Communication method and apparatus

Abstract

A communication method and apparatus. The method comprises: a first analytics function network element receives an analytics context transfer request from a second analytics function network element, and the first analytics function network element sends an analytics context to the second analytics function network element, wherein the analytics context comprises the identifier of a first model and the identifier of a model training function network element. By means of the method, the second analytics function network element obtains the analytics context which comprises the identifier of the first model and the identifier of the model training function network element, instead of directly obtaining first information, and the second analytics function network element can obtain the first information from the model training function network element on the basis of the identifier of the first model and information of the model training function network element, so that the second analytics function network element can obtain the model used by the first analytics function network element; moreover, the security of model obtaining can be improved.

Description

Communication method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on October 30, 2023, with application number 202311428205.5 and invention name "A Communication Method and Device", the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of communication technology, and in particular to a communication method and device. Background Art

[0004] Due to internal (e.g. load balancing, graceful shutdown) or external triggers (e.g. user equipment (UE) mobility), a service consuming network element may transfer one or more analytics subscriptions from one analytics logical function (AnLF) network element to another AnLF network element, i.e. from a source AnLF network element to a target AnLF network element.

[0005] Currently, a service-consuming NE or source AnLF NE needs to use the NE discovery process to discover a target AnLF NE. This process is used to transfer the analysis context of the analysis subscription to be transferred from the source AnLF NE to the target AnLF NE. After the target AnLF NE obtains the analysis context, it hopes to continue providing services to the service-consuming NE using the model previously used by the source AnLF NE. However, how to enable the target AnLF NE to continue providing services to the service-consuming NE using the model previously used by the source AnLF NE is a significant issue.

[0006] Summary of the Invention

[0007] The embodiments of the present application provide a communication method and apparatus for solving the problem that a source AnLF network element notifies a target AnLF element that a model used by the source AnLF network element has a security risk.

[0008] In a first aspect, the present application provides a communication method, which can be performed by a first analysis function network element or a module (such as a chip) in the first analysis function network element. The method includes: the first analysis function network element receiving an analysis context transfer request from a second analysis function network element; the first analysis function network element sending an analysis context to the second analysis function network element, where the analysis context includes an identifier of a first model and an identifier of a model training function network element.

[0009] Using the above method, the analysis context provided by the first analysis function network element to the second analysis function network element includes the identifier of the first model and the identifier of the model training function network element, rather than directly including the first information, which can improve the security of model acquisition.

[0010] In a possible implementation, the first analysis function network element receives first information from the model training function network element, where the first information is associated with the first model.

[0011] In a possible implementation, the first information includes an identifier of the model training function network element.

[0012] The model training function network element provides first information to the first analysis function network element, where the first information is associated with the first model.

[0013] The model training function network element is a producer of the model associated with the first information. The model training function network element authorizes the first analysis function network element to obtain the model associated with the first information. The first information includes an identifier of the first model, and the model associated with the first information is the first model.

[0014] The first information is information related to the first model. Exemplarily, the first information includes the network element identifier of the producer of the model, that is, the identifier of the network element with the model training function, or the network element identifier of the network element that provides information related to the first model. The first information may also include the address of the model, such as a URL.

[0015] In one possible implementation, before the first analysis function network element receives an analysis context transfer request from the second analysis function network element, the first analysis function network element uses the first model to provide services corresponding to the analysis identifier; the first analysis function network element sends an analysis subscription transfer request to the second analysis function network element, and the analysis subscription transfer request includes the analysis identifier.

[0016] In one possible implementation, the analysis context transfer request includes the manufacturer's identifier of the second analysis function network element; before the first analysis function network element sends the analysis context to the second analysis function network element, the first analysis function network element obtains a first interoperability identifier, which is the interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is the interoperability identifier of the model training function network element; the first analysis function network element determines that the first interoperability identifier includes the manufacturer's identifier of the second analysis function network element.

[0017] The above design can be used to determine whether the first interoperability identifier includes the identifier of the manufacturer of the second analysis function network element.

[0018] In a possible implementation, the first analysis function network element obtains the first interoperability identifier from the model training function network element or the network storage function network element.

[0019] In one possible implementation, before the first analysis function network element receives an analysis context transfer request from the second analysis function network element, the first analysis function network element sends a model request message to the model training function network element, and the model request message includes the analysis identifier; the first analysis function network element receives the identifier of the first model from the model training function network element.

[0020] In one possible implementation, before the first analysis function network element sends the analysis context to the second analysis function network element, the first analysis function network element sends a first request message to the model training function network element, and the first request message is used to request the model training function network element to agree that the first analysis function network element provides the second analysis function network element with the identifier of the first model; the first analysis function network element receives a first response message from the model training function network element, and the first response message indicates that it agrees that the first analysis function network element provides the second analysis function network element with the identifier of the first model.

[0021] The above design can realize the request model training function network element to authorize the first analysis function network element to provide the identification of the first model to the second analysis function network element.

[0022] In a second aspect, the present application provides a communication method, which can be performed by a second analysis function network element or a module (such as a chip) in the second analysis function network element. The method includes: the second analysis function network element sends an analysis context transfer request to the first analysis function network element; the second analysis function network element receives an analysis context from the first analysis function network element, the analysis context including an identifier of a first model and an identifier of a model training function network element; the second analysis function network element sends the identifier of the first model to the model training function network element; the second analysis function network element receives first information from the model training function network element, where the first information is associated with the first model.

[0023] Using the above method, the analysis context obtained by the second analysis function network element includes the identifier of the first model and the identifier of the model training function network element, instead of obtaining the first information directly from the first analysis function network element. The second analysis function network element can obtain the first information from the model training function network element based on the identifier of the first model and the identifier of the model training function network element, so that the second analysis function network element can obtain the model used by the first analysis function network element and improve the security of model acquisition.

[0024] In a possible implementation, the first information includes an identifier of the model training function network element.

[0025] In a possible implementation, the analysis context transfer request includes an identifier of a manufacturer of the second analysis function network element.

[0026] In one possible implementation, before the second analysis function network element sends an analysis context transfer request to the first analysis function network element, the second analysis function network element receives an analysis subscription transfer request from the first analysis function network element, and the analysis subscription transfer request includes analysis subscription information; the second analysis function network element determines the first analysis function network element based on the analysis subscription information.

[0027] In one possible implementation, before the second analysis function network element sends an analysis context transfer request to the first analysis function network element, the second analysis function network element receives an analysis subscription request from a service consumption network element; the analysis subscription request includes analysis subscription information; the second analysis function network element determines the first analysis function network element based on the analysis subscription information.

[0028] In a third aspect, the present application provides a communication method, which can be performed by a model training function network element or a module (such as a chip) in the model training function network element. The method includes: the model training function network element receives an identifier of a first model from a second analysis function network element; the model training function network element determines first information based on the identifier of the first model, the first information being associated with the first model; and the model training function network element sends the first information to the second analysis function network element.

[0029] By adopting the above method, when the model training function network element determines that the second analysis function network element obtains the identifier of the first model, it provides the first information to the second analysis function network element, and can improve the security of model acquisition.

[0030] In one possible implementation, before the model training function network element receives the identifier of the first model from the second analysis function network element, the model training function network element receives a first request message from the first analysis function network element, and the first request message is used to request the model training function network element to agree that the first analysis function network element provides the identifier of the first model to the second analysis function network element; the model training function network element sends a first response message to the first analysis function network element, and the first response message indicates that it agrees that the first analysis function network element provides the identifier of the first model to the second analysis function network element.

[0031] With the above design, the model training function network element can authorize the first analysis function network element to provide the second analysis function network element with the identifier of the first model.

[0032] In one possible implementation, the model training function network element receives a model request message from the first analysis function network element, and the model request message includes an analysis identifier; the model training function network element sends the identifier of the first model to the first analysis function network element, and the first model is used to provide a service corresponding to the analysis identifier.

[0033] In one possible implementation, before the model training function network element receives the identifier of the first model from the second analysis function network element, the model training function network element sends a first interoperability identifier to the first analysis function network element, where the first interoperability identifier is the interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is the interoperability identifier of the model training function network element.

[0034] In one possible implementation, before the model training function network element receives the identifier of the first model from the second analysis function network element, the model training function network element sends first information to the first analysis function network element, where the first information is associated with the first model.

[0035] In a possible implementation, the first information includes an identifier of the model training function network element.

[0036] In a fourth aspect, the present application provides a communication method, which can be performed by a first analysis function network element or a module (such as a chip) in the first analysis function network element. The method includes: the first analysis function network element receiving an analysis context transfer request from a second analysis function network element; and the first analysis function network element sending an analysis context to the second analysis function network element, where the analysis context includes an association identifier and an identifier of a model training function network element.

[0037] Using the above method, the analysis context provided by the first analysis function network element to the second analysis function network element includes the association identifier and the identifier of the model training function network element, rather than directly including the first information, which can improve the security of model acquisition.

[0038] In a possible implementation, the association identifier corresponds to the first information, the model training function network element is used to provide the first information, and the first information is associated with the first model.

[0039] In one possible implementation, the first analysis function network element sends a model request message to the model training function network element, and the model request message includes an analysis identifier; the first analysis function network element receives the identifier of the first model and the association identifier from the model training function network element, and the first model is used to provide the service corresponding to the analysis identifier.

[0040] With the above design, the first analysis function network element can use the existing subscription association identifier as the association identifier.

[0041] In one possible implementation, after the first analysis function network element receives the analysis context transfer request from the second analysis function network element, the first analysis function network element sends a third request message to the model training function network element, and the third request message includes the identifier of the first model; the third request message is used to request the model training function network element to generate an identifier associated with the first information; the first analysis function network element receives a third response message from the model training function network element, and the third response message includes the associated identifier.

[0042] With the above design, the first analysis function network element can request the model training function network element to generate an identifier associated with the first information as an association identifier. Alternatively, it can be described as follows: the first analysis function network element can request the model training function network element to generate an identifier associated with the first model as an association identifier.

[0043] In one possible implementation, before the first analysis function network element receives an analysis context transfer request from the second analysis function network element, the first analysis function network element uses the first model to provide services corresponding to the analysis identifier; the first analysis function network element sends an analysis subscription transfer request to the second analysis function network element, and the analysis subscription transfer request includes the analysis identifier.

[0044] In one possible implementation, the analysis context transfer request includes the manufacturer's identifier of the second analysis function network element; before the first analysis function network element sends the analysis context to the second analysis function network element, the first analysis function network element obtains a first interoperability identifier, which is the interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is the interoperability identifier of the model training function network element; the first analysis function network element determines that the first interoperability identifier includes the manufacturer's identifier of the second analysis function network element.

[0045] In a possible implementation, the first analysis function network element obtains the first interoperability identifier from the model training function network element or the network storage function network element.

[0046] In a fifth aspect, the present application provides a communication method, which can be performed by a second analysis function network element or a module (such as a chip) in the second analysis function network element. The method includes: the second analysis function network element sends an analysis context transfer request to the first analysis function network element; the second analysis function network element receives an analysis context from the first analysis function network element, the analysis context including an association identifier and an identifier of a model training function network element; the second analysis function network element sends the association identifier to the model training function network element; the second analysis function network element receives the first information from the model training function network element, the first information being associated with the first model.

[0047] Using the above method, the analysis context obtained by the second analysis function network element includes the association identifier and the identifier of the model training function network element, instead of obtaining the first information directly from the first analysis function network element. The second analysis function network element can obtain the first information from the model training function network element based on the association identifier and the identifier of the model training function network element, so that the second analysis function network element can obtain the model used by the first analysis function network element and improve the security of model acquisition.

[0048] In a possible implementation, the first association identifier corresponds to the first information, and the model training function network element is used to provide the first information.

[0049] In one possible implementation, before the second analysis function network element sends an analysis context transfer request to the first analysis function network element, the second analysis function network element receives an analysis subscription transfer request from the first analysis function network element, and the analysis subscription transfer request includes analysis subscription information; the second analysis function network element determines the first analysis function network element based on the analysis subscription information.

[0050] In one possible implementation, before the second analysis function network element sends an analysis context transfer request to the first analysis function network element, the second analysis function network element receives an analysis subscription request from a service consumption network element; the analysis subscription request includes analysis subscription information; the second analysis function network element determines the first analysis function network element based on the analysis subscription information.

[0051] In a sixth aspect, the present application provides a communication method, which can be performed by a model training function network element or a module (such as a chip) in the model training function network element. The method includes: the model training function network element receives an association identifier from a second analysis function network element; the model training function network element determines first information based on the association identifier, where the first information is associated with the first model; and the model training function network element sends the first information to the second analysis function network element.

[0052] By adopting the above method, when the model training function network element determines that the second analysis function network element obtains the association identifier, it provides the first information to the second analysis function network element, and can improve the security of model acquisition.

[0053] In one possible implementation, before the model training function network element receives the association identifier from the second analysis function network element, the model training function network element receives a third request message from the first analysis function network element, and the third request message includes the identifier of the first model; the third request message is used to request the model training function network element to generate an identifier associated with the first information; the model training function network element sends a third response message to the first analysis function network element, and the third response message includes the association identifier.

[0054] In one possible implementation, the model training function network element receives a model request message from the first analysis function network element, and the model request message includes an analysis identifier; the model training function network element sends the identifier of the first model and the association identifier to the first analysis function network element, and the first model is used to provide the service corresponding to the analysis identifier.

[0055] In one possible implementation, the model training function network element also sends a first interoperability identifier to the first analysis function network element, where the first interoperability identifier is the interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is the interoperability identifier of the model training function network element.

[0056] In a seventh aspect, the present application provides a communication method, which can be performed by a first analysis function network element or a module (such as a chip) in the first analysis function network element. The method includes: the first analysis function network element receiving an analysis context transfer request from a second analysis function network element, wherein the analysis context transfer request includes a model receiving address; and the first analysis function network element sending an identifier of a first model and the model receiving address to a model training function network element.

[0057] By adopting the above method, the analysis context provided by the first analysis function network element to the second analysis function network element includes the identifier of the first model and the model receiving address, rather than directly including the first information, which can improve the security of model acquisition.

[0058] In one possible implementation, before the first analysis function network element receives an analysis context transfer request from the second analysis function network element, the first analysis function network element uses the first model to provide services corresponding to the analysis identifier; the first analysis function network element sends an analysis subscription transfer request to the second analysis function network element, and the analysis subscription transfer request includes the analysis identifier.

[0059] In one possible implementation, the analysis context transfer request includes the manufacturer's identifier of the second analysis function network element; before the first analysis function network element sends the analysis context to the second analysis function network element, the first analysis function network element obtains a first interoperability identifier, which is the interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is the interoperability identifier of the model training function network element; the first analysis function network element determines that the first interoperability identifier includes the manufacturer's identifier of the second analysis function network element.

[0060] In a possible implementation, the first analysis function network element obtains the first interoperability identifier from the model training function network element or the network storage function network element.

[0061] In one possible implementation, before the first analysis function network element receives an analysis context transfer request from the second analysis function network element, the first analysis function network element sends a model request message to the model training function network element, and the model request message includes the analysis identifier; the first analysis function network element receives the identifier of the first model from the model training function network element.

[0062] In an eighth aspect, the present application provides a communication method, which can be performed by a second analysis function network element or a module (such as a chip) in the second analysis function network element. The method includes: the second analysis function network element sending an analysis context transfer request to the first analysis function network element; wherein the analysis context transfer request includes a model receiving address; and the second analysis function network element obtaining first information based on the model receiving address, where the first information is associated with the first model.

[0063] Using the above method, the second analysis function network element provides the model receiving address to the first analysis function network element, and obtains the first information based on the model receiving address. This allows the second analysis function network element to obtain the model used by the first analysis function network element and improves the security of model acquisition.

[0064] In one possible implementation, before the second analysis function network element sends an analysis context transfer request to the first analysis function network element, the second analysis function network element receives an analysis subscription transfer request from the first analysis function network element, and the analysis subscription transfer request includes analysis subscription information; the second analysis function network element determines the first analysis function network element based on the analysis subscription information.

[0065] In one possible implementation, before the second analysis function network element sends an analysis context transfer request to the first analysis function network element, the second analysis function network element receives an analysis subscription request from a service consumption network element; the analysis subscription request includes analysis subscription information; the second analysis function network element determines the first analysis function network element based on the analysis subscription information.

[0066] In a ninth aspect, the present application provides a communication method, which can be performed by a model training function network element or a module (such as a chip) in the model training function network element. The method includes: the model training function network element receives an identifier of a first model and a model receiving address from a second analysis function network element; the model training function network element determines first information based on the identifier of the first model, the first information being associated with the first model; and the model training function network element provides the first information based on the model receiving address.

[0067] Using the above method, the model training function network element obtains the model receiving address from the first analysis function network element, and provides the first information based on the model receiving address, so that the second analysis function network element can obtain the model used by the first analysis function network element, and can improve the security of model acquisition.

[0068] In one possible implementation, the model training function network element receives a model request message from the first analysis function network element, and the model request message includes an analysis identifier; the model training function network element sends the identifier of the first model to the first analysis function network element, and the first model is used to provide a service corresponding to the analysis identifier.

[0069] In one possible implementation, the model training function network element also sends a first interoperability identifier to the first analysis function network element, where the first interoperability identifier is the interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is the interoperability identifier of the model training function network element.

[0070] In the tenth aspect, the present application provides a communication device, which can be a first device, or a module or unit (for example, a chip, or a chip system, or a circuit) in the first device that corresponds one-to-one to the method / operation / step / action described in any one of the first to ninth aspects, or can be used in combination with the first device.

[0071] In the eleventh aspect, the present application provides a communication device comprising at least one processing element and at least one storage element, wherein the at least one storage element is used to store programs and data, and the at least one processing element is used to read and execute the programs and data stored in the storage element, so that the method described in any one of the above aspects of the present application is implemented.

[0072] In a twelfth aspect, the present application further provides a computer program, which, when executed on a computer, enables the computer to execute any of the methods described in any of the above aspects.

[0073] In the thirteenth aspect, the present application provides a communication device, which includes: an interface circuit and at least one processor; the interface circuit is used to provide input and / or output of programs or instructions to the at least one processor; the at least one processor is used to execute the program or instructions so that the communication device can implement any method described in any of the above aspects.

[0074] In one possible manner, the communication device includes the at least one memory, and the at least one memory is used to store the program or instruction.

[0075] In a fourteenth aspect, the present application provides a computer storage medium storing a software program. When the software program is read and executed by one or more processors, it can implement any of the methods described in any of the above aspects.

[0076] In a fifteenth aspect, the present application provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the methods described in any of the above aspects.

[0077] In the sixteenth aspect, the present application provides a chip system, which includes at least one chip and a memory, and the at least one chip is used to read and execute the program stored in the memory to implement any of the methods described in any of the above aspects.

[0078] In the seventeenth aspect, the present application provides a communication system, which includes a first analysis function network element, a second analysis function network element and a model training function network element, the first analysis function network element executes the method described in any one of the first, fourth or seventh aspects, the second analysis function network element executes the method described in any one of the second, fifth or eighth aspects, and the model training function network element executes the method described in any one of the third, sixth or ninth aspects.

[0079] In one possible embodiment, the system further includes a network storage function network element and / or a service consumption network element.

[0080] Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 is a schematic diagram of the 5G network architecture based on the service-oriented architecture in this application;

[0082] FIG2 is one of the flow charts of an overview of a communication method in this application;

[0083] FIG3 is a flow chart showing a service consumption network element triggering a target AnLF to send an analysis context transfer request to a first AnLF in this application;

[0084] FIG4 is a flowchart of a first AnLF triggering a target AnLF to send an analysis context transfer request to the first AnLF in this application;

[0085] FIG5 is a second flow chart of an overview of a communication method in this application;

[0086] FIG6 is a third flow chart of an overview of a communication method in this application;

[0087] FIG7 is a fourth flow chart of an overview of a communication method in this application;

[0088] FIG8 is a fifth flow chart of an overview of a communication method in this application;

[0089] FIG9 is a schematic structural diagram of a communication device in this application;

[0090] FIG10 is a schematic structural diagram of another communication device in this application. DETAILED DESCRIPTION

[0091] The specific implementation of the present application is described below with reference to the accompanying drawings in the embodiments of the present application. However, the implementation of the present application may also include combining these embodiments without departing from the spirit or scope of the present application, such as adopting other embodiments and making structural changes. Therefore, the detailed description of the following embodiments should not be understood in a restrictive sense. The terms used in the examples section of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.

[0092] The embodiments of the present application can be applied to various communication systems, such as: global system for mobile communications (GSM) system, code division multiple access (CDMA) system, wideband code division multiple access (WCDMA) system, general packet radio service (GPRS), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), universal mobile telecommunication system (UMTS), world-wide interoperability for microwave access (WIMAX) communication system, fifth generation (5G) system or new radio (NR), or applied to future communication systems or other similar communication systems.

[0093] Figure 1 is a schematic diagram of a 5G network architecture based on a service-oriented architecture. The 5G network architecture shown in Figure 1 may include terminal devices, access network devices, and core network devices. The terminal device accesses the data network (DN) through the access network device and the core network device. Among them, the core network device includes a variety of network functions (NFs) or network elements, for example, including some or all of the following network elements: unified data management (UDM) network element, unified data repository (UDR) network element, application function (AF) network element, policy control function (PCF) network element, access and mobility management function (AMF) network element, session management function (SMF) network element, user plane function (UPF) network element, network data analytics function (NWDAF) network element, network repository function (NRF) network element (not shown in the figure), etc.

[0094] The access network device may be a radio access network (RAN) device. For example: a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next generation NodeB (gNB) in a 5G mobile communication system, a next generation base station in a sixth generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a wireless fidelity (WiFi) system, etc.; it may also be a module or unit that performs part of the functions of a base station, for example, a centralized unit (CU) or a distributed unit (DU). The radio access network device may be a macro base station, a micro base station or an indoor station, a relay node or a donor node, etc. The embodiments of the present application do not limit the specific technology and specific device form adopted by the radio access network device.

[0095] Terminal devices can be user equipment (UE), mobile stations, mobile terminals, etc. Terminal devices can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), the Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, and smart cities. Terminal devices can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, urban air vehicles (such as drones and helicopters), ships, robots, robotic arms, smart home devices, etc.

[0096] Access network equipment and terminal devices can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; on water; or in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of access network equipment and terminal devices.

[0097] The following is a brief introduction to some core network equipment:

[0098] The AMF network element, referred to as AMF, performs functions such as mobility management and access authentication / authorization. It is also responsible for transmitting user policies between terminal devices and the PCF.

[0099] The SMF network element, referred to as SMF, includes functions such as session management, execution of control policies issued by PCF, selection of UPF, and allocation of Internet Protocol (IP) addresses for terminal devices.

[0100] The UPF network element, referred to as UPF, serves as the interface with the data network and includes functions such as user plane data forwarding, session / flow-level billing statistics, and bandwidth limitation.

[0101] UDM network element, referred to as UDM, includes functions such as executing and managing contract data and user access authorization.

[0102] The UDR network element, referred to as UDR, includes the access functions of executing contract data, policy data, application data and other types of data.

[0103] NEF network element, referred to as NEF, is used to support the opening of capabilities and events.

[0104] The AF network element, abbreviated as AF, conveys the application side's requirements to the network side, such as quality of service (QoS) requirements or user status event subscriptions. The AF can be a third-party functional entity or an application server deployed by the operator.

[0105] The PCF network element, referred to as PCF, includes policy control functions such as session and service flow level billing, QoS bandwidth guarantee and mobility management, and terminal device policy decision-making.

[0106] NRF network elements, or NRF for short, can be used to provide network element discovery capabilities. Based on requests from other network elements, they provide network element information corresponding to the network element type. NRF network elements also provide network element management services, such as network element registration, update, and deregistration, as well as network element status subscription and push notification.

[0107] NWDAF network element, referred to as NWDAF, is mainly used to collect data (including one or more of terminal device data, access network device data, core network network element data and third-party application device data), wherein these data can be the terminal device, access network device, core network network element or third-party application device data itself, or the terminal device on the access network device, the core network network element or the third-party application device. Then, data analysis is performed based on the collected data, and the data analysis results are output for use by the network, network management equipment and application execution policy decision-making. NWDAF can use machine learning models for data analysis. In an embodiment of the present application, an NWDAF can be a separate network element, or it can be set up together with other network elements, for example, NWDAF is set up in a PCF network element or an AMF network element.

[0108] In Release 17 of the 3rd Generation Partnership Project (3GPP), the training and inference functions of NWDAF are split. An NWDAF can support only the model training function, only the data inference function, or both the model training and data inference functions.

[0109] In this application, the model training function network element may be an NWDAF supporting the model training function, which may also be referred to as a training NWDAF, or an NWDAF supporting a model training logical function (MTLF), referred to as MTLF. For example, the MTLF may perform model training based on the acquired data to obtain a trained model.

[0110] The analysis function network element can be an NWDAF that supports data reasoning, also known as a reasoning NWDAF, or an NWDAF that supports the analytics logical function (AnLF), or simply AnLF. For example, the AnLF can request a model from the MTLF via a model subscription (MLModelProvision_Subscribe) service or message. The model can be trained by the MTLF based on relevant model data. Furthermore, the AnLF can input the input data into the trained model to obtain analysis results or reasoning data.

[0111] It is understood that MTLF can be understood as NWDAF that at least supports model training. As a possible implementation method, MTLF can also support data reasoning. AnLF can be understood as NWDAF that at least supports data reasoning. As a possible implementation method, AnLF can also support model training.

[0112] It can be understood that the above network elements are examples of one implementation method, and this application does not exclude the existence of network elements or devices with the above network element functions in 6G or newer wireless communication systems that have other names or other forms.

[0113] It is understood that the above-mentioned network element or function can be a network element in a hardware device, a software function running on dedicated hardware, or a virtualized function instantiated on a platform (e.g., a cloud platform). As a possible implementation method, the above-mentioned network element or function can be implemented by a single device, or can be implemented by multiple devices together, or can be a functional module within a single device, which is not specifically limited in the embodiments of the present application.

[0114] In Figure 1, Nudr, Npcf, Namf, Nudm, Nsmf, Naf, and Nnwdaf are service interfaces provided by the above-mentioned UDR, PCF, AMF, UDM, SMF, AF, and NWDAF, respectively, which are used to call corresponding service operations.

[0115] The following is an explanation of the basic technical concepts involved in this application:

[0116] 1. Analysis ID

[0117] An analysis identifier can be used to indicate an analysis business, or analysis service (or simply service). This service is associated with a model, meaning the model can be used to execute the service. Alternatively, the analysis identifier is associated with the model, meaning the model is used to execute the service associated with the analysis identifier.

[0118] Alternatively, it can be understood that the MTLF is associated with an analysis identifier, that is, the model support provided by the MTLF is used to execute the service corresponding to the analysis identifier. For example, the MTLF can be associated with one or more analysis identifiers. It can be understood that the MTLF can provide a model for the service corresponding to each of the one or more analysis identifiers. For example, MTLF1 is associated with analysis identifier 1 and analysis identifier 2, that is, MTLF1 corresponds to analysis identifier 1 and analysis identifier 2. Then, MTLF1 can provide a model for the service corresponding to analysis identifier 1, and a model for the service corresponding to analysis identifier 2.

[0119] 2. Interoperability indicator

[0120] For example, the interoperability identifier can correspond to the MTLF, or to the analysis identifier, or to the analysis identifier corresponding to the MLTF. Alternatively, the interoperability identifier can be described as being related to the MTLF, or the interoperability identifier is related to the analysis identifier. The interoperability identifier can also be called an interoperability indicator, a machine learning (ML) model interoperability identifier, or a model interoperability indicator.

[0121] The interoperability identifier includes a list of vendors, or is described as a list of NWDAF providers (or suppliers). The vendors in the vendor list are allowed to retrieve or use models provided by the MTLF. The interoperability identifier also indicates that the MTLF supports vendors requesting models provided by the MTLF for the NWDAF of the vendors in the vendor list. The interoperability identifier also indicates that the vendors in the vendor list are allowed to obtain models from the MTLF. The interoperability identifier also indicates that the MTLF allows the vendors in the vendor list to obtain models from the MTLF.

[0122] The interoperability identifier is a list of MTLF providers, for example, the interoperability identifier represents the manufacturer identifier, or the interoperability identifier is associated with the manufacturer identifier. The interoperability identifier can be associated with the analysis identifier, such as a one-to-one correspondence between the two, indicating that the MTLF allows the corresponding manufacturer or the MTLF included in the manufacturer to obtain the model corresponding to the analysis identifier, and / or indicates that the MTLF is allowed to interoperate with the AnLF on the model corresponding to the analysis identifier. Optionally, a MTLF may have one or more interoperability identifiers. If there are multiple interoperability identifiers, the multiple interoperability identifiers correspond to different analysis identifiers respectively. For example, MTLF NF ID 1 corresponds to analysis identifier 1 and analysis identifier 2, wherein the MTLF to which MTLF NF ID 1 belongs has interoperability identifier 1 and interoperability identifier 2, interoperability identifier 1 corresponds to analysis identifier 1, and interoperability identifier 2 corresponds to analysis identifier 2. Optionally, if the MTLF to which MTLF NF ID 1 belongs and the MTLF to which MTLF NF ID 2 belongs support interoperability, the MTLF to which MTLF NF ID 2 belongs may have interoperability identifier 1 and interoperability identifier 2, wherein interoperability identifier 1 corresponds to analysis identifier 1, and / or, interoperability identifier 2 corresponds to analysis identifier 2, that is, MTLFs of the same manufacturer may have the same interoperability identifier for the same analysis identifier. In addition, if the MTLF to which MTLF NF ID 1 belongs and the MTLF to which MTLF NF ID 2 belongs belong to different manufacturers, the MTLF to which MTLF NF ID 2 belongs may have interoperability identifier 3 and interoperability identifier 4, wherein interoperability identifier 3 corresponds to analysis identifier 1, and / or, interoperability identifier 4 corresponds to analysis identifier 2, that is, MTLFs of the same manufacturer may have different interoperability identifiers for the same analysis identifier.

[0123] Exemplarily, analysis identifier 1 is associated with model 1, i.e., model 1 is used to execute the service corresponding to analysis identifier 1, and analysis identifier 1 is associated with interoperability identifier 1, i.e., model 1 is associated with interoperability identifier 1. Assume that interoperability identifier 1 includes the identifier of manufacturer 1 and the identifier of manufacturer 2, i.e., model 1 can be provided to manufacturer 1 and manufacturer 2 for use. Alternatively, it can be understood that if the manufacturer of the NWDAF is manufacturer 1 or manufacturer 2, then the NWDAF can use model 1.

[0124] For example, a MTLF may have one or more interoperability identifiers. If there are multiple interoperability identifiers, the multiple interoperability identifiers may correspond to different analysis identifiers. For example, MTLF1 corresponds to analysis identifier 1 and analysis identifier 2, where interoperability identifier 1 corresponds to analysis identifier 1 and interoperability identifier 2 corresponds to analysis identifier 2.

[0125] 3. Model Producer

[0126] A model producer is the entity that produces the model, or is authorized to provide model information to other entities based on network configuration. Consumers can obtain the model based on the model information. Model information includes, but is not limited to, the uniform resource locator (URL) of the model file and the model itself.

[0127] 4. Manufacturer logo

[0128] The vendor ID of the vendor can also be expressed as network element information, identifying the vendor or manufacturer of the network element. For example, Vendor ID1 identifies the vendor of the NWDAF network element.

[0129] The vendor identifier can be used to identify a device manufacturer. A vendor identifier can correspond to one or more NWDAF device identifiers. For example, NWDAF NF ID 1 and NWDAF NF ID 2 can both correspond to vendor identifier 1. This means that the MTLF to which MTLF NF ID 1 belongs and the MTLF to which MTLF NF ID 2 belongs belong to the same vendor, whose vendor identifier is vendor identifier 1.

[0130] Currently, according to the model authorization process, the transfer or use of a model must be authorized by the model producer. Therefore, before a source AnLF network element can transfer a model to a third party, it must obtain authorization from the model producer (i.e., the MTLF network element that produced the model). If the source AnLF network element directly carries the model address to the target AnLF (i.e., the third party) through the analysis context, this poses a security risk.

[0131] Based on the network system architecture shown in FIG1 and the contents of the above related technical introduction, several possible communication methods are provided in the embodiment of the present application. In the following, the analysis function network element is AnLF and the model training function network element is MTLF as an example for explanation.

[0132] The present application provides a communication method, as shown in FIG2 , which includes:

[0133] Step 200: The second AnLF sends an analysis context transfer request to the first AnLF. Correspondingly, the first AnLF receives the analysis context transfer request from the second AnLF.

[0134] Exemplarily, the first AnLF provides a service corresponding to an analysis identifier for a service-consuming network element, and the analysis subscription corresponding to the analysis identifier is associated with an analytics context identifier. If the first AnLF or the service-consuming network element determines to select a target AnLF, that is, decides to transfer the analysis subscription from the first AnLF to the target AnLF, the target AnLF is triggered to send an analysis context transfer request to the first AnLF. The following description uses the target AnLF as an example, where the second AnLF is used as the target. The first AnLF may also be referred to as the source AnLF.

[0135] Exemplarily, the analysis context transfer request includes the analysis context identifier, so that the first AnLF determines that the analysis subscription to be transferred is the analysis subscription associated with the analysis context identifier, and further determines the analysis context corresponding to the analysis context identifier.

[0136] For example, the analysis context identifier may be a subscription correlation ID, or a set of user permanent identifiers (SUPI) and related analysis IDs for UE-related analysis, or an analysis ID for NF-related analysis.

[0137] Step 210: The first AnLF sends an analysis context to the second AnLF. Correspondingly, the second AnLF receives the analysis context from the first AnLF.

[0138] The analysis context includes the identifier of the first model and the identifier of the first MTLF. The first AnLF uses the first model to provide a service corresponding to the analysis identifier for the service-consuming network element. The first MTLF corresponding to the identifier of the first MTLF is the producer of the first model. That is, the first AnLF obtains ML model information from the first MTLF to provide the service corresponding to the analysis identifier. The ML model information can also be referred to as first information, and the first information is associated with the first model. The first information may include an ML model file address (e.g., a URL or a fully qualified domain name (FQDN), or an analytics data repository functional (ADRF) ID or an ADRF set ID. When the ML model information includes an ADRFID or ADRF set ID, the first information may also include a storage transaction ID. Optionally, the first information may include an identifier of the first model. Optionally, the first information may include an interoperability identifier corresponding to the analysis identifier corresponding to the first model of the MTLF. The first information may also include other content, which is not limited in this application. It is understandable that part of the content included in the first information can be used to obtain the first model, and the first information also includes other content, for example, relevant information for describing the first model, model accuracy information, model applicable scenario information, etc.

[0139] The first AnLF obtains, from the first MTLF, ML model information of a model used to provide a service corresponding to the analysis identifier.

[0140] Step 220: The second AnLF sends the identifier of the first model to the first MTLF. Correspondingly, the first MTLF receives the identifier of the first model from the second AnLF.

[0141] Exemplarily, the second AnLF sends a model request message to the first MTLF, where the model request message includes an identifier of the first model.

[0142] The model request message may be a model provision subscription (Nnwdaf_MLModelProvision_Subscribe) message.

[0143] Exemplarily, the second AnLF sends the identifier of the first model to the first MTLF corresponding to the identifier of the first MTLF according to the identifier of the first MTLF in the analysis context.

[0144] Step 230: The first MTLF determines first information according to the identifier of the first model.

[0145] Exemplarily, the first MTLF determines whether the first model can be provided to the second AnLF. For example, the first MTLF may index the context in which the first model is used based on the identifier of the first model and perform analysis and determination. For example, the first MTLF may determine whether the region of the first model has changed. If the first MTLF determines that the first model can be provided to the second AnLF, the first information is determined based on the identifier of the first model. If the first MTLF determines that the first model cannot be provided to the second AnLF, the first MTLF may return a rejection message or return a new model to the second AnLF.

[0146] Step 240: The first MTLF sends the first information to the second AnLF. Correspondingly, the second AnLF receives the first information from the first MTLF.

[0147] For the specific content of the first information, please refer to the relevant description in the above step 210.

[0148] Step 250: The second AnLF obtains the first model according to the first information.

[0149] For example, the second AnLF may obtain the first model according to the URL in the first information. Alternatively, the second AnLF may send a model acquisition request to the ADRF identified by the ADRFID in the first information, and the ADRF may send the first model to the first AnLF.

[0150] Using the above method, the analysis context obtained by the second AnLF includes the identifier of the first model and the identifier of the first MTLF, instead of directly including the first information. The second AnLF can obtain the first information from the first MTLF based on the identifier of the first model and the identifier of the first MTLF, so that the second AnLF can obtain the model used by the first AnLF network element and improve the security of model acquisition.

[0151] The embodiment shown in Figure 2 is described below in conjunction with Figures 3 and 4. In the following, the analysis function network element is AnLF, the model training function network element is MTLF, and the network storage function network element is NRF.

[0152] As shown in FIG3 , the process in which the service consuming network element determines that a target AnLF needs to be selected and triggers the target AnLF to send an analysis context transfer request to the first AnLF is as follows:

[0153] Step 301: A service consuming network element sends a first analysis subscription message to a first AnLF, wherein the first analysis subscription message includes an analysis identifier.

[0154] Exemplarily, the service consumption network element requests the first AnLF to provide it with the service corresponding to the analysis identifier through the first analysis subscription message. For example, the service consumption network element can be AMF, SMF or other core network elements.

[0155] Exemplarily, the analysis subscription message may be Nnwdaf_AnalyticsSubscription_Subscribe.

[0156] Step 302: The first AnLF sends a model request message to the first MTLF, wherein the model request message includes an analysis identifier.

[0157] Exemplarily, the model request message is a model provision subscription (Nnwdaf_MLModelProvision_Subscribe) message.

[0158] In one possible implementation, the first AnLF may obtain the first MTLF through the network element discovery process. Exemplarily, the first AnLF sends an NF discovery message 1 to the NRF. The NF discovery message 1 includes an analysis identifier. For example, the NF discovery message may be Nnrf_NF Discovery. The NF discovery message 1 is used to discover the MTLF, or to discover the NWDAF of the included MTLF. The NRF determines the first MTLF based on the analysis identifier in the NF discovery message 1. The NRF sends an NF discovery response message 1 to the first AnLF. The NF discovery response message 1 includes information about the first MTLF, wherein the information about the first MTLF may include at least one of the identifier of the first MTLF, the analysis identifier, and the first interoperability identifier. The first interoperability identifier is the interoperability identifier corresponding to the analysis identifier of the first MTLF or the interoperability identifier of the first MTLF. For example, the information of the first MTLF is the NF information (profile) of the first MTLF.

[0159] It is understood that the NRF can determine one or more MTLFs based on the analysis identifier in the NF Discovery Message 1. In this case, the NF Discovery Response Message 1 can include information about the one or more MTLFs. The first MTLF can be understood as any one of the one or more MTLFs. The following description only uses the first MTLF as an example.

[0160] Step 303: The first MTLF sends the identifier of the first model to the first AnLF.

[0161] Exemplarily, the first MTLF determines the first model according to the analysis identifier in the model request message. The first model is used to provide a service corresponding to the analysis identifier.

[0162] In one possible implementation, the first MTLF may also send at least one of a subscription correlation ID, the first information, and the first interoperability identifier to the first AnLF. For example, the subscription correlation ID is subscription correlation ID 1. For a description of the first information, refer to step 210 above. Each of the above information may be carried in one or more messages, which is not limited in this application.

[0163] It can be understood that the first MTLF is the producer of the model corresponding to the identifier of the first model.

[0164] It can also be understood that the first MTLF is the provider of the model corresponding to the identifier of the first model.

[0165] It can also be understood that the first MTLF is the provider of the first information of the model corresponding to the identifier of the first model.

[0166] It can also be understood that the first MTLF provides the first model and / or information of the first model to the first AnLF.

[0167] It can also be understood that the first MTLF provides the first model and / or the information of the first model to the first AnLF, and the first model and / or the information of the first model are used to provide the analysis service corresponding to the analysis identifier.

[0168] The model subscription association corresponding to the subscription association identifier and the analysis identifier is used to identify the model subscription between the first AnLF and the first MTLF. In addition, the first MTLF stores the corresponding relationship between the subscription association identifier and the first information.

[0169] Step 304: The first AnLF uses the first model to provide the service consuming network element with the service corresponding to the analysis identifier.

[0170] Exemplarily, the first AnLF obtains the first model based on the first information, and uses the first model to provide the service corresponding to the analysis identifier for the service consumption network element. One possible scenario is that the first AnLF obtains the model based on the first information, for example, through the URL of the model in the first information, for example, through the ADRF in the first information, the first AnLF obtains the URL of the first model from the ADRF, and then obtains the first model through the URL. The above situations can all be understood as the first AnLF obtaining the first model from the first MTLF. Alternatively, it can be understood as the first AnLF obtaining information about the first model from the first MTLF.

[0171] It can be understood that the first AnLF obtains the first model from the first MTLF. Alternatively, it can be understood that the first AnLF obtains information about the first model from the first MTLF.

[0172] It can also be understood that the first AnLF obtains information about the first model for analysis from the first MTLF. Alternatively, it can be understood that the first AnLF obtains the first model for analysis from the first MTLF. Alternatively, it can be understood that the first AnLF obtains the first model and / or information about the first model for analysis to identify the corresponding analysis service.

[0173] It can also be understood that the first AnLF obtains the first model from the first MTLF, and uses the first model to provide a service corresponding to the analysis identifier.

[0174] Step 305: The first AnLF sends an analysis context identifier, for example, subscription correlation ID 2, to the service consuming network element.

[0175] The analysis subscription association corresponding to the analysis context identifier and the analysis identifier is used to identify the analysis subscription between the first AnLF and the service consumption network element. In addition, the first AnLF stores the corresponding relationship (or association relationship) between the analysis context identifier and at least one of the identifier of the first model, the subscription association identifier, the first information, and the identifier of the first MTLF.

[0176] Step 306: The service consuming network element determines and selects the target AnLF.

[0177] For example, the service consuming network element may determine the target AnLF based on internal logic or external trigger conditions. For example, the service consuming network element starts requesting related analysis, or receives a stop subscription request for an existing analysis, and then selects a new AnLF to continue serving it.

[0178] In a possible implementation, the service consuming network element may determine the target AnLF through a network element discovery process.

[0179] Exemplarily, the service-consuming network element sends an NF discovery message 2 to the NRF. NF discovery message 2 is used to discover an AnLF, or to discover the NWDAF of the included AnLF. The NRF determines one or more AnLFs based on NF discovery message 2. The NRF sends an NF discovery response message 2 to the service-consuming network element. NF discovery response message 2 includes information about the one or more AnLFs. The service-consuming network element determines a target AnLF based on the information about the one or more AnLFs. The following description uses the example of the target AnLF being the second AnLF, where the second AnLF is one of the one or more AnLFs.

[0180] Step 307: The service consuming network element sends a second analysis subscription message to the second AnLF, wherein the second analysis subscription message includes an analysis identifier.

[0181] Exemplarily, the second analysis subscription message further includes analysis subscription information, wherein the analysis subscription information includes at least one of an identifier of the first AnLF, SUPI, analysis filter information of UE-related analysis, and an analysis context identifier.

[0182] Step 308: The second AnLF sends an analysis context transfer request to the first AnLF.

[0183] Exemplarily, the second AnLF determines the first AnLF according to the analysis subscription information, and the analysis context transfer request includes an analysis context identifier.

[0184] Step 309: The first AnLF sends an analysis context to the second AnLF, where the analysis context includes the identifier of the first model and the identifier of the first MTLF.

[0185] Exemplarily, the analysis context identifier has a corresponding relationship with the identifier of the first model and the identifier of the first MTLF. The first AnLF determines the analysis context corresponding to the analysis context identifier according to the analysis context identifier, and the analysis context includes the identifier of the first model and the identifier of the first MTLF.

[0186] In one possible implementation, before the first AnLF sends the analysis context to the second AnLF, the analysis context transfer request may optionally also include the manufacturer's identifier of the second AnLF. Furthermore, the first AnLF may determine whether the manufacturer's identifier of the second AnLF belongs to the first interoperability identifier based on the first interoperability identifier, or may be described as determining whether the first interoperability identifier includes the manufacturer's identifier of the second AnLF. That is, as can be seen from the above, the first interoperability identifier includes a list of manufacturer identifiers, and the first AnLF determines whether the manufacturer's identifier of the second AnLF belongs to the list of manufacturer identifiers. The first AnLF may obtain the first interoperability identifier from the first MTLF (see step 303) or from the NRF (see step 302). In one possible implementation, before the first AnLF sends the analysis context to the second AnLF, the first AnLF may also send a first request message to the first MTLF, the first request message being used to request the first MTLF to agree that the first AnLF provide the identifier of the first model to the second AnLF. Furthermore, the first MTLF sends a first response message to the first AnLF, the first response message indicating whether the first AnLF agrees to provide the identifier of the first model to the second AnLF. For example, if the first MTLF agrees that the first AnLF provides the second AnLF with the identifier of the first model, a first response message is sent to the first AnLF, where the first response message indicates that the first AnLF agrees to provide the second AnLF with the identifier of the first model. If the first MTLF disagrees that the first AnLF provides the second AnLF with the identifier of the first model, a first response message is sent to the first AnLF, where the first response message indicates that the first AnLF disagrees to provide the second AnLF with the identifier of the first model. This application does not limit the specific method of how the first MTLF determines whether to agree that the first AnLF provides the second AnLF with the identifier of the first model.

[0187] The first request message may also be described as an identifier for requesting permission for the first AnLF to provide the second AnLF with the first model, or an identifier for requesting authorization for the first AnLF to provide the second AnLF with the first model.

[0188] Exemplarily, the first request message may include at least one of a subscription association identifier, an identifier of the first model, an identifier of the second AnLF, or an identifier of the manufacturer of the second AnLF. If the first request message includes the identifier of the manufacturer of the second AnLF, the first MTLF may determine whether the identifier of the manufacturer of the second AnLF belongs to the first interoperability identifier. If the identifier of the manufacturer of the second AnLF belongs to the first interoperability identifier, the first MTLF may agree to allow the first AnLF to provide the identifier of the first model to the second AnLF; otherwise, the first MTLF may not agree to allow the first AnLF to provide the identifier of the first model to the second AnLF.

[0189] Step 310: The second AnLF sends the identifier of the first model to the first MTLF.

[0190] Exemplarily, the second AnLF sends a model provision subscription message to the first MTLF, where the model provision subscription message includes an identifier of the first model.

[0191] Step 311: The first MTLF determines first information according to the identifier of the first model.

[0192] Step 312: The first MTLF sends the first information to the second AnLF.

[0193] Step 313: The second AnLF obtains the first model according to the first information.

[0194] Steps 308 to 313 may refer to the above-mentioned steps 200 to 250 and will not be repeated here.

[0195] As shown in FIG4 , the process in which the first AnLF determines to select the target AnLF and triggers the target AnLF to send an analysis context transfer request to the first AnLF is as follows:

[0196] Steps 401 to 405 may refer to the above-mentioned steps 301 to 305 .

[0197] Step 406: The first AnLF determines that a target AnLF needs to be selected.

[0198] For example, if the first AnLF determines that it is in an overload state, or is close to or exceeds the service uptime according to the network element state, or the first AnLF is ready to shut down and stop providing external services, the first AnLF determines to select a target AnLF.

[0199] In a possible implementation manner, the first AnLF may determine the target AnLF through a network element discovery process.

[0200] Exemplarily, the first AnLF sends an NF Discovery Message 2 to the NRF. NF Discovery Message 2 is used to discover the AnLF, or to discover the NWDAF of the AnLF. The NRF determines one or more AnLFs based on NF Discovery Message 2. The NRF sends an NF Discovery Response Message 2 to the first AnLF. NF Discovery Response Message 2 includes information about one or more AnLFs. The first AnLF determines a target AnLF based on the information about the one or more AnLFs. The following description uses the second AnLF as an example, where the target AnLF is one of the one or more AnLFs.

[0201] Step 407: The first AnLF sends an analysis subscription transfer request to the second AnLF.

[0202] Exemplarily, analyzing the subscription transfer request includes analyzing subscription information, where the analyzing subscription information includes at least one of an identifier of the first AnLF, a SUPI, analysis filter information of UE-related analysis, and an analysis context identifier.

[0203] Steps 408 to 413 may refer to the above-mentioned steps 308 to 313 .

[0204] As shown in Figures 3 and 4 above, the service consumption network element or the first AnLF can determine and select the target AnLF, thereby triggering the target AnLF to send an analysis context transfer request to the first AnLF. The following embodiments are described only by taking the example of the service consumption network element determining and selecting the target AnLF and then triggering the second AnLF to send an analysis context transfer request to the first AnLF. It is understandable that the following embodiments are also applicable to the scenario where the first AnLF determines and selects the target AnLF and then triggers the second AnLF to send an analysis context transfer request to the first AnLF.

[0205] The present application also provides a communication method, as shown in FIG5 , which includes:

[0206] Steps 501 to 507 refer to the above-mentioned steps 301 to 307.

[0207] Step 508: The second AnLF sends an analysis context transfer request to the first AnLF.

[0208] Illustratively, the analysis context transfer request includes an analysis context identifier.

[0209] Step 509: The first AnLF sends a second request message to the first MTLF, where the second request message is used to request the MTLF to agree that the first AnLF provides the first information to the second AnLF.

[0210] The second request message may also be described as being used to request permission for the first AnLF to provide the first information to the second AnLF, or to request authorization for the first AnLF to provide the first information to the second AnLF.

[0211] Alternatively, the second request message can also be described as being used to request the MTLF to agree that the first AnLF provides the first model for the second AnLF, to request permission for the first AnLF to provide the first model for the second AnLF, or to request authorization for the first AnLF to provide the first model for the second AnLF.

[0212] Exemplarily, the analysis context identifier has a corresponding relationship with the identifier of the first model, the identifier of the first MTLF and the first information, and the first AnLF determines the identifier of the first model and the identifier of the first MTLF corresponding to the analysis context identifier based on the analysis context identifier, and determines that the analysis context corresponding to the analysis context identifier includes the first information. The first information is associated with the first model. The first information may include an ML model file address (for example, a URL or FQDN), or an ADRFID or ADRF set D. When the ML model information includes an ADRFID or ADRF set ID, the first information may also include a storage transaction identifier. Optionally, the first information may include an identifier of the first model. The first information may also include other content, which is not limited in this application. It is understandable that part of the content included in the first information can be used to obtain the first model, and the first information also includes other content, for example, relevant information for describing the first model, etc.

[0213] It can also be understood that the first AnLF does not directly provide the first information to the second AnLF, or it can be understood that before the first AnLF sends the first information to the second AnLF, it needs to obtain permission or authorization from the first MTLF.

[0214] Exemplarily, the second request message may include at least one of a subscription association identifier, an identifier of the first model, an identifier of the second AnLF, or an identifier of a manufacturer of the second AnLF.

[0215] Step 510: The first MTLF sends a second response message to the first AnLF, where the first response message indicates that the first AnLF agrees to provide the first information to the second AnLF.

[0216] For example, if the first MTLF agrees that the first AnLF provides the first information to the second AnLF, a second response message is sent to the first AnLF, where the second response message indicates that the first AnLF agrees to provide the first information to the second AnLF. If the first MTLF disagrees that the first AnLF provides the first information to the second AnLF, the second response message indicates that the first AnLF disagrees to provide the first information to the second AnLF. This application does not limit how the first MTLF determines whether to agree that the first AnLF provides the first information to the second AnLF. The following is only explained using the example of the second response message indicating that the first AnLF agrees to provide the first information to the second AnLF.

[0217] Step 511: The first AnLF sends an analysis context to the second AnLF, wherein the analysis context includes the first information and / or the model file of the first model.

[0218] Optionally, step 512: the second AnLF obtains the first model according to the first information.

[0219] By adopting the above method, the first MTLF authorizes the first AnLF to provide the first information, and the analysis context sent by the first AnLF to the second AnLF may include the first information, so that the second AnLF can obtain the model used by the first AnLF network element and improve the security of model acquisition.

[0220] The present application also provides a communication method, as shown in FIG6 , which includes:

[0221] Steps 601 to 607 refer to the above-mentioned steps 301 to 307.

[0222] Step 608: The second AnLF sends an analysis context transfer request to the first AnLF.

[0223] Illustratively, the analysis context transfer request includes an analysis context identifier.

[0224] Step 609: The first AnLF sends an analysis context to the second AnLF, wherein the analysis context includes an association identifier and an identifier of the first MTLF. The association identifier in this case is a subscription association identifier.

[0225] Exemplarily, the analysis context identifier has a corresponding relationship with the subscription association identifier and the identifier of the first MTLF, and the first AnLF determines the analysis context corresponding to the analysis context identifier according to the analysis context identifier, wherein the analysis context includes the subscription association identifier and the identifier of the first MTLF.

[0226] As can be seen from the above step 305, the first AnLF stores the correspondence between the analysis context identifier and the subscription association identifier. Therefore, the subscription association identifier can be determined according to the analysis context identifier.

[0227] Step 610: The second AnLF sends a subscription association identifier to the first MTLF.

[0228] Step 611: The first MTLF determines first information according to the subscription association identifier.

[0229] As can be seen from the above step 303, the first MTLF stores the correspondence between the subscription association identifier and the first information. Therefore, the first MTLF can determine the first information according to the subscription association identifier.

[0230] Step 612: The first MTLF sends the first information to the second AnLF.

[0231] Step 613: The second AnLF obtains the first model according to the first information.

[0232] Using the above method, the second AnLF obtains the subscription association identifier and the identifier of the first MTLF by analyzing the context, instead of directly obtaining the first information. The second AnLF can obtain the first information from the first MTLF based on the subscription association identifier and the information of the first MTLF, so that the second AnLF can obtain the model used by the first AnLF network element and improve the security of model acquisition.

[0233] The present application also provides a communication method, as shown in FIG7 , which includes:

[0234] Steps 701 to 707 refer to the above-mentioned steps 301 to 307.

[0235] Step 708: The second AnLF sends an analysis context transfer request to the first AnLF.

[0236] Illustratively, the analysis context transfer request includes an analysis context identifier.

[0237] Step 709: The first AnLF sends a third request message to the first MTLF, where the third request message includes the identifier of the first model.

[0238] The third request message is used to request the first MTLF to allocate an identifier associated with the first model.

[0239] Exemplarily, the analysis context identifier has a corresponding relationship with the identifier of the first model and the identifier of the first MTLF, and the first AnLF determines the identifier of the first model and the identifier of the first MTLF corresponding to the analysis context identifier according to the analysis context identifier.

[0240] Step 710: The first MTLF sends a third response message to the first AnLF.

[0241] Exemplarily, the first MTLF generates an association identifier for the first information, and saves a correspondence between the association identifier and the first information.

[0242] The third response message includes the association identifier and the identifier of the first MTLF. The association identifier in this case is the association identifier associated with the first information, which can also be called a model association identifier or a model information association identifier. The following description takes the model association identifier as an example.

[0243] Step 711: The first AnLF sends an analysis context to the second AnLF, wherein the analysis context includes a model association identifier and an identifier of the first MTLF.

[0244] Step 712: The second AnLF sends the model association identifier to the first MTLF.

[0245] Step 713: The first MTLF determines first information according to the model association identifier.

[0246] As can be seen from the above step 710, the first MTLF stores the correspondence between the model association identifier and the first model. Therefore, the first MTLF can determine the first information according to the model association identifier.

[0247] Step 714: The first MTLF sends the first information to the second AnLF.

[0248] Step 715: The second AnLF obtains the first model according to the first information.

[0249] Using the above method, the second AnLF obtains the model association identifier and the identifier of the first MTLF by analyzing the context, instead of directly obtaining the first information. The second AnLF can obtain the first information from the first MTLF based on the model association identifier and the information of the first MTLF, so that the second AnLF can obtain the model used by the first AnLF network element and improve the security of model acquisition.

[0250] The present application also provides a communication method, as shown in FIG8 , which includes:

[0251] Steps 801 to 807 refer to the above-mentioned steps 301 to 307.

[0252] Step 808: The second AnLF sends an analysis context transfer request to the first AnLF.

[0253] Exemplarily, the analysis context transfer request includes an analysis context identifier and a model receiving address.

[0254] Step 809: The first AnLF sends a fourth request message to the first MTLF. The fourth request message includes the model receiving address and the identifier of the first model.

[0255] Exemplarily, the analysis context identifier has a corresponding relationship with the identifier of the first model and the identifier of the first MTLF, and the first AnLF determines the identifier of the first model and the identifier of the first MTLF corresponding to the analysis context identifier according to the analysis context identifier.

[0256] The fourth request message is used to request the first MTLF to provide the first information according to the model receiving address.

[0257] Step 810: The model training function network element determines first information according to the identifier of the first model.

[0258] Step 811: The first MTLF provides first information according to the model receiving address.

[0259] Step 812: The second analysis function network element obtains the first information according to the model receiving address.

[0260] Step 813: The second analysis function network element obtains the first model according to the first information.

[0261] By adopting the above method, the second AnLF provides the model receiving address, and the first MTLF provides the first information according to the model receiving address, so that the second AnLF can obtain the model used by the first AnLF network element and improve the security of model acquisition.

[0262] It is understandable that in order to implement the functions in the above embodiments, the first analysis function network element, the model training function network element, and the second analysis function network element include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and method steps of each example described in the embodiments disclosed in this application, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0263] Figures 9 and 10 are schematic diagrams of the structures of possible communication devices provided in embodiments of the present application. These communication devices can be used to implement the functions of the first analysis function network element, the model training function network element, or the second analysis function network element in the above method embodiments, thereby also achieving the beneficial effects possessed by the above method embodiments.

[0264] As shown in Figure 9, the communication device 900 includes a processing unit 910 and a transceiver unit 920. The communication device 900 is used to implement the functions of the first analysis function network element, the model training function network element or the second analysis function network element in the above method embodiment.

[0265] When the communication device 900 is used to implement the function of the first analysis function network element in the above method embodiment:

[0266] The processing unit 910 calls the transceiver unit 920 to execute: receiving an analysis context transfer request from the second analysis function network element; sending an analysis context to the second analysis function network element, where the analysis context includes the identifier of the first model and the identifier of the model training function network element.

[0267] In a possible implementation, the transceiver unit 920 is used to receive first information from the model training function network element, where the first information is associated with the first model.

[0268] In a possible implementation, the first information includes an identifier of the model training function network element.

[0269] In one possible implementation, before receiving an analysis context transfer request from a second analysis function network element, the processing unit 910 is used to use the first model to provide a service corresponding to the analysis identifier; the transceiver unit 920 is used to send an analysis subscription transfer request to the second analysis function network element, and the analysis subscription transfer request includes the analysis identifier.

[0270] In one possible implementation, the analysis context transfer request includes the identifier of the manufacturer of the second analysis function network element; before sending the analysis context to the second analysis function network element, the transceiver unit 920 is used to obtain a first interoperability identifier, where the first interoperability identifier is the interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is the interoperability identifier of the model training function network element; the processing unit 910 is used to determine that the first interoperability identifier includes the identifier of the manufacturer of the second analysis function network element.

[0271] In a possible implementation, the transceiver unit 920 is configured to obtain the first interoperability identifier from the model training function network element or the network storage function network element.

[0272] In one possible implementation, before receiving an analysis context transfer request from a second analysis function network element, the transceiver unit 920 is used to send a model request message to the model training function network element, where the model request message includes the analysis identifier; and receive the identifier of the first model from the model training function network element.

[0273] In one possible implementation, before sending the analysis context to the second analysis function network element, the transceiver unit 920 is used to send a first request message to the model training function network element, wherein the first request message is used to request the model training function network element to agree that the first analysis function network element provides the second analysis function network element with the identifier of the first model; and receive a first response message from the model training function network element, wherein the first response message indicates that the first analysis function network element agrees to provide the second analysis function network element with the identifier of the first model.

[0274] When the communication device 900 is used to implement the function of the second analysis function network element in the above method embodiment:

[0275] The processing unit 910 calls the transceiver unit 920 to execute: sending an analysis context transfer request to the first analysis function network element; receiving an analysis context from the first analysis function network element, the analysis context including the identifier of the first model and the identifier of the model training function network element; sending the identifier of the first model to the model training function network element; receiving first information from the model training function network element, the first information being associated with the first model.

[0276] In a possible implementation, the first information includes an identifier of the model training function network element.

[0277] In a possible implementation, the analysis context transfer request includes an identifier of a manufacturer of the second analysis function network element.

[0278] In one possible implementation, before sending an analysis context transfer request to the first analysis function network element, the transceiver unit 920 is used to receive an analysis subscription transfer request from the first analysis function network element, and the analysis subscription transfer request includes analysis subscription information; the second analysis function network element determines the first analysis function network element based on the analysis subscription information.

[0279] In one possible implementation, before the second analysis function network element sends an analysis context transfer request to the first analysis function network element, the second analysis function network element receives an analysis subscription request from a service consumption network element; the analysis subscription request includes analysis subscription information; and the processing unit 910 is used to determine the first analysis function network element based on the analysis subscription information.

[0280] When the communication device 900 is used to implement the function of the model training function network element in the above method embodiment:

[0281] The transceiver unit 920 is used to receive the identifier of the first model from the second analysis function network element; the processing unit 910 is used to determine the first information based on the identifier of the first model, and the first information is associated with the first model; the transceiver unit 920 is used to send the first information to the second analysis function network element.

[0282] In one possible implementation, before receiving the identifier of the first model from the second analysis function network element, the transceiver unit 920 is used to receive a first request message from the first analysis function network element, where the first request message is used to request the model training function network element to agree that the first analysis function network element provides the identifier of the first model to the second analysis function network element; and send a first response message to the first analysis function network element, where the first response message indicates that the first analysis function network element agrees to provide the identifier of the first model to the second analysis function network element.

[0283] In one possible implementation, the transceiver unit 920 is used to receive a model request message from the first analysis function network element, where the model request message includes an analysis identifier; and send the identifier of the first model to the first analysis function network element, where the first model is used to provide a service corresponding to the analysis identifier.

[0284] In one possible implementation, the transceiver unit 920 is used to send a first interoperability identifier to the first analysis function network element, where the first interoperability identifier is the interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is the interoperability identifier of the model training function network element.

[0285] In one possible implementation, the transceiver unit 920 is configured to send first information to the first analysis function network element before receiving an identifier of the first model from the second analysis function network element, where the first information is associated with the first model.

[0286] In a possible implementation, the first information includes an identifier of the model training function network element.

[0287] A more detailed description of the processing unit 910 and the transceiver unit 920 can be directly obtained by referring to the relevant description in the above method embodiment, and will not be repeated here.

[0288] As shown in Figure 10, communication device 1000 includes a processor 1010 and an interface circuit 1020. Processor 1010 and interface circuit 1020 are coupled to each other. It will be appreciated that interface circuit 1020 may be a transceiver or an input / output interface. Optionally, communication device 1000 may further include a memory 1030 for storing instructions executed by processor 1010, input data required by processor 1010 to execute instructions, or data generated by processor 1010 after executing instructions.

[0289] When the communication device 1000 is used to implement the method shown in FIG. 5 , the processor 1010 is used to implement the functions of the processing unit 910 , and the interface circuit 1020 is used to implement the functions of the transceiver unit 920 .

[0290] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0291] The present application provides another example of a device, which includes at least one processor and at least one memory, the at least one processor and the at least one memory being coupled together, the at least one memory being used to store instructions. When the instructions are executed by the at least one processor, the communication device executes the method in the above-described embodiment. For example, as shown in FIG10 , a communication device 1000 includes a processor 1010 and a memory 1030. The processor 1010 and the memory 1030 are coupled together, and the memory 1030 stores instructions. When the instructions stored in the memory 1030 are executed by the processor 1010, the communication device 1000 executes the method executed by each network element in the above-described embodiment.

[0292] The method steps in the embodiments of the present application can be implemented in hardware or in software instructions that can be executed by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disk, mobile hard disk, CD-ROM or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. The storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in the above-mentioned network element. The processor and the storage medium can also exist in the above-mentioned network element as discrete components.

[0293] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are performed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, or other programmable device. The computer program or instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a digital video disk; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage media.

[0294] In the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0295] In this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In the text description of this application, the character " / " generally indicates that the previous and next associated objects are in an "or" relationship; in the formula of this application, the character " / " indicates that the previous and next associated objects are in a "division" relationship. "Including at least one of A, B and C" can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B and C.

[0296] It is understood that the various numbers used in the embodiments of this application are merely for ease of description and are not intended to limit the scope of the embodiments of this application. The order of the sequence numbers of the above-mentioned processes does not necessarily imply a specific order of execution; the order of execution of the processes should be determined by their functions and inherent logic.

Claims

1. A communication method, characterized in that: The method includes: The first analysis function network element receives an analysis context transfer request from the second analysis function network element; The first analysis function network element sends an analysis context to the second analysis function network element, where the analysis context includes an identifier of the first model and an identifier of the model training function network element.

2. The method according to claim 1, characterized in that Also includes: The first analysis function network element receives first information from the model training function network element, where the first information is associated with the first model.

3. The method according to claim 2, characterized in that The first information includes an identifier of the model training function network element.

4. The method according to any one of claims 1 to 3, characterized in that: The model training functional network element is the producer of the first model.

5. The method according to any one of claims 1 to 4, characterized in that: Before the first analysis function network element receives the analysis context transfer request from the second analysis function network element, the method further includes: The first analysis function network element provides a service corresponding to the analysis identifier using the first model; The first analysis function network element sends an analysis subscription transfer request to the second analysis function network element, where the analysis subscription transfer request includes the analysis identifier.

6. The method according to claim 5, characterized in that Before the first analysis function network element sends the analysis context to the second analysis function network element, the method further includes: The first analysis function network element obtains a first interoperability identifier, where the first interoperability identifier is an interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is an interoperability identifier of the model training function network element; The first analysis function network element determines that the first interoperability identifier includes the identifier of the manufacturer of the second analysis function network element.

7. The method according to claim 6, characterized in that The analysis context transfer request includes an identifier of a manufacturer of the second analysis function network element.

8. The method according to claim 6, characterized in that The first analysis function network element obtains the first interoperability identifier, including: The first analysis function network element obtains the first interoperability identifier from the model training function network element or the network storage function network element.

9. The method according to claim 5 or 6, characterized in that Before the first analysis function network element receives the analysis context transfer request from the second analysis function network element, the method further includes: The first analysis function network element sends a model request message to the model training function network element, where the model request message includes the analysis identifier; The first analysis function network element receives an identifier of the first model from the model training function network element.

10. The method according to any one of claims 1 to 9, characterized in that: Before the first analysis function network element sends the analysis context to the second analysis function network element, the method further includes: The first analysis function network element sends a first request message to the model training function network element, where the first request message is used to request the model training function network element to agree that the first analysis function network element provides the second analysis function network element with an identifier of the first model; The first analysis function network element receives a first response message from the model training function network element, and the first response message indicates that the first analysis function network element agrees to provide the identifier of the first model to the second analysis function network element.

11. A communication method, characterized in that: The method includes: The second analysis function network element sends an analysis context transfer request to the first analysis function network element; The second analysis function network element receives the analysis context from the first analysis function network element, where the analysis context includes an identifier of the first model and an identifier of the model training function network element; The second analysis function network element sends the identifier of the first model to the model training function network element; The second analysis function network element receives first information from the model training function network element, where the first information is associated with the first model.

12. The method according to claim 11, characterized in that The first information includes an identifier of the model training function network element.

13. The method according to claim 11 or 12, characterized in that The analysis context transfer request includes an identifier of a manufacturer of the second analysis function network element.

14. The method according to any one of claims 11 to 13, characterized in that: Before the second analysis function network element sends the analysis context transfer request to the first analysis function network element, the method further includes: The second analysis function network element receives an analysis subscription transfer request from the first analysis function network element, wherein the analysis subscription transfer request includes analysis subscription information; The second analysis function network element determines the first analysis function network element according to the analysis subscription information.

15. The method according to any one of claims 11 to 13, characterized in that: Before the second analysis function network element sends the analysis context transfer request to the first analysis function network element, the method further includes: The second analysis function network element receives an analysis subscription request from a service consumption network element; the analysis subscription request includes analysis subscription information; The second analysis function network element determines the first analysis function network element according to the analysis subscription information.

16. A communication method, characterized in that: The method includes: The model training function network element receives the identifier of the first model from the second analysis function network element; The model training function network element determines first information according to the identifier of the first model, where the first information is associated with the first model; The model training function network element sends the first information to the second analysis function network element.

17. The method according to claim 16, characterized in that Before the model training function network element receives the identifier of the first model from the second analysis function network element, the method further includes: The model training function network element receives a first request message from the first analysis function network element, where the first request message is used to request the model training function network element to agree that the first analysis function network element provides the second analysis function network element with an identifier of the first model; The model training function network element sends a first response message to the first analysis function network element, and the first response message indicates that it agrees with the first analysis function network element to provide the identifier of the first model to the second analysis function network element.

18. The method according to claim 16 or 17, characterized in that Also includes: The model training function network element receives a model request message from the first analysis function network element, where the model request message includes an analysis identifier; The model training function network element sends the identifier of the first model to the first analysis function network element, and the first model is used to provide a service corresponding to the analysis identifier.

19. The method according to any one of claims 16 to 18, characterized in that: Before the model training function network element receives the identifier of the first model from the second analysis function network element, the method further includes: The model training function network element sends a first interoperability identifier to the first analysis function network element, where the first interoperability identifier is the interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is the interoperability identifier of the model training function network element.

20. The method according to any one of claims 16 to 19, characterized in that: Before the model training function network element receives the identifier of the first model from the second analysis function network element, the method further includes: The model training function network element sends the first information to the first analysis function network element, where the first information is associated with the first model.

21. The method according to any one of claims 16 to 20, characterized in that: The first information includes an identifier of the model training function network element.

22. A communication method, characterized in that: The method includes: The first analysis function network element receives an analysis context transfer request from the second analysis function network element; The first analysis function network element sends an analysis context to the second analysis function network element, where the analysis context includes an association identifier and an identifier of a model training function network element.

23. The method of claim 22, wherein: The association identifier corresponds to the first information, the model training function network element is used to provide the first information, and the first information is associated with the first model.

24. The method according to claim 22 or 23, characterized in that The method further comprises: The first analysis function network element sends a model request message to the model training function network element, where the model request message includes an analysis identifier; The first analysis function network element receives the identifier of the first model and the association identifier from the model training function network element, and the first model is used to provide the service corresponding to the analysis identifier.

25. The method according to claim 23 or 24, characterized in that After the first analysis function network element receives the analysis context transfer request from the second analysis function network element, the method further includes: The first analysis function network element sends a third request message to the model training function network element, and the third request message includes the first model The third request message is used to request the model training function network element to generate an identifier associated with the first information; The first analysis function network element receives a third response message from the model training function network element, and the third response message includes the association identifier.

26. The method according to any one of claims 23 to 25, characterized in that Before the first analysis function network element receives the analysis context transfer request from the second analysis function network element, the method further includes: The first analysis function network element provides a service corresponding to the analysis identifier using the first model; The first analysis function network element sends an analysis subscription transfer request to the second analysis function network element, where the analysis subscription transfer request includes the analysis identifier.

27. The method according to any one of claims 22 to 26, characterized in that Before the first analysis function network element sends the analysis context to the second analysis function network element, the method further includes: The first analysis function network element obtains a first interoperability identifier, where the first interoperability identifier is an interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is an interoperability identifier of the model training function network element; The first analysis function network element determines that the first interoperability identifier includes the identifier of the manufacturer of the second analysis function network element.

28. The method of claim 27, wherein: The analysis context transfer request includes an identifier of a manufacturer of the second analysis function network element.

29. The method of claim 27, wherein: The method further comprises: The first analysis function network element obtains the first interoperability identifier from the model training function network element or the network storage function network element.

30. A communication method, characterized in that: The method includes: The second analysis function network element sends an analysis context transfer request to the first analysis function network element; The second analysis function network element receives the analysis context from the first analysis function network element, where the analysis context includes an association identifier and an identifier of the model training function network element; The second analysis function network element sends the association identifier to the model training function network element; The second analysis function network element receives first information from the model training function network element, where the first information is associated with a first model.

31. The method of claim 30, wherein: The association identifier corresponds to the first information.

32. The method according to claim 30 or 31, characterized in that Before the second analysis function network element sends the analysis context transfer request to the first analysis function network element, the method further includes: The second analysis function network element receives an analysis subscription transfer request from the first analysis function network element, wherein the analysis subscription transfer request includes analysis subscription information; The second analysis function network element determines the first analysis function network element according to the analysis subscription information.

33. The method according to claim 30 or 31, characterized in that Before the second analysis function network element sends the analysis context transfer request to the first analysis function network element, the method further includes: The second analysis function network element receives an analysis subscription request from a service consumption network element; the analysis subscription request includes analysis subscription information; The second analysis function network element determines the first analysis function network element according to the analysis subscription information.

34. A communication method, characterized in that: The method includes: The model training function network element receives the association identifier from the second analysis function network element; The model training function network element determines first information according to the association identifier, where the first information is associated with the first model; The model training function network element sends the first information to the second analysis function network element.

35. The method of claim 34, wherein: Before the model training function network element receives the association identifier from the second analysis function network element, the method further includes: The model training function network element receives a third request message from the first analysis function network element, where the third request message includes an identifier of the first model; the third request message is used to request the model training function network element to generate an identifier associated with the first information; The model training function network element sends a third response message to the first analysis function network element, and the third response message includes the association identifier.

36. The method according to claim 34 or 35, characterized in that The method further comprises: The model training function network element receives a model request message from the first analysis function network element, where the model request message includes an analysis identifier; The model training function network element sends the identifier of the first model and the association identifier to the first analysis function network element, and the first A model is used to provide services corresponding to analysis identifiers.

37. The method according to any one of claims 34 to 36, characterized in that The method further comprises: The model training function network element sends a first interoperability identifier to the first analysis function network element, where the first interoperability identifier is the interoperability identifier corresponding to the analysis identifier of the model training function network element, or the first interoperability identifier is the interoperability identifier of the model training function network element.

38. A communication device, characterized in that: The method comprises a unit or a module for executing the method according to any one of claims 1 to 37.

39. A communication device, characterized in that: The communication device comprises at least one processor; the at least one processor is used to execute the method according to any one of claims 1 to 37.

40. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a program, and when the program is run on a device, the device is caused to perform the method according to any one of claims 1 to 37.

41. A computer program product, characterized in that The computer program product comprises a program or instructions, and when the program or instructions are executed by a device, the device is caused to perform the method according to any one of claims 1 to 37.

42. A communication system, characterized in that: The communication system includes a first analysis function network element and a second analysis function network element, wherein the first analysis function network element is used to execute the method according to any one of claims 1 to 10, and the second analysis function network element is used to execute the method according to any one of claims 11 to 15.

43. The communication system according to claim 42, characterized in that The communication system also includes a model training function network element, which is used to execute the method according to any one of claims 16 to 21.

44. A communication method, characterized in that: The method includes: The second analysis function network element sends an analysis context transfer request to the first analysis function network element; The first analysis function network element receives the analysis context transfer request from the second analysis function network element, and the first analysis function network element sends an analysis context to the second analysis function network element, where the analysis context includes an identifier of the first model and an identifier of the model training function network element; The second analysis function network element receives the analysis context from the first analysis function network element; The second analysis function network element sends the identifier of the first model to the model training function network element; The second analysis function network element receives first information from the model training function network element, where the first information is associated with the first model.

45. The method of claim 44, wherein: The method further comprises: The model training function network element receives the identifier of the first model from the second analysis function network element, and the model training function network element determines the first information according to the identifier of the first model; The model training function network element sends the first information to the second analysis function network element.

46. ​​A communication system, characterized in that: The communication system includes a first analysis function network element and a second analysis function network element, wherein the first analysis function network element is used to execute the method as described in any one of claims 22 to 29, and the second analysis function network element is used to execute the method as described in any one of claims 30 to 33.

47. The communication system according to claim 46, characterized in that The communication system also includes a model training function network element, which is used to execute the method described in any one of claims 34 to 37.

48. A communication method, characterized in that: The method includes: The second analysis function network element sends an analysis context transfer request to the first analysis function network element; The first analysis function network element receives the analysis context transfer request from the second analysis function network element, and the first analysis function network element sends an analysis context to the second analysis function network element, where the analysis context includes an association identifier and an identifier of a model training function network element; The second analysis function network element receives the analysis context from the first analysis function network element; The second analysis function network element sends the association identifier to the model training function network element; The second analysis function network element receives first information from the model training function network element, where the first information is associated with a first model.

49. The method of claim 48, wherein: The method further comprises: The model training function network element receives the association identifier from the second analysis function network element, and the model training function network element determines the first information according to the association identifier; The model training function network element sends the first information to the second analysis function network element.

Images