a network device serving a first cell, the method includes: Receive artificial intelligence (AI) information from the terminal; Send an AI usage instruction to the terminal, the AI ​​usage instruction being used to indicate that the AI ​​information sent by the terminal is used.

14. The method according to claim 13, characterized in that, Sending AI usage instructions to the terminal includes: Send a handover request, the handover request being used to request that the terminal be switched to the second cell, the handover request carrying the AI ​​usage instruction; Receive a switching request response, wherein the AI ​​usage indication is included in the switching request response; A switching command is sent to the terminal, the switching command carrying the AI ​​usage instruction.

15. The method according to claim 13, characterized in that, Sending AI usage instructions to the terminal includes: A switching command is sent to the terminal, the switching command carrying the AI ​​usage instruction.

16. The method according to any one of claims 13 to 15, characterized in that, The method further includes: Receive a request message, the request message being used to request the AI ​​information; Send the AI ​​information.

17. The method according to claim 16, characterized in that, The request message includes a terminal identifier and / or an identifier for the AI ​​model, wherein the AI ​​model is the model that generates the AI ​​information.

18. A communication method, characterized in that, Applied to a terminal, the method includes: Receive an AI usage instruction from a fourth network device, the AI ​​usage instruction being used to indicate that the AI ​​information sent by the terminal is used by the fourth network device; In the event of an abnormal event occurring on the terminal, an abnormal event report is recorded, which includes AI information; The abnormal event report is sent to a third network device, which is a network device serving a third cell, and the third cell is the cell in which the terminal performs Radio Resource Control (RRC) reconstruction.

19. The method according to claim 18, characterized in that, The step of receiving the AI ​​usage instruction from the fourth network device includes: receiving a switching command from the fourth network device, the switching command carrying the AI ​​usage instruction.

20. The method according to claim 18 or 19, characterized in that, Prior to receiving the AI ​​usage instruction from the fourth network device, the method further includes: Send some or all of the AI ​​information to the fourth network device.

21. The method according to any one of claims 1 to 20, characterized in that, The AI ​​information includes predicted abnormal events and one or more of the following: predicted measurement information, identifiers of recommended candidate cells, or information of an AI model, wherein the AI ​​model is the model that generates the AI ​​information.

22. A communication device, characterized in that, It includes one or more functional units for implementing the method as described in any one of claims 1 to 21.

23. A communication device, characterized in that, Includes a processor for executing program code to cause the communication device to implement the method as described in any one of claims 1 to 21.

24. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the method as described in any one of claims 1 to 21 is performed.

25. A computer program product, characterized in that, Includes a computer program, which, when run, causes the method as described in any one of claims 1 to 21 to be performed.

Images