Communication method and apparatus

Abstract

A communication method and apparatus. The method comprises: a first network element sends a first message to a second network element, the first message comprising an analytic identifier, and the first message being used for requesting a model that provides a service corresponding to the analytic identifier; the first network element receives a second message from the second network element, the second message comprising a first identifier, information of M network elements, and information of a first model, the first identifier being associated with the analytic identifier, and the first identifier corresponding to at least two vertical federated learning models; and the M network elements use the at least two vertical federated learning models to provide the service, M being a positive integer, and the at least two vertical federated learning models comprising the first model. By using the above method, the first network element makes a request to the second network element for the model that provides the service corresponding to the analytic identifier, and when the second network element determines that the vertical federated learning models are to be used, the second network element sends the second message to the first network element, so that the first network element can, on the basis of content of the second message, initiate the use of the vertical federated learning models for the execution of an analytic task.

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 January 11, 2024, with application number 202410048093.9 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] Federated learning among multiple network data analytics function (NWDAF) elements is a machine learning technology used in core networks. It trains machine learning (ML) models across multiple distributed entities with local datasets, without exchanging or sharing those datasets. Compared to traditional centralized ML, this technology eliminates the need to upload all local datasets to a single server, thus addressing key issues such as data privacy, security, and access rights.

[0005] Federated learning can be categorized into three types based on the characteristics of the participating data sources: horizontal federated learning, vertical federated learning, and federated transfer learning. Currently, the 5G Core (5GC) only supports horizontal federated learning and the execution of analytical tasks using horizontal federated learning models. However, implementing analytical tasks using vertical federated learning models is a significant area of ​​concern. Summary of the Invention

[0006] The embodiments of the present application provide a communication method and apparatus for performing analysis tasks through a vertical federated learning model.

[0007] In a first aspect, the present application provides a communication method, the execution subject of the method can be a first network element or a chip inside the first network element. The method includes: the first network element sends a first message to the second network element; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the first network element receives a second message from the second network element, and the second message includes the first identifier, information of M network elements, and information of the first model; wherein the first identifier is associated with the analysis identifier, and the first identifier corresponds to at least two vertical federated learning models; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, the at least two vertical federated learning models include the first model, and the M network elements each correspond to the at least two vertical federated learning models.

[0008] Using the above method, the first network element requests the second network element to provide a model of the service corresponding to the analysis identifier. When the second network element determines to use the vertical federated learning model, the second network element sends the first identifier, information of M network elements and at least one item of information of the first model to the first network element. Then, the first network element can initiate the use of the vertical federated learning model to perform the analysis task based on the above information.

[0009] In one possible design, the first network element determines at least one network element based on the information of the M network elements; the first network element sends a third message to the at least one network element, the third message includes the first identifier, and the third message is used to request the vertical federated learning model corresponding to the first identifier to provide services.

[0010] Using the above design, the first network element can send a third message to at least one of the M network elements, that is, initiate an analysis task using the vertical federated learning model to at least one network element.

[0011] In one possible design, the first network element obtains a first intermediate result according to the first model; the first network element receives at least one intermediate result from the at least one network element, and the at least one network element corresponds one-to-one to the at least one intermediate result; the first network element determines an output according to the first intermediate result and the at least one intermediate result; and the first network element sends the output to the service consumption network element.

[0012] With the above design, the producer of the first model can be the main participant in the vertical federation task corresponding to the first identifier. Therefore, the first network element can collect various intermediate results and determine the output.

[0013] In one possible design, the first network element obtains a first intermediate result according to the first model; the first network element sends the first intermediate result to a third network element; the third network element is one of the at least one network element; the first network element receives the output from the third network element; and the first network element sends the output to the service consumption network element.

[0014] With this design, the producer of the first model can be a slave participant in the vertical federation task corresponding to the first identifier, while the producer of the model used by the third network element can be a master participant in the vertical federation task corresponding to the first identifier. Therefore, the first network element can send the first intermediate result to the third network element, which then determines the output.

[0015] In one possible design, before the first network element sends the first message to the second network element, the first network element receives a fourth message from the service consumption network element, and the fourth message includes information about the analysis identifier and / or the first object, wherein the first object corresponds to the analysis identifier; and the fourth message is used to request the service corresponding to the analysis identifier.

[0016] In one possible design, the third message also includes information about the first object.

[0017] In one possible design, the third message further includes an identifier of the first object in the vertical federation task corresponding to the first identifier;

[0018] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0019] With the above design, the first network element can convert the identifier of the first object into the identifier of the first object in the vertical federation task corresponding to the first identifier.

[0020] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, wherein the first mapping relationship is the identifier of the network entity identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity identifier in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier; if the information of the first object includes the network entity identifier of the first object, the first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the network entity identifier of the first object and the first mapping relationship; if the information of the first object includes the user entity identifier of the first object, the first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the user entity identifier of the first object and the second mapping relationship. Using the above design, the first network element can convert the network entity identifier or user entity identifier of the first object into the identifier of the first object in the vertical federation task corresponding to the first identifier, that is, the identifier of the first object in the vertical federation task.

[0021] In one possible design, the user entity identifier is a SUPI.

[0022] In one possible design, the second message also includes first indication information, wherein the first indication information indicates that the first model is a vertical federated learning model; or, the first indication information indicates that the model corresponding to the first identifier is a vertical federated learning model; or, the first indication information indicates that the task corresponding to the first identifier is a vertical federated task.

[0023] In one possible design, the information of the M network elements includes network entity identifiers of the M network elements, subscription association addresses of the M network elements, and at least one of role information of the M network elements.

[0024] In one possible design, the j-th network element is any one of the M network elements, and the role information of the j-th network element indicates the role of the producer of the j-th vertical federated learning model in the vertical federated task corresponding to the first identifier; wherein, the j-th network element is the user of the j-th vertical federated learning model, and at least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model, j is less than or equal to M, and j is a positive integer.

[0025] In a second aspect, the present application provides a communication method, which can be performed by a second network element or a chip inside the second network element. The method includes: the second network element receives a first message from the first network element; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the second network element sends a second message to the first network element, and the second message includes the first identifier, information of M network elements, and information of the first model; wherein the first identifier is associated with the analysis identifier, and the first identifier corresponds to at least two vertical federated learning models; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, the at least two vertical federated learning models include the first model, and the M network elements each correspond to the at least two vertical federated learning models.

[0026] Using the above method, the first network element requests the second network element to provide a model of the service corresponding to the analysis identifier. When the second network element determines to use the vertical federated learning model, the second network element sends the first identifier, information of M network elements and at least one item of information of the first model to the first network element. Then, the first network element can initiate the use of the vertical federated learning model to perform the analysis task based on the above information.

[0027] In one possible design, before the second network element sends the second message to the first network element, the second network element determines the first identifier, information of the M network elements and at least one of the information of the first model based on the analysis identifier.

[0028] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, wherein the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier.

[0029] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0030] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0031] In one possible design, the second message also includes first indication information, wherein the first indication information indicates that the first model is a vertical federated learning model; or, the first indication information indicates that the model corresponding to the first identifier is a vertical federated learning model; or, the first indication information indicates that the task corresponding to the first identifier is a vertical federated task.

[0032] In one possible design, the information of the M network elements includes network entity identifiers of the M network elements, subscription association addresses of the M network elements, and at least one of role information of the M network elements.

[0033] In one possible design, the j-th network element is any one of the M network elements, and the role information of the j-th network element indicates the role of the producer of the j-th vertical federated learning model in the vertical federated task corresponding to the first identifier; wherein, the j-th network element is the user of the j-th vertical federated learning model, and at least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model, j is less than or equal to M, and j is a positive integer.

[0034] In a third aspect, the present application provides a communication method, the execution subject of which may be a first network element or a chip inside the first network element. The method comprises: the first network element sends a first message to the second network element; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the first network element receives a second message from the second network element, the second message includes a second identifier and / or first indication information, the first indication information indicates that the model that provides the service corresponding to the analysis identifier is a vertical federated learning model, and the second identifier is used to identify the first message; the first network element sends a third message to the second network element, the third message is used to request a service corresponding to the analysis identifier, and the third message includes the second identifier.

[0035] Using the above method, the first network element requests the second network element to provide a model of the service corresponding to the analysis identifier. When the second network element determines to use the vertical federated learning model, the second network element sends a second identifier and / or a first indication information to the first network element. That is, the second network element does not provide the model information to the first network element, but uses the first indication information to notify the first network element that the model providing the service corresponding to the analysis identifier is a vertical federated learning model, and uses the second identifier to enable the second network element to request the service corresponding to the analysis identifier, that is, to initiate the use of the vertical federated learning model to perform the analysis task.

[0036] In one possible design, the first network element receives output from the second network element; the first network element sends the output to a service consuming network element.

[0037] In one possible design, before the first network element sends the first message to the second network element, the first network element receives a fourth message from the service consumption network element, and the fourth message includes information about the analysis identifier and / or the first object, wherein the first object corresponds to the analysis identifier; and the fourth message is used to request the service corresponding to the analysis identifier.

[0038] In one possible design, the third message also includes information about the first object.

[0039] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0040] With the above design, the first network element can convert the identifier of the first object into the identifier of the first object in the vertical federation task corresponding to the first identifier.

[0041] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, wherein the first mapping relationship is the identifier of the network entity identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity identifier in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier; if the information of the first object includes the network entity identifier of the first object, the first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the network entity identifier of the first object and the first mapping relationship; if the information of the first object includes the user entity identifier of the first object, the first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the user entity identifier of the first object and the second mapping relationship.

[0042] Using the above design, the first network element can convert the network entity identifier or user entity identifier of the first object into the identifier of the first object in the vertical federation task corresponding to the first identifier, that is, the identifier of the first object in the vertical federation task.

[0043] In a fourth aspect, the present application provides a communication method, the execution subject of the method may be a second network element or a chip inside the second network element. The method comprises: the second network element receives a first message from the first network element; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the second network element sends a second message to the first network element, the second message includes a second identifier and / or first indication information, the first indication information indicates that the model that provides the service corresponding to the analysis identifier is a vertical federated learning model, and the second identifier is used to identify the first message; the second network element receives a third message from the first network element, the third message is used to request the service corresponding to the analysis identifier, and the third message includes the second identifier.

[0044] Using the above method, the first network element requests the second network element to provide a model of the service corresponding to the analysis identifier. When the second network element determines to use the vertical federated learning model, the second network element sends a second identifier and / or a first indication information to the first network element. Then, the first network element can determine to use the vertical federated learning model based on the first indication information, and send a third message based on the second identifier, that is, initiate the use of the vertical federated learning model to perform the analysis task.

[0045] In one possible design, before the second network element sends the second message to the first network element, the second network element determines the information of the first model based on the analysis identifier; the second network element saves the correspondence between the second identifier and the information of the first model.

[0046] Using the above method, the second network element saves the correspondence between the second identifier and the information of the first model, and then can determine the information of the first model based on the second identifier in the third message, and provide the service corresponding to the analysis identifier based on the first model, that is, initiate the use of the vertical federated learning model to perform the analysis task.

[0047] In one possible design, when the second network element determines the information of the first model based on the analysis identifier, the second network element determines the information of the first model, the information of M network elements and the first identifier based on the analysis identifier; when the second network element saves the correspondence between the second identifier and the information of the first model, the second network element saves the correspondence between the second identifier and the information of the first model, the information of the M network elements and the first identifier; wherein, the first identifier is associated with the analysis identifier, and the first identifier corresponds to at least two vertical federated learning models; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, the at least two vertical federated learning models include the first model, and the M network elements each correspond to the at least two vertical federated learning models.

[0048] In one possible design, after the second network element receives the third message from the first network element, the second network element determines the information of the first model, the information of the M network elements and the first identifier based on the second identifier; the second network element determines at least one network element based on the information of the M network elements; the second network element sends a fifth message to the at least one network element, the fifth message including the first identifier, and the fifth message is used to request the vertical federated learning model corresponding to the first identifier to provide services; the second network element obtains a first intermediate result based on the first model; the second network element receives at least one intermediate result from the at least one network element, and the at least one network element corresponds one-to-one to the at least one intermediate result; the second network element determines the output based on the first intermediate result and the at least one intermediate result.

[0049] With the above design, the second network element is the main participant of the vertical federation task corresponding to the first identifier.

[0050] In one possible design, after the second network element receives the third message from the first network element, the second network element determines the information of the first model, the information of the M network elements and the first identifier based on the second identifier; the second network element determines at least one network element based on the information of the M network elements; the second network element sends a fifth message to the at least one network element, the fifth message includes the first identifier, and the third message is used to request the vertical federated learning model corresponding to the first identifier to provide services; the second network element obtains a first intermediate result based on the first model; the second network element sends the first intermediate result to the third network element; and the second network element receives the output from the third network element.

[0051] With the above design, the second network element is a slave-master participant of the vertical federation task corresponding to the first identifier. The producer of the model used by the third network element is a slave-master participant of the vertical federation task corresponding to the first identifier.

[0052] In one possible design, the second network element sends the output to the first network element.

[0053] In one possible design, the third message also includes information about the first object and / or an identifier of the first object in the vertical federation task corresponding to the first identifier.

[0054] In one possible design, the second message also indicates a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier.

[0055] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0056] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0057] In one possible design, the information of the M network elements includes network entity identifiers of the M network elements, subscription association addresses of the M network elements, and at least one of role information of the M network elements.

[0058] In one possible design, the j-th network element is any one of the M network elements, and the role information of the j-th network element indicates the role of the producer of the j-th vertical federated learning model in the vertical federated task corresponding to the first identifier; wherein, the j-th network element is the user of the j-th vertical federated learning model, and at least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model, j is less than or equal to M, and j is a positive integer.

[0059] In a fifth aspect, the present application provides a communication device, the method comprising: a transceiver unit and a processing unit; the transceiver unit is used to send and receive messages; the processing unit is used to send a first message to a second network element through the transceiver unit; and receive a second message from the second network element; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the second message includes a first identifier, information of M network elements and information of the first model; wherein the first identifier is associated with the analysis identifier, and the first identifier corresponds to at least two vertical federated learning models; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, the at least two vertical federated learning models include the first model, and the M network elements each correspond to the at least two vertical federated learning models.

[0060] In one possible design, the processing unit is used to determine at least one network element based on the information of the M network elements; the transceiver unit is used to send a third message to the at least one network element, the third message including the first identifier, and the third message is used to request the vertical federated learning model corresponding to the first identifier to provide services.

[0061] In one possible design, the processing unit is used to obtain a first intermediate result based on the first model; the transceiver unit is used to receive at least one intermediate result from the at least one network element, and the at least one network element corresponds one-to-one to the at least one intermediate result; the processing unit is used to determine the output based on the first intermediate result and the at least one intermediate result; the transceiver unit is used to send the output to the service consumption network element.

[0062] In one possible design, the processing unit is used to obtain a first intermediate result based on the first model; the transceiver unit is used to send the first intermediate result to a third network element, receive output from the third network element, and send the output to a service consumption network element; the third network element is one of the at least one network element.

[0063] In one possible design, the transceiver unit is used to receive a fourth message from the service consumption network element before sending the first message to the second network element, the fourth message including the analysis identifier and information of the first object, wherein the first object corresponds to the analysis identifier; and the fourth message is used to request the service corresponding to the analysis identifier.

[0064] In one possible design, the third message also includes information about the first object.

[0065] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0066] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0067] In one possible design, the third message also includes the identifier of the first object in the vertical federation task corresponding to the first identifier; the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, the first mapping relationship being the identifier of the network entity identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship being the identifier of the user entity identifier in the vertical federation task corresponding to the first identifier; the processing unit is used to determine the identifier of the first object in the vertical federation task corresponding to the first identifier based on the network entity identifier of the first object and the first mapping relationship if the information of the first object includes the network entity identifier of the first object; and to determine the identifier of the first object in the vertical federation task corresponding to the first identifier based on the user entity identifier of the first object and the second mapping relationship if the information of the first object includes the user entity identifier of the first object.

[0068] In one possible design, the user entity identifier is a SUPI.

[0069] In one possible design, the second message also includes first indication information, wherein the first indication information indicates that the first model is a vertical federated learning model; or, the first indication information indicates that the model corresponding to the first identifier is a vertical federated learning model; or, the first indication information indicates that the task corresponding to the first identifier is a vertical federated task.

[0070] In one possible design, the information of the M network elements includes network entity identifiers of the M network elements, subscription association addresses of the M network elements, and at least one of role information of the M network elements.

[0071] In one possible design, the j-th network element is any one of the M network elements, and the role information of the j-th network element indicates the role of the producer of the j-th vertical federated learning model in the vertical federated task corresponding to the first identifier; wherein, the j-th network element is the user of the j-th vertical federated learning model, and at least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model, j is less than or equal to M, and j is a positive integer.

[0072] In a sixth aspect, the present application provides a communication device, which includes: a transceiver unit and a processing unit; the transceiver unit is used to send and receive messages, and the processing unit is used to receive a first message from a first network element through the transceiver unit, and send a second message to the first network element; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the second message includes a first identifier, information of M network elements and information of the first model; wherein, the first identifier is associated with the analysis identifier, and the first identifier corresponds to at least two vertical federated learning models; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, the at least two vertical federated learning models include the first model, and the M network elements each correspond to the at least two vertical federated learning models.

[0073] In one possible design, the processing unit is used to determine the first identifier, information of the M network elements and at least one of the information of the first model based on the analysis identifier before sending the second message to the first network element.

[0074] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0075] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0076] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, wherein the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier.

[0077] In one possible design, the second message also includes first indication information, wherein the first indication information indicates that the first model is a vertical federated learning model; or, the first indication information indicates that the model corresponding to the first identifier is a vertical federated learning model; or, the first indication information indicates that the task corresponding to the first identifier is a vertical federated task.

[0078] In one possible design, the information of the M network elements includes network entity identifiers of the M network elements, subscription association addresses of the M network elements, and at least one of role information of the M network elements.

[0079] In one possible design, the j-th network element is any one of the M network elements, and the role information of the j-th network element indicates the role of the producer of the j-th vertical federated learning model in the vertical federated task corresponding to the first identifier; wherein, the j-th network element is the user of the j-th vertical federated learning model, and at least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model, j is less than or equal to M, and j is a positive integer.

[0080] In the seventh aspect, the present application provides a communication device, the method including: a transceiver unit and a processing unit; the transceiver unit is used to send and receive messages, the processing unit is used to send a first message to a second network element through the transceiver unit, receive a second message from the second network element, and the second network element sends a third message; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the second message includes a second identifier and / or first indication information, the first indication information indicates that the model that provides the service corresponding to the analysis identifier is a vertical federated learning model, and the second identifier is used to identify the first message; the third message is used to request the service corresponding to the analysis identifier, and the third message includes the second identifier.

[0081] In one possible design, the transceiver unit is used to receive the output from the second network element; and send the output to the service consuming network element.

[0082] In one possible design, the transceiver unit is used to receive a fourth message from the service consumption network element before sending the first message to the second network element, the fourth message including the analysis identifier and information of the first object, wherein the first object corresponds to the analysis identifier; and the fourth message is used to request the service corresponding to the analysis identifier.

[0083] In one possible design, the third message also includes information about the first object.

[0084] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0085] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0086] In one possible design, the third message also includes the identifier of the first object in the vertical federated learning model; the second message also indicates a first mapping relationship and / or a second mapping relationship, the first mapping relationship being the identifier of the network entity identifier in the vertical federated learning model, and the second mapping relationship being the identifier of the user entity identifier in the vertical federated learning model; the processing unit is used to determine the identifier of the first object in the vertical federated learning model based on the network entity identifier of the first object and the first mapping relationship if the information of the first object includes the network entity identifier of the first object; and determine the identifier of the first object in the vertical federated learning model based on the user entity identifier of the first object and the second mapping relationship if the information of the first object includes the user entity identifier of the first object.

[0087] In an eighth aspect, the present application provides a communication device, the method comprising: a transceiver unit and a processing unit; the transceiver unit is used to send and receive messages, the processing unit is used to receive a first message from a first network element through the transceiver unit, send a second message to the first network element, and receive a third message from the first network element; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the second message includes a second identifier and / or first indication information, the first indication information indicates that the model that provides the service corresponding to the analysis identifier is a vertical federated learning model, and the second identifier is used to identify the first message; the third message is used to request the service corresponding to the analysis identifier, and the third message includes the second identifier.

[0088] In one possible design, the processing unit is used to, before sending the second message to the first network element, enable the second network element to determine the information of the first model based on the analysis identifier; and save the correspondence between the second identifier and the information of the first model.

[0089] In one possible design, the processing unit is used to, when determining the information of the first model according to the analysis identifier, the second network element determines the information of the first model, the information of M network elements and the first identifier according to the analysis identifier; when the second network element saves the correspondence between the second identifier and the information of the first model, it saves the correspondence between the second identifier and the information of the first model, the information of the M network elements and the first identifier; wherein, the first identifier is associated with the analysis identifier, and the first identifier corresponds to at least two vertical federated learning models; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, the at least two vertical federated learning models include the first model, and the M network elements each correspond to the at least two vertical federated learning models.

[0090] In one possible design, the processing unit is used to determine the information of the first model, the information of the M network elements and the first identifier based on the second identifier after receiving the third message from the first network element; determine at least one network element based on the information of the M network elements; the transceiver unit is used to send a fifth message to the at least one network element, the fifth message including the first identifier, and the fifth message is used to request the vertical federated learning model corresponding to the first identifier to provide services; the processing unit is used to obtain a first intermediate result based on the first model; the transceiver unit is used to receive at least one intermediate result from the at least one network element, and the at least one network element corresponds one-to-one to the at least one intermediate result; the processing unit is used to determine the output based on the first intermediate result and the at least one intermediate result.

[0091] In one possible design, the processing unit is used to determine the information of the first model, the information of the M network elements and the first identifier based on the second identifier after receiving the third message from the first network element; determine at least one network element based on the information of the M network elements; the transceiver unit is used to send a fifth message to the at least one network element, the fifth message including the first identifier, and the third message is used to request the vertical federated learning model corresponding to the first identifier to provide services; the processing unit is used to obtain a first intermediate result based on the first model; the transceiver unit is used to send the first intermediate result to the third network element; and the second network element receives the output from the third network element.

[0092] In one possible design, the transceiver unit is used to send the output to the first network element.

[0093] In one possible design, the third message also includes information about the first object and / or an identifier of the first object in the vertical federation task corresponding to the first identifier.

[0094] In one possible design, the second message also indicates a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier.

[0095] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0096] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0097] In one possible design, the information of the M network elements includes network entity identifiers of the M network elements, subscription association addresses of the M network elements, and at least one of role information of the M network elements.

[0098] In one possible design, the j-th network element is any one of the M network elements, and the role information of the j-th network element indicates the role of the producer of the j-th vertical federated learning model in the vertical federated task corresponding to the first identifier; wherein, the j-th network element is the user of the j-th vertical federated learning model, and at least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model, j is less than or equal to M, and j is a positive integer.

[0099] In the ninth aspect, the present application provides a communication device, which may 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 fourth aspects, or may be capable of being used in combination with the first device.

[0100] In the tenth 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 first to fourth aspects of the present application is implemented.

[0101] In the eleventh aspect, the present application further provides a computer program, which, when executed on a computer, enables the computer to execute the method described in any one of the first to fourth aspects above.

[0102] In the twelfth 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 one of the above-mentioned first to fourth aspects.

[0103] 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.

[0104] In the thirteenth 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, the software program can implement any of the methods described in any one of the first to fourth aspects above.

[0105] In a fourteenth aspect, the present application provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any one of the methods described in any one of the first to fourth aspects above.

[0106] In the fifteenth 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 one of the methods described in any one of the first to fourth aspects above.

[0107] In the sixteenth aspect, the present application provides a communication system, which includes a first network element and a second network element, wherein the first network element executes the method described in any one of the first and third aspects, and the second network element executes the method described in any one of the second and fourth aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0108] Figure 1 is a schematic diagram of the 5G network architecture based on the service-oriented architecture in this application;

[0109] Figure 2 is a schematic diagram of the process of vertical federated learning training in this application;

[0110] FIG3 is a flowchart illustrating an overview of a communication method in the present application;

[0111] FIG4 is one of the flow charts for obtaining output in this application;

[0112] FIG5 is a second flowchart of obtaining output in this application;

[0113] FIG6 is a third flowchart of obtaining output in this application;

[0114] FIG7 is a flowchart illustrating another communication method in the present application;

[0115] FIG8 is a flow chart showing the execution of an analysis task by a first network element and at least one network element through a vertical federated learning model in the present application;

[0116] FIG9 is a flow chart showing the second network element and at least one network element performing an analysis task through a vertical federated learning model in the present application;

[0117] FIG10 is a flow chart of another communication method in the present application;

[0118] FIG11 is a flow chart of another communication method in the present application;

[0119] FIG12 is a schematic structural diagram of a communication device in this application;

[0120] FIG13 is a schematic structural diagram of another communication device in this application. DETAILED DESCRIPTION

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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; and 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.

[0127] The following is a brief introduction to some core network equipment:

[0128] 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.

[0129] 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.

[0130] 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.

[0131] UDM network element, referred to as UDM, includes functions such as executing and managing contract data and user access authorization.

[0132] 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.

[0133] NEF network element, referred to as NEF, is used to support the opening of capabilities and events.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] NWDAF network element, referred to as NWDAF, has the function of collecting 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. NWDAF also has functions such as model training, data analysis, and model reasoning. For example, it performs data analysis based on the collected data and outputs the data analysis results for use by the network, network management equipment and application execution policy decision-making. 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, setting the NWDAF to a PCF network element or an AMF network element.

[0138] 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.

[0139] Among them, the NWDAF that supports the model training function can be used to train machine learning (ML) models or artificial intelligence (AI) models, and expose new training services; for example, providing trained AI models or ML models. The NWDAF that supports the model training function can also be called a training NWDAF, or an NWDAF that supports the model training logical function (MTLF), referred to as MTLF. For example, the MTLF can perform model training based on the acquired data to obtain a trained model.

[0140] An NWDAF that supports data reasoning can be used to reason and derive analytical information and expose analytical services. An NWDAF that supports data reasoning can also be called a reasoning NWDAF, or an NWDAF that supports analytics logical function (AnLF), abbreviated as AnLF. For example, AnLF can request a model from MTLF via a model subscription (MLModelProvision_Subscribe) service or message. The model can be obtained by MTLF based on model-related data training. Furthermore, AnLF can input input data into the trained model to obtain analysis results or reasoning data.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] The following is an explanation of the basic technical concepts involved in this application:

[0146] 1. Federated Learning

[0147] Federated learning (FL) is a machine learning framework that effectively enables multiple users to utilize data and conduct machine learning modeling while meeting user privacy, data security, and government regulations. As a distributed machine learning paradigm, FL effectively addresses data silos by enabling joint modeling without sharing user data. This technically breaks down data silos and enables artificial intelligence (AI) collaboration.

[0148] 2. Vertical federated learning (VFL)

[0149] To train data from different domains, distributed model training can be achieved using vertical federated learning (VFL). As a machine learning technique, VFL can be used to address model training and inference challenges when participants are reluctant to share their original data. It is suitable for scenarios where participants' training sample identifications (IDs) overlap significantly, but their data features overlap less. VFL combines the different data features of shared samples from multiple participants for federated learning, meaning that each participant's training data is vertically partitioned. This is why it's called vertical federated learning.

[0150] Taking the linear regression algorithm as an example, the process of vertical federated learning training is shown in Figure 2.

[0151] Client A has a dataset Client B has a dataset where y i It is label data, then the model to be trained is as follows:

[0152] Assume that the objective function used for linear regression is as follows,

[0153] Where L is the loss function, as follows:

[0154] Since the original data D on client A A D on client B B They cannot be aggregated together, so they cannot be trained based on the traditional centralized training method. However, they can be trained based on the vertical federation training method, as follows:

[0155] make Then the L transformation is as follows:

[0156] make Then L = L A +L B +L AB (Formula 5)

[0157] Let the residual Then L is about Θ A and Θ B The gradient is as follows:

[0158] Accordingly, the model parameters are updated as follows:

[0159] The training process of vertical federated learning is as follows:

[0160] Step 1: Client A and client B initialize model parameters Θ respectively A and Θ B ;

[0161] Step 2, client A based on Θ A calculate and L A , and then send it to client B;

[0162] Step 3, client B based on Θ B calculate Further based on and y i Calculate d i , L AB , L B , and finally based on L A , L AB , L B Calculate L. Client B will d i Send to client A;

[0163] Step 4: Client A and client B each use d i Calculate separately as well as Then based on as well as Update model parameters Θ A and Θ B .

[0164] Among them, steps 2 to 4 are executed in a loop until the model training end condition is met, such as the number of iterations reaches a set threshold (such as 10,000 times) or the value of the loss function L is less than a set threshold (such as 0.001).

[0165] Through the above technology, the interaction of original data between different domains is avoided, and the business experience model can be trained. In the inference phase, client A and client B are based on the trained model parameters Θ A and Θ B Calculate local inference results (also known as intermediate results) as well as Then client A will send the local inference results Sent to client B, who will finalize the inference result (also known as prediction result, analysis output, or output)

[0166] For the convenience of description, Θ is used below. A Represents the longitudinal federated learning model trained by client A, using Θ B Represents the longitudinal federated learning model trained by client B.

[0167] 3. Participants in vertical federated learning

[0168] In this application, participants in vertical federated learning may also be referred to as participating devices in vertical federated learning, participants in vertical federated tasks, or participants in vertical federated learning tasks. This application does not limit this. This application uses participants in vertical federated tasks as an example for illustration.

[0169] In vertical federated learning, there are multiple types of participants, such as UEs, NWDAFs, and AFs. For example, the participants in a vertical federated task include client A and client B. Optionally, the participants in a vertical federated task can include more clients, without specific limitations. For another example, client A and client B can each be a different AF or a different NWDAF, or an AF and an NWDAF, respectively.

[0170] For example, the main roles of participants in a vertical federation task are as follows:

[0171] Master Participant: During the training phase of a vertical federated learning model, the entity responsible for providing labeled data for the training data of the vertical federated task. The master participant can determine the final output based on multiple intermediate results. For example, client B is the master participant. The master participant can also provide partial training data for the vertical federated task.

[0172] Slave: An entity responsible for providing partial training data for a vertical federated task. A slave can determine intermediate results from the corresponding vertical federated learning model, but cannot determine the final output. For example, client A in the preceding example is a slave.

[0173] Optionally, participants in the vertical federated task may also include a coordinator, where the coordinator is responsible for coordinating participants in training the vertical federated learning model.

[0174] 4. Analysis ID

[0175] 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.

[0176] 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.

[0177] In this application, a vertical federated task refers to a task corresponding to vertical federated learning. A vertical federated task can also be referred to as a vertical federated activity or a vertical federated learning task. A vertical federated task can be associated with an analysis identifier, meaning that the vertical federated learning model provided by the vertical federated task can provide the service corresponding to the analysis identifier. Alternatively, it can be understood that the identifier of the vertical federated task is associated with the analysis identifier.

[0178] Vertical federated tasks may include training and / or reasoning. Among them, training can also be called model training, or vertical federated learning model training, which is used to obtain a vertical federated learning model. Reasoning refers to using the vertical federated learning model obtained in the training phase to perform reasoning or perform reasoning tasks (or prediction tasks or analysis tasks). Reasoning can also be called model reasoning, or vertical federated learning model reasoning, or model prediction, or vertical federated learning model prediction. In this application, reasoning and prediction can be used interchangeably.

[0179] The identifier of a vertical federated task is used to identify a vertical federated task, and to determine the vertical federated learning model corresponding to the vertical federated task, and / or the participant information of the vertical federated task, and / or the user information of the vertical federated learning model.

[0180] It is understood that a vertical federation task can correspond to multiple vertical federated learning models, and thus, multiple participants in the vertical federation task. That is, each vertical federated learning model corresponds to a corresponding participant. It is understood that participants in a vertical federation task refer to some or all of the participants in the vertical federation task. Participants in a vertical federation jointly participate in the vertical federation task and each obtains an independent vertical federated learning model. Participants in a vertical federation may or may not include a coordinator.

[0181] Similarly, a vertical federated learning model can have multiple users, meaning each vertical federated learning model corresponds to a corresponding user. It can be understood that a vertical federated learning model user refers to an entity that uses the vertical federated learning model obtained during the training phase to perform reasoning or perform reasoning tasks (or prediction tasks or analysis tasks). Reasoning can also be referred to as model reasoning, vertical federated learning model reasoning, model prediction, or vertical federated learning model prediction.

[0182] In one possible implementation, the participants of the vertical federated task and the users of the vertical federated learning model can be the same. In this case, the two descriptions of participants in the vertical federated task and users of the vertical federated learning model can be interchangeable. For example, client A and client B can be both participants in the vertical federated task and users of the vertical federated learning model. In other words, client A participates in training the vertical federated learning model Θ. A , you can also use the vertical federated learning model Θ A Similarly, client B participates in training the vertical federated learning model Θ B , you can also use the vertical federated learning model Θ B .

[0183] In another possible implementation, the participants of the vertical federated task and the users of the vertical federated learning model can also be different. For example, the aforementioned client A and / or client B only serve as participants in the vertical federated task and not as users of the vertical federated learning model. For example, client A only participates in training the vertical federated learning model Θ A , vertical federated learning model Θ A The user is not client A, or client A does not have the ability to use the vertical federated learning model Θ A For example, the vertical federated learning model Θ A The user is client C, that is, client C can use the vertical federated learning model Θ A , optional, and client A cannot use the vertical federated learning model Θ A Among them, client A plays the role of a slave participant in the vertical federation task, and client C plays the role of a slave participant as well. That is, if client B participates in training the vertical federated learning model Θ B , you can also use the vertical federated learning model Θ B , and client B plays the role of the primary participant in the vertical federation task, then the intermediate results calculated by client C need to be sent to client B.

[0184] For example, participant information for a vertical federated task may include, but is not limited to, at least one of the participant's network entity identifier, the participant's subscription association address, and the participant's role information. User information for a vertical federated learning model may include, but is not limited to, at least one of the user's network entity identifier, the user's subscription association address, and the user's role information. The user's role information is the same as the role information of the participant used to train the vertical federated learning model used by the user.

[0185] For example, client A and client B participate in the vertical federation task A. During the training phase, client A obtains a vertical federation learning model Θ A , client B also obtains a vertical federated learning model Θ B Assume that client A and client B can be participants in the vertical federated task A and users of the vertical federated learning model. In the inference phase, if client A receives the identifier of the vertical federated task A, client A can determine the vertical federated learning model Θ corresponding to the vertical federated task A based on the identifier of the vertical federated task A. A , and then we can use the vertical federated learning model Θ ACalculate an intermediate result. Similarly, if client B receives the identifier of vertical federated task A, client B can determine the vertical federated learning model Θ corresponding to vertical federated task A based on the identifier of vertical federated task A. B , and then we can use the vertical federated learning model Θ B Calculate an intermediate result. In addition, client A can also determine the participant information of vertical federated task A based on the identifier of vertical federated task A. For example, the participant information of vertical federated task A includes the network entity identifier of client A, indicating that client A's role in vertical federated task A is a slave participant, and the network entity identifier of client B, indicating that client B's role in vertical federated task A is a master participant. Client A then sends the intermediate result obtained through its own calculation to client B. Alternatively, client B can also determine the participant information of vertical federated task A based on the identifier of vertical federated task A, and then client B can request the intermediate result from client A.

[0186] It is understandable that client A and / or client B may also participate in other vertical federated tasks, that is, have multiple vertical federated learning models. Through the identification of the vertical federated task, a vertical federated learning model can be uniquely identified, as well as the corresponding vertical federated task participant information and / or vertical federated learning model user information.

[0187] Based on the network system architecture shown in FIG1 and the contents of the above-mentioned related technical introduction, several possible communication methods are provided in the embodiments of the present application to realize the execution of analysis tasks through the vertical federated learning model. In the following, the following methods can be implemented by the first network element or the module or chip in the first network element, or the second network element or the module or chip in the second network element. The first network element can be a core network element. For example, the first network element can be an NWDAF (such as AnLF), an AF or other core network element. For example, the second network element can be an NWDAF (such as MTLF) or other core network element.

[0188] As shown in FIG3 , the present application provides a communication method, which includes:

[0189] Step 300: The first network element sends a first message to the second network element. Correspondingly, the second network element receives the first message from the first network element.

[0190] The first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier.

[0191] Exemplarily, the first message may also be referred to as a model request message. For example, the first message may be a model provision subscription (Nnwdaf_MLModelProvision_Subscribe) message.

[0192] In one possible implementation, before the first network element sends the first message to the second network element, the first network element may receive a fourth message from the service-consuming network element. The fourth message is used to request the service corresponding to the analysis identifier, and the fourth message may include the analysis identifier. The service-consuming network element may also be referred to as the fourth network element, and this application does not limit its name.

[0193] Step 310: The second network element sends a second message to the first network element. Correspondingly, the first network element receives the second message from the second network element.

[0194] Exemplarily, the second message may also be referred to as a model notification message. For example, the second message may be a model provision notification (Nnwdaf_MLModelProvision_Notify) message.

[0195] The second message includes one or more of the following: a first identifier, information of M network elements, and information of a first model, wherein the first identifier is associated with the analysis identifier, the first identifier corresponds to at least two vertical federated learning models, and the users of the at least two vertical federated learning models include M network elements, M is a positive integer, and the at least two vertical federated learning models corresponding to the first identifier include the first model.

[0196] Exemplarily, the first identifier can be understood as the identifier of a vertical federated task, or the first identifier is used to identify a vertical federated task. Each vertical federated task is associated with at least two vertical federated learning models, or it can be understood that at least two vertical federated learning models are obtained through the training phase of the vertical federated task. Therefore, the first identifier can correspond to at least two vertical federated learning models, or it can be understood that although the first identifier is the same, the vertical federated learning models identified by the first identifier are different in different participants of the vertical federated task.

[0197] Exemplarily, the user of at least two vertical federated learning models can also be described as a device that uses at least two vertical federated learning models. It can also be understood as an entity that uses at least two vertical federated learning models to provide inference services (or inference results), or an entity that uses at least two vertical federated learning models to provide prediction services (or outputs), or an entity that uses at least two vertical federated learning models to provide analysis and identification services, or an entity that has the ability to use at least two vertical federated learning models.

[0198] For example, if the users of at least two vertical federated learning models include M network elements, then the M network elements can each use their corresponding vertical federated learning model to provide inference services. There is a one-to-one correspondence between the M network elements and the M vertical federated learning models, and the at least two vertical federated learning models corresponding to the first identifier include the aforementioned M vertical federated learning models.

[0199] Exemplarily, the users of at least two vertical federated learning models include M network elements, then each of the M network elements can use at least one vertical federated learning model to provide reasoning services, that is, one network element can use one or more vertical federated learning models to provide reasoning services.

[0200] Exemplarily, the information of the M network elements includes at least one of network entity identifiers of the M network elements, subscription association addresses of the M network elements, and role information of the M network elements.

[0201] For example, information of M network elements may be represented as a network element information list, where a tuple in the list includes one or more of a network entity identifier, a subscription association address, and role information.

[0202] Among them, taking the jth network element as an example, the jth network element is any one of the M network elements, and the role information of the jth network element indicates the role of the producer of the jth vertical federated learning model in the vertical federated task corresponding to the first identifier; for example, the role here is the main participant, or the slave participant, or the coordinator, etc.

[0203] Among them, the j-th network element is the user of the j-th vertical federated learning model, and the at least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model.

[0204] Exemplarily, the number of vertical federated learning models corresponding to the first identifier is at least two, and the first model is one of them. The first model is a vertical federated learning model, or the type of the first model is a vertical federated learning model. The second network element provides information about the first model to the first network element. The first network element can be understood as a user of the first model, that is, a user of the vertical federated learning model. The second network element can be a producer of the first model and a participant in the vertical federated task corresponding to the first identifier.

[0205] Exemplarily, the information of the first model may include an ML model file address (e.g., a uniform resource locator (URL) or a fully qualified domain name (FQDN), or an analytics data repository functional (ADRF) ID or an ADRF set ID. When an ADRFID or ADRF set ID is included, the first information may also include a storage transaction ID. Optionally, the information of the first model may include an identifier of the first model. In addition, 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.

[0206] For example, the information of the first model includes a uniform resource locator (URL), and the first network element can obtain the first model according to the URL. Alternatively, the information of the first model may include an ADRFID, and the first network element may send a model acquisition request to an ADRF identified by the ADRFID, and the ADRF may send the first model to the first network element.

[0207] Exemplarily, the first identifier and / or the information of the M network elements may be included in the information of the first model, or located outside the information of the first model, and this application does not limit this. For example, the information of the first model includes the model file address, the first identifier and / or the information of the M network elements.

[0208] It can be understood that the information of the M network elements may be all or part of the user information of at least two vertical federated learning models corresponding to the first identifier.

[0209] In Example A, there are M network elements corresponding to the at least two vertical federated learning models corresponding to the first identifier, that is, M ≥ 2. The information of the M network elements is all user information of the at least two vertical federated learning models corresponding to the first identifier. In other words, the M network elements may include the first network element.

[0210] In Example B, there are M+1 at least two vertical federated learning models corresponding to the first identifier. The information of the M network elements is partial user information of the at least two vertical federated learning models corresponding to the first identifier. The M network elements do not include network elements using the first model, that is, they do not include the first network element. Because the first network element uses the first model, there is no need to notify the first network element again. In other words, the M network elements do not need to include the first network element.

[0211] At this time, the first network element can obtain all user information of at least two vertical federated learning models corresponding to the first identifier based on the information of the M network elements and its own information.

[0212] In addition, in a possible implementation, the second message also includes information of N network elements, where the N network elements are participants of the vertical federated learning task corresponding to the first identifier, or producers of at least two vertical federated learning models corresponding to the first identifier, and N is a positive integer.

[0213] For example, the number of vertical federated learning models corresponding to the first identifier is three, namely Model 1, Model 2, and Model 3. Among them, network element 1 trains Model 1, network element 2 trains Model 2, and network element 3 trains Model 3. It can be understood that the participants of the vertical federated task corresponding to the first identifier include network elements 1, 2, and 3. For example, network elements 1 and 2 can be slave participants of the vertical federated task corresponding to the first identifier, and network element 3 can be the master participant of the vertical federated task corresponding to the first identifier. It can also be described as that the producers of the three vertical federated learning models corresponding to the first identifier include network elements 1, 2, and 3.

[0214] The information of the N network elements includes information of network element 1, information of network element 2, and information of network element 3.

[0215] In one example, network element A is the user of model 1, network element B is the user of model 2, and network element C is the user of model 3. That is, the users of the three vertical federated learning models corresponding to the first identifier include network element A, network element B, and network element C. Network element A, network element B, and network element C each use a different model.

[0216] Among them, network element 1, network element 2, network element 3, network element A, network element B, and network element C are different from each other. That is, the producer and user of model 1 are different network elements, the producer and user of model 2 are different network elements, and the producer and user of model 3 are different network elements.

[0217] In combination with the above example A, the information of the M network elements includes the information of network element A, the information of network element B and the information of network element C.

[0218] In combination with the above example B, if the first network element is network element A, the information of the M network elements includes information of network element B and information of network element C.

[0219] In another example, network element A is a user of model 1, network element 2 is a user of model 2, and network element 3 is a user of model 3. That is, the users of the three vertical federated learning models corresponding to the first identifier include network element A, network element 2, and network element 3.

[0220] Among them, network element 1 is different from network element A. That is, the producer and user of model 1 are different network elements, the producer and user of model 2 are the same network element, and the producer and user of model 3 are the same network element.

[0221] In combination with the above example A, the information of the M network elements includes the information of network element A, the information of network element 2 and the information of network element 3.

[0222] In combination with the above example B, if the first network element is network element A, the information of the M network elements includes the information of network element 2 and the information of network element 3.

[0223] The above examples are merely examples, and there may be other examples, which are not limited in this application.

[0224] For example, the second network element may determine the vertical federation task or vertical federation learning model based on the analysis identifier. Further, relevant information of the vertical federation task or vertical federation learning model is obtained, specifically including: the first identifier, information of the first model, and information of the M network elements.

[0225] Exemplarily, the second network element may determine at least one of the first identifier, the first model, and the information of the M network elements in the following manner:

[0226] First, the second network element can determine at least one model based on the analysis identifier, and the at least one model can provide the service corresponding to the analysis identifier. The at least one model can include a common model (or a non-vertical federated learning model) and a vertical federated learning model, or the at least one model can be a vertical federated learning model. The number of vertical federated learning models can also be one or more. In addition, if the second network element only determines the common model, the existing process can be referred to and will not be repeated here.

[0227] The specific process of the second network element determining the vertical federated learning model may be as follows:

[0228] In one possible design, the second network element can determine the vertical federated learning model based on the analysis identifier. As can be seen from the aforementioned information regarding vertical federated tasks, the analysis identifier is related to the vertical federated task. For example, the analysis identifier only supports vertical federated tasks and does not support other machine learning tasks (such as analysis to generate a common model). Furthermore, the second network element can determine that the first model is a vertical federated learning model based on the analysis identifier.

[0229] In another possible design, the second network element may first determine the first identifier based on the analysis identifier. As can be seen from the aforementioned content regarding vertical federated tasks, the first identifier is associated with the analysis identifier. Furthermore, the second network element may determine, based on the first identifier, one of the vertical federated learning models corresponding to the vertical federated task, namely, the first model. It is understood that the analysis identifier may be associated with the identifiers of one or more vertical federated tasks, and thus the second network element may determine one or more vertical federated learning models.

[0230] Then, the second network element may determine a model from at least one model in the following manner but not limited to the following manner.

[0231] For example, after a model is trained, the second network element may obtain performance information or performance parameters about the model, such as accuracy or error. Furthermore, the first message may also include information indicating model performance requirements. Furthermore, the second network element may determine a model that meets the performance requirements from at least one model based on the information indicating the model performance requirements in the first message and the performance information corresponding to the at least one model. The information indicating the model performance requirements may be provided by the service consuming network element. For example, before step 300, the service consuming network element may also provide the information indicating the model performance requirements to the first network element via a fourth message.

[0232] For example, the second network element can determine, based on the analysis identifier, between common model A and vertical federated learning model B. Both common model A and vertical federated learning model B can provide the service corresponding to the analysis identifier. The first message also includes information indicating model performance requirements. Furthermore, based on the performance information of common model A, the performance information of vertical federated learning model B, and the information indicating model performance requirements, the second network element can determine that common model A does not meet the performance requirements, while vertical federated learning model B does. That is, the second network element ultimately selects vertical federated learning model B. The fact that vertical federated learning model B can provide the service corresponding to the analysis identifier can be understood as meaning that vertical federated learning model B and other vertical federated learning models with the same vertical federated task identifier as vertical federated learning model B can jointly provide the service corresponding to the analysis identifier. Vertical federated learning model B meets the performance requirements, meaning that vertical federated learning model B and other vertical federated learning models with the same vertical federated task identifier as vertical federated learning model B jointly meet the performance requirements.

[0233] It is understandable that if at least one model includes a common model and a vertical federated learning model, the second network element may select the common model or the vertical federated learning model. If the common model is selected, the existing process can be referred to. The second network element provides the first network element with information about the common model, and the first network element uses the common model to provide the service consuming network element with the service corresponding to the analysis identifier. This is not further described here. The following only uses the example of the second network element selecting a vertical federated learning model, where the vertical federated learning model selected by the second network element is recorded as the first model.

[0234] Finally, after the second network element determines the first model, the second network element may further determine information of M network elements and / or information of N network elements. For example, the second network element has already determined the first identifier in the process of determining the vertical federated learning model. In combination with the above-mentioned content regarding the vertical federated task, it can be seen that the second network element may also determine the participant information of the vertical federated task (i.e., the information of the N network elements) and / or the user information of the vertical federated learning model based on the first identifier, wherein the information of the M network elements may be part or all of the user information of the vertical federated learning model.

[0235] Exemplarily, after the training phase of the vertical federated task corresponding to the first identifier is completed, taking the i-th vertical federated learning model as an example, the i-th vertical federated learning model is any one of the at least two vertical federated learning models corresponding to the first identifier, and the producer of the i-th vertical federated learning model or the user of the i-th vertical federated learning model may also send a notification message to the second network element, where the notification message includes information about the producer of the i-th vertical federated learning model and information about the user of the i-th vertical federated learning model. The producer of the i-th vertical federated learning model may also be understood as one of the participants of the vertical federated task corresponding to the first identifier.

[0236] That is, through the above process, the second network element can obtain the user information of at least two vertical federated learning models corresponding to the first identifier, and / or the producer information of at least two vertical federated learning models corresponding to the first identifier, wherein the producer information of at least two vertical federated learning models corresponding to the first identifier can be described as the participant information of the vertical federated task corresponding to the first identifier. In addition, the user information of at least two vertical federated learning models corresponding to the first identifier, and / or the producer information of at least two vertical federated learning models corresponding to the first identifier can also be stored in the second network element in a preconfigured manner.

[0237] In addition, in one possible implementation, the notification message may further include at least one of the information of the i-th vertical federated learning model, for example, an identifier of the i-th vertical federated learning model. Alternatively, the second network element further stores identifiers corresponding to at least two vertical federated learning models corresponding to the first identifier.

[0238] In one possible implementation, the first message may be replaced by information about M network elements and identifiers of M models, where the M network elements correspond one-to-one to the M models. The M models belong to at least two vertical federated learning models corresponding to the first identifier.

[0239] For example, taking the jth network element as an example, the jth network element is any one of the M network elements, and the jth network element is the user of the jth vertical federated learning model. The first network element can send the identifier of the jth vertical federated learning model to the jth network element so that the jth network element calculates the intermediate result according to the jth vertical federated learning model.

[0240] In another possible implementation, the first message may be replaced by information about M network elements and identifiers of K models, where the M network elements correspond to the K models. The K models belong to at least two vertical federated learning models corresponding to the first identifier.

[0241] In one possible implementation, the second message may further include first indication information, where the first indication information indicates that the model providing the service corresponding to the analysis identifier is a vertical federated learning model. Alternatively, the first indication information indicates that the first model is a vertical federated learning model; alternatively, the first indication information indicates that the model corresponding to the first identifier is a vertical federated learning model; alternatively, the first indication information indicates that the task corresponding to the first identifier is a vertical federated task.

[0242] Furthermore, the first network element may determine that the type of the first model is a vertical federated learning model based on the first indication information. In addition, the first indication information is optional information. Since the second message includes information of M network elements, the first network element may also determine that the type of the first model is a vertical federated learning model based on the information of the M network elements.

[0243] Further, optionally, step 320: the first network element sends a first identifier to at least one network element among the M network elements. Exemplarily, the first network element sends a third message to at least one network element among the M network elements, and the third message is used to request the vertical federated learning model corresponding to the first identifier to provide services. For example, the first identifier can be carried by analyzing a subscription request message, or a (vertical federated learning) prediction request message, or a vertical federated learning model prediction request message. The network element that receives the message can determine the vertical federated learning model that it can use based on the first identifier, and then calculate the intermediate results based on the vertical federated learning model.

[0244] Exemplarily, the first network element determines at least one network element according to the information of the M network elements, and sends a third message to the at least one network element.

[0245] Exemplarily, in combination with the information of the M network elements, the first network element may determine, based on the information of the M network elements, that at least one network element may include the following situations:

[0246] In conjunction with Example A above, there are M vertical federated learning models corresponding to the first identifier, and the M network elements are all users of the vertical federated learning models corresponding to the first identifier. In this case, the first network element can determine the information of M-1 network elements based on the information of the M network elements, where the M-1 network elements do not include the first network element. Furthermore, the first network element can send a third message to each of the M-1 network elements.

[0247] Combined with the above example B, there are M+1 vertical federated learning models corresponding to the first identifier, then the M network elements are partial users of the vertical federated learning model corresponding to the first identifier, among which the M network elements do not include the first network element, then the first network element can send the third message to the M network elements respectively.

[0248] As can be seen from step 300 above, before the first network element sends the first message to the second network element, the first network element receives a fourth message from the service consuming network element. The fourth message includes an analysis identifier and information about the first object, where the first object is the analysis object corresponding to the analysis identifier. The fourth message is used to request the service corresponding to the analysis identifier.

[0249] For example, the first object may also be referred to as a target UE. For example, the fourth message includes analysis identifier 1 and / or SUPI of UE1, where analysis identifier 1 identifies the mobility service of the UE and the first object is UE1. The fourth message is used to request analysis of the mobility of UE1.

[0250] The information of the first object includes a network entity identifier of the first object or a user entity identifier of the first object. Exemplarily, the user entity identifier is a user permanent identifier (SUPI).

[0251] In one possible implementation, the third message further includes the identifier of the first object in at least two vertical federated learning models corresponding to the first identifier, which can also be described as the identifier of the first object in the vertical federated task corresponding to the first identifier.

[0252] In one possible design, the second message further indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0253] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity identifier in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0254] In one example, the second message may further indicate or include a first mapping relationship, where the first mapping relationship is the identifier of the network entity identifier in at least two vertical federated learning models corresponding to the first identifier. Alternatively, the identifier of the network entity identifier in the vertical federated task corresponding to the first identifier. For example, the first mapping relationship may be implemented as follows: (NF ID, VFL ID).

[0255] Exemplarily, the first network element first obtains the network entity identifier of the first object. For example, the network entity identifier of the first object can be provided by the service consuming network element. For example, before step 300, the service consuming network element can also provide the network entity identifier of the first object to the first network element through a fourth message. Furthermore, the first network element determines the identifier of the first object in at least two vertical federated learning models corresponding to the first identifier based on the network entity identifier of the first object and the first mapping relationship. At this time, the first object can be a network entity. For example, the first network element queries the first mapping relationship based on the NF ID of the first object to determine the VFL ID of the first object.

[0256] In another example, the second message may further indicate a second mapping relationship, where the second mapping relationship is an identifier of the user entity identifier in at least two vertical federated learning models corresponding to the first identifier. For example, the second mapping relationship may be implemented as follows: (SUPI, VFL ID) or (UE ID, UE VFL ID).

[0257] Exemplarily, the first network element first obtains the user entity identifier of the first object. For example, the user entity identifier of the first object can be provided by the service consumption network element. For example, before step 300, the service consumption network element can also provide the user entity identifier of the first object to the first network element through a fourth message. Furthermore, the first network element determines the identifier of the first object in the vertical federated learning model based on the user entity identifier of the first object and the second mapping relationship. At this time, the first object can be a terminal device, such as a UE. For example, the first network element queries the second mapping relationship based on the SUPI of the first object to determine the VFL ID of the first object. Alternatively, the first network element queries the second mapping relationship based on the UE ID of the first object to determine the UE VFL ID of the first object.

[0258] In another possible implementation manner, the third message further includes information about the first object.

[0259] For example, the network entity identifier of the first object or the user entity identifier of the first object. If the third message also includes the network entity identifier of the first object, the network element that receives the network entity identifier of the first object can determine the identifier of the first object in the vertical federated learning model based on the first mapping relationship and the network entity identifier of the first object. Alternatively, if the third message also includes the user entity identifier of the first object, the network element that receives the user entity identifier of the first object can determine the identifier of the first object in the vertical federated learning model based on the second mapping relationship and the user entity identifier of the first object.

[0260] Furthermore, after the first network element sends the third message to at least one network element, in one possible implementation, the first network element obtains a first intermediate result according to the first model; the first network element receives at least one intermediate result from the at least one network element, where the at least one network element has a one-to-one correspondence with the at least one intermediate result; and the first network element determines an output based on the first intermediate result and the at least one intermediate result. In another possible implementation, the first network element obtains the first intermediate result according to the first model; the first network element sends the first intermediate result to a third network element; the third network element is one of the at least one network element; and the first network element receives the output from the third network element.

[0261] Depending on the role of the producer in the first model, the first network element may obtain output in the following possible ways.

[0262] In the following, the producer of the first model is the main participant or the slave participant in the vertical federation task corresponding to the first identifier. For the convenience of description, the producer of the first model is referred to as the main participant or the slave participant below. Among them, the producer of the first model is the main participant (or slave participant), which can also be described as that the model obtained by the first network element (i.e., the first model) is the model generated by the main participant (or slave participant) in the vertical federation task corresponding to the first identifier, or that the second network element is the main participant (or slave participant) in the vertical federation task corresponding to the first identifier. The following is explained by taking the example that the third message includes the first identifier and the identifier of the first object in at least two vertical federated learning models corresponding to the first identifier (hereinafter referred to as the VFL ID of the first object).

[0263] Mode 1: The producer of the first model is the main participant.

[0264] Exemplarily, in combination with the above example A, the information of M network elements includes the information of the first network element and the information of other M-1 network elements, wherein the information of the first network element includes the role information of the first network element, wherein the role information of the first network element indicates that the producer of the first model is the main participant. Alternatively, in combination with the above example B, the information of M network elements does not include the information of the first network element, the information of M network elements includes the role information of M network elements, the role information of M network elements can be one information or M information, the role information of M network elements indicates that the producers of the models used by each of the M network elements are all slave participants in the vertical federation task corresponding to the first identifier, hereinafter referred to as the producers of the models used by each of the M network elements are all slave participants, then the first network element determines that the producer of the first model is the main participant based on the role information of the M network elements.

[0265] Exemplarily, the first network element determines at least one network element based on information from M network elements and sends a third message to each of the at least one network elements. The third message includes a first identifier and an identifier of the first object in at least two vertical federated learning models corresponding to the first identifier (hereinafter referred to as the VFL ID of the first object). Exemplarily, in conjunction with Example A above, the number of the at least one network element is M-1, and in conjunction with Example B above, the number of the at least one network element is M. The network element that receives the first identifier and the VFL ID of the first object can determine the corresponding vertical federated learning model based on the first identifier and calculate a corresponding intermediate result based on the VFL ID of the first object and the determined vertical federated learning model. Each of the at least one network element determines an intermediate result. The at least one network element sends the corresponding intermediate result to the first network element. That is, the first network element receives at least one intermediate result from the at least one network element, and there is a one-to-one correspondence between the at least one network element and the at least one intermediate result. The first network element also obtains a first intermediate result based on the first model. Further, the first network element determines an output based on the first intermediate result and the at least one received intermediate result. The above process is illustrated below with reference to FIG4.

[0266] In Figure 4, the number of at least one network element is 2, and at least one network element is network element X and network element Y. Network element X is the user of vertical federated learning model X, network element Y is the user of vertical federated learning model Y, and the producer of vertical federated learning model X and the producer of vertical federated learning model Y are both slave participants.

[0267] S401: A first network element sends a first identifier and a VFL ID of a first object to network element X and network element Y respectively.

[0268] S402A: Network element X determines a vertical federated learning model X according to the first identifier, and determines an intermediate result X according to the vertical federated learning model X and the VFL ID of the first object.

[0269] S402B: Network element Y determines a vertical federated learning model Y according to the first identifier, and determines an intermediate result Y according to the vertical federated learning model Y and the VFL ID of the first object.

[0270] S403A: Network element X sends intermediate result X to the first network element.

[0271] S403B: Network element Y sends intermediate result Y to the first network element.

[0272] S404: The first network element obtains a first intermediate result according to the first model.

[0273] Exemplarily, the first network element calculates the first intermediate result according to the VFL ID of the first object and the first model. This application does not limit the order of S404 and S401, S402A, S402B, S403A, and S403B.

[0274] S405: The first network element determines an output according to the first intermediate result, the intermediate result X, and the intermediate result Y.

[0275] Mode 2: The producer of the first model is a slave participant.

[0276] Among them, the producer of the first model is a slave participant, and the producer of the model used by the third network element is a master participant.

[0277] Exemplarily, in combination with the above example A, if M=2, the information of the M network elements includes the information of the first network element and the information of the third network element; if M>2, the information of the M network elements includes the information of the first network element and the information of the third network element, as well as the information of other M-2 network elements, wherein the information of the first network element includes the role information of the first network element, and the role information of the first network element indicates that the producer of the first model is a slave participant. The information of the third network element includes the role information of the third network element, and the role information of the third network element indicates that the producer of the model used by the third network element is a master participant. In combination with the above example B, the information of the M network elements does not include the information of the first network element; if M=2, the information of the M network elements includes the information of the third network element; if M>2, the information of the M network elements includes the information of the third network element, as well as the information of other M-2 network elements, wherein the information of the third network element includes the role information of the third network element, and the role information of the third network element indicates that the producer of the model used by the third network element is a master participant. Furthermore, the first network element can determine that the producer of the first model is a slave participant based on the information of the third network element.

[0278] Exemplarily, the first network element determines at least one network element based on the information of M network elements, and sends a third message to the at least one network element, where the third message includes the first identifier and the VFL ID of the first object. Exemplarily, in combination with the above example A, the number of the at least one network element is M-1, and in combination with the above example B, the number of the at least one network element is M. The network element that receives the first identifier and the VFL ID of the first object can determine the corresponding longitudinal federated learning model based on the first identifier, and calculate the intermediate result based on the VFL ID of the first object and the determined longitudinal federated learning model. Each network element in the at least one network element determines an intermediate result.

[0279] Next, there are two possible implementation methods:

[0280] Possible Implementation Method a: Network elements other than the third network element in the at least one network element send corresponding intermediate results to the first network element. That is, the first network element receives intermediate results from network elements other than the third network element in the at least one network element. The first network element also obtains a first intermediate result based on the first model, and further sends the first intermediate result and the received intermediate result to the third network element. The third network element may determine an output based on the intermediate result received from the first network element and the intermediate result calculated by itself, and send the output to the first network element.

[0281] Possible Implementation Method b: The network elements other than the third network element in the at least one network element send the corresponding intermediate results to the third network element. The first network element also obtains a first intermediate result based on the first model and further sends the first intermediate result to the third network element. The third network element may determine an output based on the intermediate results from the network elements other than the third network element in the at least one network element, the first intermediate result, and the intermediate result calculated by itself, and send the output to the first network element.

[0282] The above process is described below with reference to FIG5 .

[0283] In Figure 5, the number of at least one network element is 2, and at least one network element is network element X and network element Y, where network element X is the user of vertical federated learning model X, network element Y is the user of vertical federated learning model Y, the producer of vertical federated learning model X is the main participant, and the producer of vertical federated learning model Y is the slave participant.

[0284] S501: The first network element sends a first identifier and a VFL ID of a first object to network element X and network element X respectively.

[0285] S502A: Network element X determines a vertical federated learning model X according to the first identifier, and determines an intermediate result X according to the vertical federated learning model X and the VFL ID of the first object.

[0286] S502B: Network element Y determines a vertical federated learning model Y according to the first identifier, and determines an intermediate result Y according to the vertical federated learning model Y and the VFL ID of the first object.

[0287] S503: Network element Y sends intermediate result Y to the first network element.

[0288] S504: The first network element obtains a first intermediate result according to the first model.

[0289] This application does not limit the order of S504, S501, S502A, S502B, and S503.

[0290] S505: The first network element sends the first intermediate result and the intermediate result Y to the network element X.

[0291] Alternatively, S503 may be replaced by network element Y sending intermediate result Y to network element X, and S505 may be replaced by the first network element sending the first intermediate result to network element X.

[0292] S506: Network element X determines an output according to the first intermediate result, intermediate result X, and intermediate result Y.

[0293] S507: Network element X sends the output to the first network element.

[0294] As an optional embodiment, the number of vertical federated learning models corresponding to the first identifier is greater than 2, the producer of the first model is a slave participant, and the information of the M network elements only includes the information of the third network element, that is, M=1. The information of the third network element includes the role information of the third network element, and the role information of the third network element indicates that the producer of the model used by the third network element is the main participant. That is, in addition to the first network element and the third network element, there is at least one other network element, and the producer of the model used by at least one other network element is a slave participant. The first network element can determine that the producer of the first model is a slave participant based on the information of the third network element. At this time, the third network element only knows its own information and the information of the third network element, but the first network element does not obtain the information of at least one other network element. In this case, the third network element can initiate the collection of intermediate results of at least one other network element and provide output. The above process is illustrated below with reference to Figure 6.

[0295] In Figure 6, the number of vertical federated learning models corresponding to the first identifier = 3, where network element X is the user of vertical federated learning model X, network element Y is the user of vertical federated learning model Y, the producer of vertical federated learning model X is the main participant, and the producer of vertical federated learning model Y is the slave participant.

[0296] S601: The first network element sends a first identifier and a VFL ID of a first object to network element X.

[0297] S602: The first network element obtains a first intermediate result according to the first model.

[0298] S603: The first network element sends the first intermediate result to network element X.

[0299] It is understandable that the first network element may also carry the first intermediate result, the first identifier, and the VFL ID of the first object in one message.

[0300] Among them, S602 and S603 can be before or after S601, and this application does not limit this.

[0301] S604: The network element X determines a vertical federated learning model X according to the first identifier, and determines an intermediate result X according to the vertical federated learning model X and the VFL ID of the first object.

[0302] S605: Network element X determines that it has not obtained the intermediate result network element of network element Y, and sends the first identifier and the VFL ID of the first object to network element Y.

[0303] Exemplarily, network element X determines, based on the first identifier, information about all users of the vertical federated learning model corresponding to the first identifier, where all users of the vertical federated learning model corresponding to the first identifier include the first network element, network element X, and network element Y. Furthermore, network element X determines, based on the obtained intermediate results, that the intermediate results of network element Y have not been obtained.

[0304] S606: Network element Y determines a vertical federated learning model Y according to the first identifier, and determines an intermediate result Y according to the vertical federated learning model Y and the VFL ID of the first object.

[0305] S607: Network element Y sends intermediate result Y to network element X.

[0306] S608: Network element X determines an output according to the first intermediate result, intermediate result X, and intermediate result Y.

[0307] S609: Network element X sends the output to the first network element.

[0308] In addition, for the above-mentioned methods 1 and 2, the network element using the producer of the model as the main participant can also determine the information of all users of the vertical federated learning model corresponding to the first identifier based on the first identifier, and judge whether all intermediate results have been obtained based on the intermediate results obtained. No further details will be given here.

[0309] As shown in FIG7 , the present application also provides a communication method, which includes:

[0310] Step 700: The first network element sends a first message to the second network element. Correspondingly, the second network element receives the first message from the first network element.

[0311] The first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier.

[0312] Exemplarily, the first message may also be referred to as a model request message.

[0313] In one possible implementation, before the first network element sends the first message to the second network element, the first network element may receive a fourth message from the service-consuming network element. The fourth message is used to request the service corresponding to the analysis identifier, and the fourth message may include the analysis identifier. For other relevant content of the fourth message, please refer to the embodiment shown in Figure 3 above.

[0314] Step 710: The second network element sends a second message to the first network element. Correspondingly, the first network element receives the second message from the second network element.

[0315] Exemplarily, the second message may also be referred to as a model notification message.

[0316] The second message includes a second identifier and / or first indication information, the second identifier being used to identify the first message, and the first indication information indicating that the model providing the service corresponding to the analysis identifier is a vertical federated learning model. Further, the first network element may determine, based on the first indication information, that the model providing the service corresponding to the analysis identifier is a vertical federated learning model.

[0317] Exemplarily, the second identifier may be a subscription correlation ID. The second identifier is associated with the vertical federated learning model subscription and is used to identify the model subscription between the second network element and the first network element. In addition, the second network element stores the corresponding relationship between the second identifier and the vertical federated learning model.

[0318] Exemplarily, before the second network element sends the second message to the first network element, that is, before step 710, the second network element can determine, based on the analysis identifier, to use the first model to provide the service corresponding to the analysis identifier, and the first model is a vertical federated learning model. Furthermore, the second network element stores the information correspondence between the second identifier and the first model, so that after receiving the second identifier, the second network element can determine the information of the first model based on the second identifier. For information about the first model, please refer to the relevant description of the embodiment shown in Figure 3.

[0319] When the second network element determines the information of the first model according to the analysis identifier, the second network element may also determine the information of the M network elements and / or the first identifier according to the analysis identifier;

[0320] When the second network element saves the correspondence between the second identifier and the information of the first model, the second network element saves the correspondence between the second identifier and the information of the first model, the information of M network elements and the first identifier; or the correspondence between the second identifier and the information of the first model, the information of M network elements; or the correspondence between the second identifier and the information of the first model, the first identifier, etc.

[0321] The first identifier is associated with the analysis identifier, the first identifier corresponds to at least two vertical federated learning models, the users of the at least two vertical federated learning models include M network elements, where M is a positive integer, and the at least two vertical federated learning models include the first model. For details, please refer to the relevant description of the embodiment shown in Figure 3 above.

[0322] Among them, the specific process of the second network element determining the first model can refer to the relevant description of the second network element determining the first identifier, the first model and at least one of the information of M network elements in the embodiment shown in Figure 3 above, which will not be repeated here.

[0323] Step 720: The first network element sends a third message to the second network element. The third message is used to request a service corresponding to the analysis identifier, and the third message includes the second identifier.

[0324] Exemplarily, the third message may further include an identifier of the first object in at least two vertical federated learning models corresponding to the first identifier, or information about the first object, such as a network entity identifier or a user entity identifier of the first object. For specific possible implementations, reference may be made to the relevant content in the embodiment shown in FIG. 3 above, and will not be further elaborated here.

[0325] Exemplarily, the second network element determines information of the first model according to the second identifier, uses the first model, and provides a service corresponding to the analysis identifier to the first network element.

[0326] Therefore, in this embodiment, the second network element does not provide model information to the first network element, but uses the first indication information to notify the first network element that the model for providing the service corresponding to the analysis identifier is a vertical federated learning model, and uses the second identifier to enable the second network element to request the service corresponding to the analysis identifier.

[0327] Furthermore, the first network element may also receive output from the second network element, and the first network element may also send the output to the service consuming network element.

[0328] Exemplarily, if the second network element stores a correspondence between the second identifier, information about the first model, information about the M network elements, and the first identifier, then after the second network element receives the third message, the second network element can determine at least one of the information about the first model, information about the M network elements, and the first identifier based on the second identifier in the third message. Furthermore, in combination with the information about the first model, information about the M network elements, and the first identifier, at least one of the second network elements can also be output.

[0329] In one possible design, after the second network element receives the third message from the first network element, the second network element determines information about the first model, information about the M network elements, and the first identifier based on the second identifier. The second network element determines at least one network element based on the information about the M network elements, and sends a fifth message to the at least one network element. The fifth message includes the first identifier and is used to request that the vertical federated learning model corresponding to the first identifier provide a service. The second network element obtains a first intermediate result based on the first model and receives at least one intermediate result from the at least one network element. The at least one network element has a one-to-one correspondence with the at least one intermediate result. The second network element determines an output based on the first intermediate result and the at least one intermediate result.

[0330] In one possible design, after the second network element receives the third message from the first network element, the second network element determines information about the first model, information about the M network elements, and the first identifier based on the second identifier. The second network element determines at least one network element based on the information about the M network elements and sends a fifth message to the at least one network element, where the fifth message includes the first identifier, and the third message is used to request the vertical federated learning model corresponding to the first identifier to provide a service. The second network element obtains a first intermediate result based on the first model, sends the first intermediate result to a third network element, and receives an output from the third network element.

[0331] The fifth message may further include an identifier of the first object in at least two vertical federated learning models corresponding to the first identifier, or information about the first object, such as a network entity identifier or a user entity identifier of the first object. For specific possible implementations, reference may be made to the relevant content in the embodiment shown in FIG. 3 above, which will not be further described here. The following description will take the example of the fifth message including the first identifier and the VFL ID of the first object.

[0332] For example, depending on the role of the second network element, the second network element may obtain the output in the following manner A or manner B:

[0333] Method A: The role of the second network element is the main participant.

[0334] Exemplarily, the second network element can obtain information about M network elements. Specifically, the second network element can determine the information of all users of the vertical federated learning model corresponding to the first identifier. Therefore, the second network element can understand its own role and the role of the producers of the models used by other users in the vertical federated task corresponding to the first identifier. The second network element can determine the information of at least one network element based on the information of the M network elements. Exemplarily, the information of the at least one network element is the user information of all users of the vertical federated learning model corresponding to the first identifier, excluding the second network element.

[0335] Exemplarily, the second network element sends a fifth message to at least one network element respectively, where the fifth message includes the first identifier and the VFL ID of the first object. The network element that receives the first identifier and the VFL ID of the first object can determine the corresponding longitudinal federated learning model based on the first identifier, and calculate the corresponding intermediate result based on the VFL ID of the first object and the determined longitudinal federated learning model. Each of the at least one network element determines an intermediate result. The at least one network element sends the corresponding intermediate result to the second network element respectively. That is, the second network element receives at least one intermediate result from the at least one network element, and the at least one network element has a one-to-one correspondence with the at least one intermediate result. The second network element also obtains the first intermediate result based on the first model. Furthermore, the second network element determines the output based on the first intermediate result and the at least one intermediate result received.

[0336] The above-mentioned method A can refer to the embodiment shown in Figure 4, wherein the first network element in the embodiment shown in Figure 4 can be replaced by a second network element.

[0337] Mode B: The role of the second network element is a slave participant.

[0338] The role of the second network element is a slave participant, and the role of the producer of the usage model of the third network element is a master participant.

[0339] Exemplarily, the second network element can obtain information about M network elements. Specifically, the second network element can determine the information of all users of the vertical federated learning model corresponding to the first identifier. Therefore, the second network element can understand its own role and the role of the producers of the models used by other users in the vertical federated task corresponding to the first identifier. The second network element can determine the information of at least one network element based on the information of the M network elements. Exemplarily, the information of the at least one network element is the user information of all users of the vertical federated learning model corresponding to the first identifier, excluding the second network element.

[0340] Exemplarily, the second network element sends the first identifier and the VFL ID of the first object to at least one network element, respectively. The network element that receives the first identifier and the VFL ID of the first object can determine the corresponding vertical federated learning model based on the first identifier, and calculate the intermediate result based on the VFL ID of the first object and the determined vertical federated learning model. Each network element in the at least one network element determines an intermediate result. The network elements other than the third network element in the at least one network element send the corresponding intermediate results to the second network element. That is, the second network element receives the intermediate results from the network elements other than the third network element in the at least one network element. The second network element also obtains the first intermediate result based on the first model, and further sends the first intermediate result and the received intermediate result to the third network element. The third network element determines an output based on the intermediate result received from the second network element and the intermediate result calculated by itself, and sends the output to the second network element.

[0341] The above-mentioned method B can refer to the embodiment shown in Figure 5, wherein the first network element in the embodiment shown in Figure 5 can be replaced by a second network element.

[0342] Furthermore, in one possible implementation, the second message includes a model subscription address and first indication information. The first network element may send a third message to the address, where the address is an address of the second network element, and the second network element stores a correspondence between the address and the information of the first model. The second network element determines the information of the first model based on the address in the third message. The second network element uses the first model and provides the first network element with a service corresponding to the analysis identifier. Exemplarily, the model subscription address and the second identifier have similar functions, and reference may be made to the above-described related description.

[0343] In the following, description is given by taking the case where the first network element is a first AnLF and the second network element is a first MTLF as an example.

[0344] The embodiment shown in FIG8 is a further example of the embodiment shown in FIG3 .

[0345] S801: The service consuming network element sends a first analysis subscription message to the first AnLF, wherein the first analysis subscription message includes an analysis identifier, a SUPI or NF ID of object X, and optionally, information indicating model performance requirements.

[0346] 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.

[0347] Exemplarily, the first analysis subscription message may specifically refer to the above description of the fourth message.

[0348] S802: The first AnLF sends a first message to the first MTLF, wherein the first message includes an analysis identifier.

[0349] In one possible implementation, the first AnLF may determine the first MTLF through a network element discovery process. Exemplarily, the first AnLF sends an NF discovery message to the NRF. The NF discovery message includes an analysis identifier. For example, the NF discovery message may be Nnrf_NF Discovery. The NF discovery message 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. The NRF sends an NF discovery response message to the first AnLF. The NF discovery response message includes information about the first MTLF, wherein the information about the first MTLF may include an identifier of the first MTLF, an analysis identifier, etc. For example, the information about the first MTLF is the NF information (profile) of the first MTLF.

[0350] It is understood that the NRF can determine one or more MTLFs based on the analysis identifier in the NF discovery message. In this case, the NF discovery response message 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.

[0351] S803: The first MTLF sends a second message to the first AnLF.

[0352] The second message includes at least one of the information of the first model, the information of the M network elements and the first identifier.

[0353] Exemplarily, the first MTLF determines the information of the first model, the information of the M network elements and at least one of the first identifier according to the analysis identifier in the model request message. For details, reference may be made to the relevant content in the embodiment shown in FIG. 3 above, which will not be repeated here.

[0354] Optionally, the second message may further include the first mapping relationship and / or the second mapping relationship.

[0355] S804: The first AnLF determines at least one network element according to the information of the M network elements.

[0356] S805: The first AnLF sends the first identifier and the VFL ID of the object X to at least one network element respectively.

[0357] Optionally, the first AnLF determines the VFL ID of the object X according to the SUPI or NF ID of the object X in the first analysis subscription message and the first mapping relationship and / or the second mapping relationship included in the second message.

[0358] The following description only takes the role of the first model producer as the main participant as an example, which is not a limitation of this application.

[0359] S806: At least one network element sends at least one intermediate result to the first AnLF, where the at least one intermediate result corresponds to the at least one network element in a one-to-one manner.

[0360] S807: The first AnLF obtains a first intermediate result according to the first model.

[0361] Exemplarily, the first AnLF calculates a first intermediate result according to the VFL ID of the object X and the first model.

[0362] S808: The first AnLF determines an output according to the first intermediate result and at least one intermediate result.

[0363] S809: The first AnLF sends the output to the service consuming network element.

[0364] Using the above method, the first AnLF can obtain the information of the first model, the information of M network elements and at least one of the first identifiers from the first MTLF, and use the vertical federated learning model together with at least one of the M network elements to perform the analysis task.

[0365] The embodiment shown in FIG9 is a further example of the embodiment shown in FIG7 .

[0366] S901 to S902 may refer to the above-mentioned S801 to S802.

[0367] S903: The first MTLF sends a second message to the first AnLF.

[0368] The second message includes the second identifier and / or the first indication information.

[0369] Exemplarily, the first MTLF determines the information of the first model, the information of the M network elements, and at least one of the first identifiers according to the analysis identifier in the model request message. For details, reference may be made to the relevant content in the embodiment shown in FIG. 3 above. The first MTLF saves the correspondence between the second identifier and the information of the first model.

[0370] Optionally, the second message may further include the first mapping relationship and / or the second mapping relationship.

[0371] S904: The first AnLF sends a third message to the first MTLF.

[0372] The third message includes the VFL ID of the object X and the second identifier.

[0373] Optionally, the first AnLF determines the VFL ID of the object X according to the SUPI or NF ID of the object X in the first analysis subscription message and the first mapping relationship and / or the second mapping relationship included in the second message.

[0374] S905: The first MTLF determines at least one of the information of the first model, the information of the M network elements, and the first identifier according to the second identifier.

[0375] S906: The first MTLF determines at least one network element according to the information of the M network elements.

[0376] S907: The first MTLF sends the first identifier and the VFL ID of the object X to at least one network element respectively.

[0377] The following description only takes the role of the first MTLF as the main participant as an example, which is not a limitation of this application.

[0378] S908: At least one network element sends at least one intermediate result to the first MTLF, where the at least one intermediate result corresponds to the at least one network element in a one-to-one manner.

[0379] S909: The first MTLF obtains a first intermediate result according to the first model.

[0380] Exemplarily, the first MTLF calculates a first intermediate result according to the VFL ID of the object X and the first model.

[0381] S910: The first MTLF determines an output according to the first intermediate result and at least one intermediate result.

[0382] S911: The first MTLF sends an output to the first AnLF.

[0383] S912: The first AnLF sends an output to the service consuming network element.

[0384] Using the above method, the first AnLF does not obtain model information from the first MTLF, but can determine to use the vertical federated learning model based on the obtained first indication information and request the service corresponding to the analysis identifier through the second identifier. The first MTLF and at least one of the M network elements jointly use the vertical federated learning model to perform the analysis task.

[0385] The present application also provides a communication method, as shown in FIG10 , which includes:

[0386] S1001: 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, a SUPI or NF ID of an object X, and information indicating model performance requirements.

[0387] S1002: The first AnLF determines that a model that meets the performance requirements cannot be obtained.

[0388] For example, the first AnLF may request a model from a model production network element, but the first AnLF is unable to obtain a model that meets the model performance requirements. For example, the model production network element (e.g., the MTLF) is unable to generate a model that meets the model performance requirements and sends a model request rejection message. The first AnLF determines that it is unable to obtain a model that meets the requirements based on the model request rejection message.

[0389] For example, the first AnLF may obtain a common model and determine that the performance of the common model does not meet the performance requirements.

[0390] S1003: The first AnLF sends a service rejection message to the service consuming network element.

[0391] The service rejection message indicates that the first AnLF cannot obtain a model that meets the performance requirement.

[0392] S1004: The service consuming network element sends an NF discovery message to the NRF.

[0393] The NF discovery message is used to discover an NWDAF that includes an MTLF and an AnLF. The NF discovery message includes an analysis identifier and third indication information. The third indication information is used to request an NWDAF with vertical federated learning capability. Optionally, the NF discovery message also includes fifth indication information, which is used to instruct the NRF to return an NWDAF that includes an MTLF and an AnLF. The fifth indication information and the third indication information can also be combined into one indication information.

[0394] S1005: The NRF sends an NF discovery response message to the service consuming network element.

[0395] Exemplarily, the NRF determines the first NWDAF based on the NF discovery message, the first NWDAF includes the MTLF and the AnLF, and the first NWDAF has the capability of vertical federated learning. The NF discovery response message includes information about the first NWDAF. When the first NWDAF sends a registration request message to the NRF, the registration request message indicates that the first NWDAF includes the MTLF and the AnLF, and the first NWDAF has the capability of vertical federated learning. The NRF determines an NWDAF that supports both MTLF and AnLF based on the fifth indication information, determines an NWDAF that has the capability of vertical federated learning based on the third indication information, and determines an NWDAF that supports MTLF and AnLF and has the capability of vertical federated learning based on the fifth indication information and the third indication information.

[0396] S1006: The service consuming network element sends a first message to the first NWDAF. The first message includes an analysis identifier and fourth instruction information, and the fourth instruction information instructs the first NWDAF to generate a vertical federated learning model corresponding to the analysis identifier. The first message also includes information indicating model performance requirements.

[0397] S1007: The first NWDAF initiates a vertical federated task W and generates a first model, which is a vertical federated learning model.

[0398] Exemplarily, the first NWDAF and at least one other network element jointly participate in a vertical federation task W, where the vertical federation task W is used to train a vertical federated learning model corresponding to the analysis identifier. The first NWDAF obtains a first model, where the first model is a vertical federated learning model that meets performance requirements and is used to provide the service corresponding to the analysis identifier. The first NWDAF stores the correspondence between the second identifier and information about the first model. The second identifier is used to identify the first message.

[0399] S1008: The first NWDAF sends a second message to the service consuming network element, where the second message includes a second identifier and the first indication information.

[0400] Optionally, the first NWDAF further sends the first mapping relationship and / or the second mapping relationship to the service consuming network element.

[0401] S1009: The service consuming network element sends a third message to the first NWDAF, where the third message includes the second identifier and the VFL ID of object X.

[0402] Optionally, the service consuming network element determines the VFL ID of object X according to the SUPI or NF ID of object X and the first mapping relationship and / or the second mapping relationship.

[0403] S1010: The first NWDAF determines information of the first model, information of at least one other network element, and an identifier of the vertical federation task W according to the second identifier.

[0404] Exemplarily, the first NWDAF saves the correspondence between the second identifier and the information of the first model, the information of at least one other network element, and the identifier of the vertical federation task W.

[0405] S1011: The first NWDAF sends the identifier of the vertical federation task W and the VFL ID of the object X to at least one other network element.

[0406] The following description only takes the role of the first NWDAF as the main participant as an example, which is not a limitation of this application.

[0407] S1012: At least one other network element sends at least one intermediate result to the first NWDAF, where the at least one intermediate result corresponds to the at least one other network element in a one-to-one manner.

[0408] S1013: The first NWDAF obtains a first intermediate result according to the first model.

[0409] Exemplarily, the first NWDAF calculates a first intermediate result according to the VFL ID of the object X and the first model.

[0410] S1014: The first NWDAF determines an output according to the first intermediate result and at least one intermediate result.

[0411] S1015: The first NWDAF sends the output to the service consuming network element.

[0412] Using the above method, the service consumption network element can discover the NWDAF that supports MTLF and AnLF and has vertical federated learning capabilities, and instruct the NWDAF to initiate a vertical federation task, and provide the service corresponding to the analysis identifier through the vertical federation learning model obtained through the vertical federation task.

[0413] The present application also provides a communication method, as shown in FIG11 , which includes:

[0414] S1101: 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, a SUPI or NF ID of an object X, and information indicating model performance requirements.

[0415] S1102: The first AnLF determines that a model that meets the performance requirements cannot be obtained.

[0416] S1103: The first AnLF sends an NF discovery message to the NRF.

[0417] The NF discovery message is used to discover an NWDAF that includes an MTLF and an AnLF. The NF discovery message includes an analysis identifier and third indication information. The third indication information is used to request an NWDAF with vertical federated learning capability. Optionally, the NF discovery message also includes fifth indication information, which is used to instruct the NRF to return an NWDAF that includes an MTLF and an AnLF. The fifth indication information and the third indication information can also be combined into one indication information.

[0418] S1104: The first AnLF sends an NF discovery response message to the NRF.

[0419] Exemplarily, the NRF determines the first NWDAF based on the NF discovery message, the first NWDAF includes the MTLF and the AnLF, and the first NWDAF has the capability of vertical federated learning. The NF discovery response message includes information about the first NWDAF. When the first NWDAF sends a registration request message to the NRF, the registration request message indicates that the first NWDAF includes the MTLF and the AnLF, and the first NWDAF has the capability of vertical federated learning. The NRF determines an NWDAF that supports both MTLF and AnLF based on the fifth indication information, determines an NWDAF that has the capability of vertical federated learning based on the third indication information, and determines an NWDAF that supports MTLF and AnLF and has the capability of vertical federated learning based on the fifth indication information and the third indication information.

[0420] S1105: The first AnLF sends a first message to the first NWDAF. The first message includes an analysis identifier and fourth instruction information, wherein the fourth instruction information instructs the first NWDAF to generate a vertical federated learning model corresponding to the analysis identifier. The first message also includes information for indicating model performance requirements.

[0421] S1106: The first NWDAF initiates a vertical federated task W and generates a first model, which is a vertical federated learning model.

[0422] Exemplarily, the first NWDAF and at least one other network element jointly participate in a vertical federation task W, where the vertical federation task W is used to train a vertical federated learning model corresponding to the analysis identifier. The first NWDAF obtains a first model, where the first model is a vertical federated learning model that meets performance requirements and is used to provide the service corresponding to the analysis identifier. The first NWDAF stores the correspondence between the second identifier and information about the first model. The second identifier is used to identify the first message.

[0423] S1107: The first NWDAF sends a second message to the first AnLF, where the second message includes a second identifier and the first indication information.

[0424] Optionally, the first NWDAF further sends the first mapping relationship and / or the second mapping relationship to the first AnLF.

[0425] S1108: The first AnLF sends the second identifier, the first indication information, and the information of the first NWDAF to the service consuming network element.

[0426] Optionally, the first AnLF further sends the first mapping relationship and / or the second mapping relationship to the first NWDAF.

[0427] S1109 to S1115 can refer to S1009 to S1015 and will not be repeated here.

[0428] Using the above method, the first AnLF can discover the NWDAF that supports MTLF and AnLF and has vertical federated learning capabilities, and instruct the NWDAF to initiate a vertical federated task, so that the service consumption network element provides the service corresponding to the analysis identifier through the vertical federated learning model obtained through the vertical federated task.

[0429] It is understood that, to implement the functions in the above embodiments, the first network element and the second network element include hardware structures and / or software modules corresponding to the respective functions. Those skilled in the art should readily appreciate that, in conjunction with the various exemplary units and method steps described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is implemented in hardware or in a hardware-driven manner by computer software depends on the specific application scenario and design constraints of the technical solution.

[0430] Figures 12 and 13 are schematic diagrams of possible communication devices provided in embodiments of the present application. These communication devices can be used to implement the functions of the first network element and the second network element in the above method embodiment, thereby also achieving the beneficial effects of the above method embodiment.

[0431] As shown in Figure 12, the communication device 1200 includes a processing unit 1210 and a transceiver unit 1220. The communication device 1200 is used to implement the functions of the first network element or the second network element in the above method embodiment.

[0432] When the communication device 1200 is used to implement the function of the first network element in the above method embodiment:

[0433] The transceiver unit 1220 is used to send and receive messages; the processing unit 1210 is used to send a first message to the second network element through the transceiver unit 1220; and receive a second message from the second network element; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the second message includes a first identifier, information of M network elements and information of the first model; wherein the first identifier is associated with the analysis identifier, and the first identifier corresponds to at least two vertical federated learning models; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, and the at least two vertical federated learning models include the first model.

[0434] In one possible design, the processing unit 1210 is used to determine at least one network element based on the information of the M network elements; the transceiver unit 1220 is used to send a third message to the at least one network element, the third message including the first identifier, and the third message is used to request the vertical federated learning model corresponding to the first identifier to provide services.

[0435] In one possible design, the processing unit 1210 is used to obtain a first intermediate result based on the first model; the transceiver unit 1220 is used to receive at least one intermediate result from the at least one network element, and the at least one network element corresponds one-to-one to the at least one intermediate result; the processing unit 1210 is used to determine the output based on the first intermediate result and the at least one intermediate result; the transceiver unit 1220 is used to send the output to the service consumption network element.

[0436] In one possible design, the processing unit 1210 is used to obtain a first intermediate result based on the first model; the transceiver unit 1220 is used to send the first intermediate result to a third network element, receive output from the third network element, and send the output to the service consumption network element; the third network element is one of the at least one network element.

[0437] In one possible design, the transceiver unit 1220 is used to receive a fourth message from the service consumption network element before sending the first message to the second network element, the fourth message including the analysis identifier and information of the first object, wherein the first object corresponds to the analysis identifier; the fourth message is used to request the service corresponding to the analysis identifier.

[0438] In one possible design, the third message also includes information about the first object.

[0439] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0440] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0441] In one possible design, the third message also includes the identifier of the first object in the vertical federation task corresponding to the first identifier; the second message also indicates a first mapping relationship and / or a second mapping relationship, the first mapping relationship being the identifier of the network entity identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship being the identifier of the user entity identifier in the vertical federation task corresponding to the first identifier; the processing unit 1210 is used to determine the identifier of the first object in the vertical federation task corresponding to the first identifier based on the network entity identifier of the first object and the first mapping relationship if the information of the first object includes the network entity identifier of the first object; and to determine the identifier of the first object in the vertical federation task corresponding to the first identifier based on the user entity identifier of the first object and the second mapping relationship if the information of the first object includes the user entity identifier of the first object.

[0442] In one possible design, the second message also includes first indication information, wherein the first indication information indicates that the first model is a vertical federated learning model; or, the first indication information indicates that the model corresponding to the first identifier is a vertical federated learning model; or, the first indication information indicates that the task corresponding to the first identifier is a vertical federated task.

[0443] In one possible design, the information of the M network elements includes network entity identifiers of the M network elements, subscription association addresses of the M network elements, and at least one of role information of the M network elements.

[0444] In one possible design, the j-th network element is any one of the M network elements, and the role information of the j-th network element indicates the role of the producer of the j-th vertical federated learning model in the vertical federated task corresponding to the first identifier; wherein, the j-th network element is the user of the j-th vertical federated learning model, and at least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model, j is less than or equal to M, and j is a positive integer.

[0445] When the communication device 1200 is used to implement the function of the first network element in the above method embodiment:

[0446] The transceiver unit 1220 is used to send and receive messages; the processing unit 1210 is used to receive a first message from a first network element through the transceiver unit 1220, and send a second message to the first network element; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the second message includes a first identifier, information of M network elements and information of the first model; wherein, the first identifier is associated with the analysis identifier, and the first identifier corresponds to at least two vertical federated learning models; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, and the at least two vertical federated learning models include the first model.

[0447] In one possible design, the processing unit 1210 is used to determine the first identifier, the information of the M network elements and at least one of the information of the first model based on the analysis identifier before sending the second message to the first network element.

[0448] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0449] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0450] In one possible design, the second message also indicates a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier.

[0451] In one possible design, the second message also includes first indication information, wherein the first indication information indicates that the first model is a vertical federated learning model; or, the first indication information indicates that the model corresponding to the first identifier is a vertical federated learning model; or, the first indication information indicates that the task corresponding to the first identifier is a vertical federated task.

[0452] In one possible design, the information of the M network elements includes network entity identifiers of the M network elements, subscription association addresses of the M network elements, and at least one of role information of the M network elements.

[0453] In one possible design, the j-th network element is any one of the M network elements, and the role information of the j-th network element indicates the role of the producer of the j-th vertical federated learning model in the vertical federated task corresponding to the first identifier; wherein, the j-th network element is the user of the j-th vertical federated learning model, and at least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model, j is less than or equal to M, and j is a positive integer.

[0454] When the communication device 1200 is used to implement the function of the second network element in the above method embodiment:

[0455] The transceiver unit 1220 is used to send and receive messages; the processing unit 1210 is used to send a first message to the second network element through the transceiver unit 1220, receive a second message from the second network element, and the second network element sends a third message; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the second message includes a second identifier and first indication information, the first indication information indicates that the model that provides the service corresponding to the analysis identifier is a vertical federated learning model, and the second identifier is used to identify the first message; the third message is used to request the service corresponding to the analysis identifier, and the third message includes the second identifier.

[0456] In one possible design, the transceiver unit 1220 is used to receive the output from the second network element; and send the output to the service consuming network element.

[0457] In one possible design, the transceiver unit 1220 is used to receive a fourth message from the service consumption network element before sending the first message to the second network element, the fourth message including the analysis identifier and information of the first object, wherein the first object corresponds to the analysis identifier; the fourth message is used to request the service corresponding to the analysis identifier.

[0458] In one possible design, the third message also includes information about the first object.

[0459] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0460] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0461] In one possible design, the third message also includes the identifier of the first object in the vertical federated learning model; the second message also indicates a first mapping relationship and / or a second mapping relationship, the first mapping relationship being the identifier of the network entity identifier in the vertical federated learning model, and the second mapping relationship being the identifier of the user entity identifier in the vertical federated learning model; the processing unit 1210 is used to determine the identifier of the first object in the vertical federated learning model according to the network entity identifier of the first object and the first mapping relationship if the information of the first object includes the network entity identifier of the first object; and to determine the identifier of the first object in the vertical federated learning model according to the user entity identifier of the first object and the second mapping relationship if the information of the first object includes the user entity identifier of the first object.

[0462] When the communication device 1200 is used to implement the function of the second network element in the above method embodiment:

[0463] The transceiver unit 1220 is used to send and receive messages, and the processing unit 1210 is used to receive a first message from a first network element through the transceiver unit 1220, send a second message to the first network element, and receive a third message from the first network element; the first message includes an analysis identifier, and the first message is used to request a model that provides a service corresponding to the analysis identifier; the second message includes a second identifier and first indication information, the first indication information indicates that the model that provides the service corresponding to the analysis identifier is a vertical federated learning model, and the second identifier is used to identify the first message; the third message is used to request the service corresponding to the analysis identifier, and the third message includes the second identifier.

[0464] In one possible design, the processing unit 1210 is used to, before sending the second message to the first network element, enable the second network element to determine the information of the first model based on the analysis identifier; and save the correspondence between the second identifier and the information of the first model.

[0465] In one possible design, the processing unit 1210 is used to, when determining the information of the first model according to the analysis identifier, the second network element determines the information of the first model, the information of M network elements and the first identifier according to the analysis identifier; when the second network element saves the correspondence between the second identifier and the information of the first model, save the correspondence between the second identifier and the information of the first model, the information of the M network elements and the first identifier; wherein, the first identifier is associated with the analysis identifier, and the first identifier corresponds to at least two vertical federated learning models; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, and the at least two vertical federated learning models include the first model.

[0466] In one possible design, the processing unit 1210 is used to determine the information of the first model, the information of the M network elements and the first identifier according to the second identifier after receiving the third message from the first network element; determine at least one network element according to the information of the M network elements; the transceiver unit 1220 is used to send a fifth message to the at least one network element, the fifth message including the first identifier, and the fifth message is used to request the vertical federated learning model corresponding to the first identifier to provide services; the processing unit 1210 is used to obtain a first intermediate result according to the first model; the transceiver unit 1220 is used to receive at least one intermediate result from the at least one network element, and the at least one network element corresponds one-to-one to the at least one intermediate result; the processing unit 1210 is used to determine the output based on the first intermediate result and the at least one intermediate result.

[0467] In one possible design, the processing unit 1210 is used to determine the information of the first model, the information of the M network elements and the first identifier based on the second identifier after receiving the third message from the first network element; determine at least one network element based on the information of the M network elements; the transceiver unit 1220 is used to send a fifth message to the at least one network element, the fifth message including the first identifier, and the third message is used to request the vertical federated learning model corresponding to the first identifier to provide services; the processing unit 1210 is used to obtain a first intermediate result based on the first model; the transceiver unit 1220 is used to send the first intermediate result to the third network element; and the second network element receives the output from the third network element.

[0468] In one possible design, the transceiver unit 1220 is used to send the output to the first network element.

[0469] In one possible design, the third message also includes information about the first object and / or an identifier of the first object in the vertical federation task corresponding to the first identifier.

[0470] In one possible design, the second message also indicates a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier.

[0471] In one possible design, the second message also indicates or includes a first mapping relationship, where the first mapping relationship is a mapping relationship between the first object and the object of the first object in the vertical federation task corresponding to the first identifier. It can be understood that the first mapping relationship is a mapping relationship between the identifier of the first object and the identifier of the first object in the vertical federation task corresponding to the first identifier. The first network element determines the identifier of the first object in the vertical federation task corresponding to the first identifier based on the identifier of the first object and the first mapping relationship.

[0472] In one possible design, the second message also indicates or includes a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is the identifier of the network entity in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity in the vertical federation task corresponding to the first identifier; it can be understood that the first mapping relationship is the relationship between the network entity identifier and the identifier in the vertical federation task corresponding to the first identifier, and the second mapping relationship is the relationship between the user entity identifier and the identifier in the vertical federation task corresponding to the first identifier.

[0473] A more detailed description of the processing unit 1210 and the transceiver unit 1220 can be directly obtained by referring to the relevant description in the above method embodiment, and will not be repeated here.

[0474] As shown in Figure 13, communication device 1300 includes a processor 1310 and an interface circuit 1320. Processor 1310 and interface circuit 1320 are coupled to each other. It is understood that interface circuit 1320 can be a transceiver or an input / output interface. Optionally, communication device 1300 may also include a memory 1330 for storing instructions executed by processor 1310, input data required by processor 1310 to execute instructions, or data generated by processor 1310 after executing instructions.

[0475] When the communication device 1300 is used to implement the method shown in FIG. 5 , the processor 1310 is used to implement the functions of the processing unit 1210 , and the interface circuit 1320 is used to implement the functions of the transceiver unit 1220 .

[0476] 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.

[0477] 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 FIG13 , a communication device 1300 includes a processor 1310 and a memory 1330. The processor 1310 and the memory 1330 are coupled together, and the memory 1330 stores instructions. When the instructions stored in the memory 1330 are executed by the processor 1310, the communication device 1300 executes the method executed by each network element in the above-described embodiment.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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: A first network element sends a first message to a second network element; the first message includes an analysis identifier, and the first message is used to request a model for providing the service corresponding to the analysis identifier; The first network element receives a second message from the second network element, the second message includes a first identifier, information of M network elements, and information of a first model; Wherein, the first identifier is associated with the analysis identifier, and at least two vertical federated learning models corresponding to the first identifier; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, and the at least two vertical federated learning models include the first model.

2. The method according to claim 1, wherein It further includes: The first network element determines at least one network element according to the information of the M network elements; The first network element sends a third message to the at least one network element, the third message includes the first identifier, and the third message is used to request the vertical federated learning model corresponding to the first identifier to provide services.

3. The method according to claim 2, characterized in that, The method further includes: The first network element obtains a first intermediate result according to the first model; The first network element receives at least one intermediate result from the at least one network element, and the at least one network element corresponds to the at least one intermediate result one by one; The first network element determines an output according to the first intermediate result and the at least one intermediate result; The first network element sends the output to a service consumption network element.

4. The method according to claim 2, wherein The method further includes: The first network element obtains a first intermediate result according to the first model; The first network element sends the first intermediate result to a third network element; the third network element is one of the at least one network element; The first network element receives an output from the third network element; The first network element sends the output to a service consumption network element.

5. The method according to any one of claims 2-4, characterized in that, Before the first network element sends the first message to the second network element, the method further includes: The first network element receives a fourth message from the service consumption network element, the fourth message includes the analysis identifier and information of a first object, wherein the first object corresponds to the analysis identifier; the fourth message is used to request the service corresponding to the analysis identifier.

6. The method according to claim 5, wherein The third message further includes the information of the first object.

7. The method according to claim 5 or 6, characterized in that, The third message further includes an identifier of the first object in the vertical federated task corresponding to the first identifier; the second message further includes a first mapping relationship and / or a second mapping relationship, the first mapping relationship is an identifier of a network entity identifier in the vertical federated task corresponding to the first identifier, and the second mapping relationship is an identifier of a user entity identifier in the vertical federated task corresponding to the first identifier; The method further includes: If the information of the first object includes the network entity identifier of the first object, the first network element determines the identifier of the first object in the vertical federated task corresponding to the first identifier according to the network entity identifier of the first object and the first mapping relationship; Alternatively, if the information of the first object includes the user entity identifier of the first object, the first network element determines the identifier of the first object in the vertical federated task corresponding to the first identifier according to the user entity identifier of the first object and the second mapping relationship.

8. The method according to any one of claims 1-7, characterized in that, The second message further includes first indication information, where the first indication information indicates that the first model is a vertical federated learning model; or, the first indication information indicates that the model corresponding to the first identifier is a vertical federated learning model; or, the first indication information indicates that the task corresponding to the first identifier is a vertical federated task.

9. The method according to any one of claims 1-8, characterized in that, The information of the M network elements includes at least one of the network entity identifiers of the M network elements, the subscription association addresses of the M network elements, and the role information of the M network elements.

10. The method according to claim 9, wherein The j-th network element is any one of the M network elements. The at least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model. The j-th network element uses the j-th vertical federated learning model to provide services. The role information of the j-th network element indicates the role of the producer of the j-th vertical federated learning model in the vertical federated task corresponding to the first identifier, where j is less than or equal to M and j is a positive integer.

11. A communication method, characterized in that, The method includes: The second network element receives a first message from the first network element; the first message includes an analysis identifier, and the first message is used to request a model for providing services corresponding to the analysis identifier. The second network element sends a second message to the first network element, and the second message includes a first identifier, information of M network elements, and information of a first model. Wherein, the first identifier is associated with the analysis identifier, and there are at least two vertical federated learning models corresponding to the first identifier; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, and the at least two vertical federated learning models include the first model.

12. The method according to claim 11, wherein Before the second network element sends the second message to the first network element, it further includes: The second network element determines at least one of the first identifier, the information of the M network elements, and the information of the first model according to the analysis identifier.

13. The method according to claim 11 or 12, characterized in that, The second message further indicates a first mapping relationship and / or a second mapping relationship. The first mapping relationship is the identifier of the network entity identifier in the vertical federated task corresponding to the first identifier, and the second mapping relationship is the identifier of the user entity identifier in the vertical federated task corresponding to the first identifier.

14. The method according to any one of claims 11-13, characterized in that, The second message further includes first indication information, where the first indication information indicates that the first model is a vertical federated learning model; or, the first indication information indicates that the model corresponding to the first identifier is a vertical federated learning model; or, the first indication information indicates that the task corresponding to the first identifier is a vertical federated task.

15. The method according to any one of claims 11-14, characterized in that, The information of the M network elements includes at least one of the network entity identifiers of the M network elements, the subscription association addresses of the M network elements, and the role information of the M network elements.

16. The method according to claim 15, wherein The j-th network element is any one of the M network elements. At least two vertical federated learning models corresponding to the first identifier include the j-th vertical federated learning model. The j-th network element uses the j-th vertical federated learning model to provide services. The role information of the j-th network element indicates the role of the producer of the j-th vertical federated learning model in the vertical federated task corresponding to the first identifier. j is less than or equal to M and j is a positive integer.

17. A communication method, characterized in that, The method includes: The first network element sends a first message to the second network element. The first message includes an analysis identifier, and the first message is used to request a model that provides services corresponding to the analysis identifier. The first network element receives a second message from the second network element. The second message includes a second identifier and first indication information. The first indication information indicates that the model that provides services corresponding to the analysis identifier is a vertical federated learning model. The second identifier is used to identify the first message. The first network element sends a third message to the second network element. The third message is used to request services corresponding to the analysis identifier. The third message includes the second identifier.

18. The method according to claim 17, wherein The method further includes: The first network element receives an output from the second network element. The first network element sends the output to a service-consuming network element.

19. The method according to claim 17 or 18, characterized in that, Before the first network element sends the first message to the second network element, the method further includes: The first network element receives a fourth message from the service-consuming network element. The fourth message includes the analysis identifier and information of a first object, where the first object corresponds to the analysis identifier. The fourth message is used to request services corresponding to the analysis identifier.

20. The method according to claim 19, wherein The third message further includes the information of the first object.

21. The method according to claim 19 or 20, characterized in that, The third message further includes an identifier of the first object in the vertical federated learning model. The second message further indicates a first mapping relationship and / or a second mapping relationship. The first mapping relationship is the identifier of a network entity identifier in the vertical federated learning model. The second mapping relationship is the identifier of a user entity identifier in the vertical federated learning model. The method further includes: If the information of the first object includes the network entity identifier of the first object, the first network element determines the identifier of the first object in the vertical federated learning model according to the network entity identifier of the first object and the first mapping relationship. Alternatively, if the information of the first object includes the user entity identifier of the first object, the first network element determines the identifier of the first object in the vertical federated learning model according to the user entity identifier of the first object and the second mapping relationship.

22. A communication method, characterized in that, The method includes: The second network element receives a first message from the first network element. The first message includes an analysis identifier, and the first message is used to request a model that provides services corresponding to the analysis identifier. The second network element sends a second message to the first network element. The second message includes a second identifier and first indication information. The first indication information indicates that the model that provides services corresponding to the analysis identifier is a vertical federated learning model. The second identifier is used to identify the first message. The second network element receives a third message from the first network element, where the third message is used to request the service corresponding to the analysis identifier, and the third message includes the second identifier.

23. The method according to claim 22, wherein Before the second network element sends a second message to the first network element, it further includes: The second network element determines information of a first model according to the analysis identifier; The second network element stores the correspondence between the second identifier and the information of the first model.

24. The method according to claim 23, wherein The second network element determines information of a first model according to the analysis identifier, including: The second network element determines the information of the first model, the information of M network elements, and a first identifier according to the analysis identifier; The second network element stores the correspondence between the second identifier and the information of the first model, including: The second network element stores the correspondence between the second identifier and the information of the first model, the information of the M network elements, and the first identifier; Wherein, the first identifier is associated with the analysis identifier, and at least two vertical federated learning models corresponding to the first identifier; the M network elements use the at least two vertical federated learning models to provide services, M is a positive integer, and the at least two vertical federated learning models include the first model.

25. The method according to claim 24, wherein After the second network element receives a third message from the first network element, it further includes: The second network element determines the information of the first model, the information of the M network elements, and the first identifier according to the second identifier; The second network element determines at least one network element according to the information of the M network elements; The second network element sends a fifth message to the at least one network element, where the fifth message includes the first identifier, and the fifth message is used to request the vertical federated learning model corresponding to the first identifier to provide services; The second network element obtains a first intermediate result according to the first model; The second network element receives at least one intermediate result from the at least one network element, and the at least one network element corresponds to the at least one intermediate result one by one; The second network element determines the output according to the first intermediate result and the at least one intermediate result.

26. The method according to claim 24, wherein After the second network element receives a third message from the first network element, it further includes: The second network element determines the information of the first model, the information of the M network elements, and the first identifier according to the second identifier; The second network element determines at least one network element according to the information of the M network elements; The second network element sends a fifth message to the at least one network element, where the fifth message includes the first identifier, and the third message is used to request the vertical federated learning model corresponding to the first identifier to provide services; The second network element obtains a first intermediate result according to the first model; The second network element sends the first intermediate result to the third network element; The second network element receives the output from the third network element.

27. The method according to claim 25 or 26, characterized in that, It further includes: The second network element sends the output to the first network element.

28. The method according to any one of claims 24-27, characterized in that, The third message further includes information of a first object, and / or an identifier of the first object in the vertical federated task corresponding to the first identifier.

29. The method according to claim 28, wherein The second message further indicates a first mapping relationship and / or a second mapping relationship, where the first mapping relationship is an identifier of a network entity identifier in a vertical federated task corresponding to the first identifier, and the second mapping relationship is an identifier of a user entity identifier in a vertical federated task corresponding to the first identifier.

30. A communication device, characterized in that, It includes units or modules for performing the method according to any one of claims 1 to 29.

31. A communication device, characterized in that, The communication device includes at least one processor; the at least one processor is configured to perform the method according to any one of claims 1 to 29.

32. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a program, and when the program runs on a device, the device is caused to perform the method according to any one of claims 1 to 29.

33. A computer program product, characterized in that, The computer program product includes a program or instruction, and when the program or instruction is executed by a device, the device is caused to perform the method according to any one of claims 1 to 29.

Images