Communication method, communication system and communication device

Abstract

Disclosed are a communication method, a communication system and a communication device, applied to the field of communications, the method comprising: a first network element sending a first message to a second network element, the first message comprising an identifier of a first machine learning ML model and a first address; the first network element receives a first request through the first address, the first request comprises the identifier of the first ML model, and the first request is used for indicating that the second network element has the capability of using and / or monitoring the first ML model. Correspondingly, the second network element sends the first request through the first address, so that the second network element can obtain the model monitoring service.

Description

[0001] This application claims priority to Chinese Patent Application No. 202411219305.1, filed with the State Intellectual Property Office of China on August 30, 2024, entitled “A Communication Method, Communication System and Communication Device”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to a communication method, a communication system, and a communication device. Background Technology

[0003] In the field of communications, machine learning (ML) models combined with network data analytics functions (NWDAF) can provide analysis / prediction services in various scenarios. In the relevant process, the NWDAF containing the analytics logical function (AnLF) acts as the model consumer. After acquiring the ML model, it can use model monitoring services or functions to monitor the analytical accuracy of the ML model and / or provide analytical feedback to the model producer, i.e., the NWDAF containing the model training logical function (MTLF).

[0004] When using the model monitoring service, model consumers can send a model monitoring registration request to the model producer corresponding to the ML model they are using. However, the current network architecture contains multiple NWDAFs containing MTLFs, and how model consumers can send model monitoring registration requests to the model producers corresponding to the ML models is a problem that urgently needs to be solved. Summary of the Invention

[0005] This application provides a communication method, communication system, and communication device for a model consumer of an ML model to send a model monitoring registration request to the model producer of the ML model, thereby obtaining model monitoring services, ensuring the accuracy of ML model usage, and improving the overall performance of the communication system and user experience.

[0006] This application provides a communication method in its first aspect. This method is executed by a first network element, or by a portion of a component within the first network element (e.g., a processor, chip, or chip system), or by a logic module or software capable of implementing all or part of the functions of the first network element. In this first aspect and its possible implementations, the method is described using the example of execution by a first network element. In this method, the first network element sends a first message to a second network element. The first message includes an identifier of a first machine learning (ML) model and a first address. The first network element receives a first request through the first address. The first request includes the identifier of the first ML model and is used to instruct the second network element to have the ability to use and / or monitor the first ML model.

[0007] In this application, the first request is a model monitoring registration request. The first request received by the first network element through the first address originates from the second network element, which encapsulates the information to be sent (the first request) into a data packet. The data packet contains the source address (the address of the second network element), the destination address (the first address), the data itself, and possible control information (such as sequence number, checksum, etc.). The second network element then sends the data packet to the next node according to the routing policy, ultimately reaching the first network element.

[0008] In this application, the first network element is an NWDAF network element containing MTLF, which is the model producer of the first ML model. The second network element is an NWDAF network element containing AnLF, which is the model consumer of the first ML model. The model consumer needs authorization from the model producer to obtain the first ML model.

[0009] In this application, the first message is used to notify the model consumer of information about available ML models. The model producer sends the first message to the model consumer when it discovers or updates an ML model and determines that the ML model is useful to the model consumer.

[0010] For example, the first message is the Nnwdaf_MLModelProvision_Notify message. It can be understood that the first network element sends information about the first ML model to the second network element via the Nnwdaf_MLModelProvision_Notify message.

[0011] In this application, the first request is used to instruct the model consumer to have the ability to use and / or monitor the first ML model. The model consumer sends the first request to the model producer when it decides to provide analytical feedback information to the model producer regarding the accuracy of the analysis of the first ML model and / or the analytical results generated by the first ML model.

[0012] For example, the first request is an Nnwdaf_MLModelMonitor_Register message. It can be understood that the second network element reports to the first network element via the Nnwdaf_MLModelMonitor_Register message that it has the ability to use and / or monitor the first ML model.

[0013] Model consumers can obtain model monitoring services by sending a model monitoring registration request to the model producer. The model monitoring service can evaluate the performance of ML models in real-time within a real-world deployment environment, including key parameters such as prediction accuracy, processing speed, and resource utilization efficiency. Real-time monitoring quickly identifies any performance degradation or anomalies in the model, thereby ensuring the stability and efficiency of the entire system.

[0014] Based on the above scheme, the first network element conveys the destination address of the model monitoring registration request to the second network element by carrying the first address in the first message. The second network element can send the model monitoring registration request through the first address, which avoids the failure of sending the model registration request and ensures that the second network element can obtain the required model monitoring service.

[0015] In one possible implementation, before the first network element sends the first message to the second network element, the method further includes: the first network element receiving first indication information from the third network element, the first indication information being used to request the first address.

[0016] In one possible implementation, before the first network element sends the first message to the second network element, the method further includes: the first network element receiving a second request from a third network element, the second request including the identifier of the second network element, the second request being used to request the first ML model.

[0017] In this application, the third network element is an NWDAF network element containing MTLF, and the second request is a model subscription request. The third network element sends the model subscription request to the first network element on behalf of the second network element, acting as the model proxy requester for the first ML model. There is no direct communication between the first and second network elements. It can be understood that the first indication information is a "model monitoring registration indication," used to instruct the second network element to send the model monitoring registration request to the model producer after acquiring the ML model, thus requiring the model producer (first network element) to provide the first address. Alternatively, the first indication information can be a "model monitoring capability indication," used to instruct the second network element to have the capability to provide accuracy information for the analysis generated by the ML model and / or to provide analytical feedback information for the analysis generated by the ML model. Through this first indication information, the first address is actively requested.

[0018] In one possible implementation, the first network element is a server for federated learning (FL), and the first ML model is an ML model trained on the first network element based on FL.

[0019] In one possible implementation, the first request also includes the identifier of a second network element. The network element used to indicate the request model monitoring service is the second network element.

[0020] In one possible implementation, the method further includes: the first network element sending a second message to the second network element, the second message being used to monitor the first ML model.

[0021] In this application, after receiving the first request, the first network element decides to provide model monitoring services to the second network element. It sends a second message to the second network element; this second message is a response to the first request and is used to obtain accuracy information for monitoring the first ML model.

[0022] For example, the second message is the Nnwdaf_MLModelMonitor_Subscribe message.

[0023] In one possible implementation, the second message includes the monitoring registration identifier of the ML model.

[0024] A second aspect of this application provides a communication method, which is executed by a first network element, or by a portion of a component within the first network element (e.g., a processor, chip, or chip system), or by a logic module or software capable of implementing all or part of the functions of the first network element. In this second aspect and its possible implementations, the method is described using the execution of the first network element as an example. In this method, the first network element sends a first message to a second network element, the first message including an identifier of a first machine learning (ML) model and second indication information, the second indication information being used to identify the first network element; the first network element receives a first request, the first request including the identifier of the first ML model, the first request being used to instruct the second network element to have the ability to use and / or monitor the first ML model.

[0025] In this application, the first network element is an NWDAF network element containing MTLF, which is the model producer of the first ML model. The second network element is an NWDAF network element containing AnLF, which is the model consumer of the first ML model. After receiving the second indication information, the second network element can discover the first network element identified by the second indication information through the NRF network element.

[0026] In this application, the first message is used to notify the model consumer of information about available ML models. The model producer sends the first message to the model consumer when it discovers or updates an ML model and determines that the ML model is useful to the model consumer.

[0027] For example, the first message is the Nnwdaf_MLModelProvision_Notify message. It can be understood that the first network element sends information about the first ML model to the second network element via the Nnwdaf_MLModelProvision_Notify message.

[0028] In this application, the first request is used to instruct the model consumer to have the ability to use and / or monitor the first ML model. The model consumer sends the first request to the model producer when it decides to provide analytical feedback information to the model producer regarding the accuracy of the analysis of the first ML model and / or the analytical results generated by the first ML model.

[0029] For example, the first request is an Nnwdaf_MLModelMonitor_Register message. It can be understood that the second network element reports to the first network element via the Nnwdaf_MLModelMonitor_Register message that it has the ability to use and / or monitor the first ML model.

[0030] Based on the above scheme, the first network element carries the second indication information in the first message, which enables the second network element to discover the first network element based on the second indication information and send a model monitoring registration request to the first network element, thereby avoiding the failure of sending the model registration request and ensuring that the second network element can obtain the required model monitoring service.

[0031] In one possible implementation of the second aspect, the second instruction information includes one or more of the following:

[0032] Network function instance identifier of the first network element;

[0033] The Internet Protocol address (IP address) of the first network element can be an IPv4 address, an IPv6 address, or an IPv6 address prefix.

[0034] The port number of the first network element; or,

[0035] The fully qualified domain name of FirstNet.

[0036] In one possible implementation of the second aspect, before the first network element sends the first message, the method further includes:

[0037] The first network element receives a second request from the third network element. The second request includes the identifier of the second network element and is used to request the first ML model.

[0038] In this application, the third network element is an NWDAF network element containing MTLF, and the second request is a model subscription request. The third network element sends the model subscription request to the first network element on behalf of the second network element. The third network element is the model proxy requester of the first ML model, and there is no direct communication between the first network element and the second network element.

[0039] In one possible implementation, the first network element is an FL server, and the first ML model is an ML model trained on the first network element based on the FL server.

[0040] In one possible implementation of the second aspect, the first request also includes the identifier of the second network element.

[0041] In one possible implementation of the second aspect, the method further includes: the first network element sending a second message to the second network element, the second message being used to monitor the first ML model.

[0042] In this application, after receiving the first request, the first network element decides to provide model monitoring services to the second network element. It sends a second message to the second network element; this second message is a response to the first request and is used to obtain accuracy information for monitoring the first ML model.

[0043] For example, the second message is the Nnwdaf_MLModelMonitor_Subscribe message.

[0044] In one possible implementation, the second message includes the monitoring registration identifier of the ML model.

[0045] The second aspect of this application provides another communication method, which is executed by a first network element, or by a component (e.g., a processor, chip, or chip system) within the first network element, or by a logic module or software capable of implementing all or part of the functions of the first network element. In the second aspect and its possible implementations, the method is described as being executed by a first network element. In this method, the first network element receives a second request from a third network element, the second request including an identifier of the second network element, and the second request is used to request a first machine learning (ML) model. The third network element requests the first ML model from the first network element on behalf of the second network element. The first network element sends a first message to the second network element, the first message including an identifier of the first ML model and second indication information, the second indication information being used to identify the first network element. The first network element receives the first request, the first request including the identifier of the first ML model, the first request being used to indicate that the second network element has the ability to use and / or monitor the first ML model.

[0046] In this application, the third network element is an NWDAF network element containing MTLF, and the second request is a model subscription request. The third network element sends the model subscription request to the first network element on behalf of the second network element. The third network element is a model proxy requester of the first ML model, and there is no direct communication between the first network element and the second network element. Alternatively, the second network element requests the first ML model from the first network element through the third network element. A third aspect of this application provides a communication method, which is executed by the first network element, or by some components (e.g., processor, chip, or chip system) of the first network element, or by a logic module or software capable of implementing all or part of the functions of the first network element. In the third aspect and its possible implementations, the method is described as being executed by the first network element. In this method, a first network element receives a second request from a third network element. The second request includes a notification target address of the second network element and a notification target address of the third network element. The second request is used to request a first machine learning (ML) model. The first network element sends a first message through the notification target address of the second network element. The first message includes the identifier of the first ML model. The first network element sends a second message through the notification target address of the third network element. The second message includes the identifier of the first ML model.

[0047] In this application, the first network element is an NWDAF network element containing MTLF, which is the model producer of the first ML model. The second network element is an NWDAF network element containing AnLF, which is the model consumer of the first ML model. The third network element is an NWDAF network element containing MTLF. The second request is a model subscription request. The third network element sends the model subscription request to the first network element on behalf of the second network element, and is the model proxy requester of the first ML model. There is no direct communication between the first network element and the second network element.

[0048] In this application, the first message is used to notify the model consumer of information about available ML models. The model producer sends the first message to the model consumer when it discovers or updates an ML model and determines that the ML model is useful to the model consumer.

[0049] For example, the first message is the Nnwdaf_MLModelProvision_Notify message. It can be understood that the first network element sends information about the first ML model to the second network element via the Nnwdaf_MLModelProvision_Notify message.

[0050] For example, the second message is an Nnwdaf_MLModelProvision_Notify message. It can be understood that the first network element sends the information of the first ML model to the third network element via the Nnwdaf_MLModelProvision_Notify message. Alternatively, it can be understood that the first network element sends the information of the first ML model to both the second and third network elements respectively.

[0051] In one possible implementation of the third aspect, the method further includes:

[0052] The first network element receives a fifth request from the third network element. The fifth request includes the identifier of the first ML model and the identifier of the second network element. The fifth request is used to indicate that the second network element has the ability to use and / or monitor the first ML model.

[0053] In this application, the fifth request is used to instruct the model consumer to have the ability to use and / or monitor the first ML model. When the model consumer decides to provide the model producer with analytical feedback information on monitoring the analytical accuracy of the first ML model and / or providing analytical results generated by the first ML model, the model proxy requester sends the fifth request to the model producer on behalf of the model consumer.

[0054] For example, the fifth request is the Nnwdaf_MLModelMonitor_Register message.

[0055] Based on the above scheme, after accepting a subscription request, the first network element sends information about the first ML model, including its identifier, to the second and third network elements. The third network element learns that the model producer of the first ML model is the first network element. When the third network element receives a model monitoring registration request from the model consumer (the second network element), it can match the request with locally maintained information and then send a model monitoring registration request to the model producer (the first network element) corresponding to the first ML model on behalf of the second network element, enabling the second network element to obtain model monitoring services.

[0056] In one possible implementation of the third aspect, the method further includes: the first network element sending a third message to the second network element, the third message being used to monitor the first ML model.

[0057] In this application, after receiving the first request, the first network element decides to provide model monitoring services to the second network element. A second message is sent to the second network element, and a third message is a response to the first request, used to obtain accuracy information for monitoring the first ML model.

[0058] For example, the second message is the Nnwdaf_MLModelMonitor_Subscribe message.

[0059] In one possible implementation, the third message includes the monitoring registration identifier of the ML model.

[0060] The fourth aspect of this application provides a communication method, which is executed by a second network element, or by a portion of a component (e.g., a processor, chip, or chip system) within the second network element, or by a logic module or software capable of implementing all or part of the functions of the second network element. In this fourth aspect and its possible implementations, the method is described as being executed by a second network element. In this method, the second network element receives a first message from a first network element, the first message including an identifier of a first machine learning (ML) model and a first address; the second network element sends a first request through the first address, the first request including the identifier of the first ML model, the first request being used to indicate that the second network element has the ability to use and / or monitor the first ML model.

[0061] In this application, the first network element is an NWDAF network element containing MTLF, which is the model producer of the first ML model. The second network element is an NWDAF network element containing AnLF, which is the model consumer of the first ML model.

[0062] In this application, the first message is used to notify the model consumer of information about available ML models. The model producer sends the first message to the model consumer when it discovers or updates an ML model and determines that the ML model is useful to the model consumer.

[0063] For example, the first message is the Nnwdaf_MLModelProvision_Notify message. It can be understood that the first network element sends information about the first ML model to the second network element via the Nnwdaf_MLModelProvision_Notify message.

[0064] In this application, the first request is used to instruct the model consumer to have the ability to use and / or monitor the first ML model. The model consumer sends the first request to the model producer when it decides to provide analytical feedback information to the model producer regarding the accuracy of the analysis of the first ML model and / or the analytical results generated by the first ML model.

[0065] For example, the first request is an Nnwdaf_MLModelMonitor_Register message. It can be understood that the second network element reports to the first network element via the Nnwdaf_MLModelMonitor_Register message that it has the ability to use and / or monitor the first ML model.

[0066] In this application, the second network element sends the first request through the first address, and encapsulates the information to be sent (the first request) into a data packet. The data packet contains the source address (the address of the second network element), the destination address (the first address), the data itself, and possible control information (such as sequence number, checksum, etc.). The second network element then sends the data packet to the next node according to the routing policy, eventually reaching the first network element.

[0067] Based on the above scheme, the first network element conveys the destination address of the model monitoring registration request to the second network element by carrying the first address in the first message. The second network element can send the model monitoring registration request through the first address, which avoids the failure of sending the model registration request and ensures that the second network element can obtain the required model monitoring service.

[0068] In one possible implementation of the fourth aspect, before the second network element receives the first message, the method further includes:

[0069] The second network element sends a first instruction message to the third network element. The first instruction message is used to request a first address.

[0070] In one possible implementation of the fourth aspect, the first request also includes the identifier of the second network element.

[0071] In one possible implementation of the fourth aspect, the method further includes: the second network element receiving a second message from the first network element, the second message being used to monitor the first ML model.

[0072] In this application, after receiving the first request, the first network element decides to provide model monitoring services to the second network element. It sends a second message to the second network element; this second message is a response to the first request and is used to obtain accuracy information for monitoring the first ML model.

[0073] For example, the second message is the Nnwdaf_MLModelMonitor_Subscribe message.

[0074] In one possible implementation, the second message includes the monitoring registration identifier of the ML model.

[0075] The fifth aspect of this application provides a communication method, which is executed by a second network element, or by a portion of a component (e.g., a processor, chip, or chip system) within the second network element, or by a logic module or software capable of implementing all or part of the functions of the second network element. In this fifth aspect and its possible implementations, the method is described as being executed by a second network element. In this method, the second network element receives a first message from a first network element, the first message including an identifier of a first machine learning (ML) model and second indication information, the second indication information being used to identify the first network element; the second network element then sends a first request to the first network element, the first request including the identifier of the first ML model, the first request being used to indicate that the second network element has the capability to use and / or monitor the first ML model.

[0076] In this application, the first network element is an NWDAF network element containing MTLF, which is the model producer of the first ML model. The second network element is an NWDAF network element containing AnLF, which is the model consumer of the first ML model.

[0077] In this application, the first message is used to notify the model consumer of information about available ML models. The model producer sends the first message to the model consumer when it discovers or updates an ML model and determines that the ML model is useful to the model consumer.

[0078] For example, the first message is the Nnwdaf_MLModelProvision_Notify message. It can be understood that the first network element sends information about the first ML model to the second network element via the Nnwdaf_MLModelProvision_Notify message.

[0079] In this application, the first request is used to instruct the model consumer to have the ability to use and / or monitor the first ML model. The model consumer sends the first request to the model producer when it decides to provide analytical feedback information to the model producer regarding the accuracy of the analysis of the first ML model and / or the analytical results generated by the first ML model.

[0080] For example, the first request is an Nnwdaf_MLModelMonitor_Register message. It can be understood that the second network element reports to the first network element via the Nnwdaf_MLModelMonitor_Register message that it has the ability to use and / or monitor the first ML model.

[0081] In one possible implementation of the fifth aspect, the second instruction information includes one or more of the following:

[0082] Network function instance identifier of the first network element;

[0083] The Internet Protocol address (IP address) of the first network element can be an IPv4 address, an IPv6 address, or an IPv6 address prefix.

[0084] The port number of the first network element; or,

[0085] The fully qualified domain name of FirstNet.

[0086] In one possible implementation of the fifth aspect, the second network element sends a first request to the first network element, including: the second network element sending a fourth request to the network storage function network element, the fourth request including second indication information; the second network element receiving a first configuration file from the network storage function network element, the first configuration file including one or more configuration information of the first network element; and the second network element sending the first request to the first network element based on the first configuration file.

[0087] In one possible implementation of the fifth aspect, the second network element obtains the second indication information through the certificate in the first message. Specifically, the first network element is a client of the Transport Layer Security (TLS) session, and the second network element is a server receiving the first message. Based on the TLS certificate of the TLS session client, the second network element determines one or more of the following information of the first network element: NF ID, IP address, port number, or FQDN, etc.

[0088] Based on the above scheme, the first network element carries the second indication information in the first message, which enables the second network element to discover the first network element based on the second indication information and send a model monitoring registration request to the first network element, thereby avoiding the failure of sending the model registration request and ensuring that the second network element can obtain the required model monitoring service.

[0089] In one possible implementation of the fifth aspect, the method further includes: the second network element receiving a second message from the first network element, the second message being used to monitor the first ML model.

[0090] In this application, after receiving the first request, the first network element decides to provide model monitoring services to the second network element. It sends a second message to the second network element; this second message is a response to the first request and is used to obtain accuracy information for monitoring the first ML model.

[0091] For example, the second message is the Nnwdaf_MLModelMonitor_Subscribe message.

[0092] In one possible implementation, the second message includes the monitoring registration identifier of the ML model.

[0093] The sixth aspect of this application provides a communication method, which is executed by a third network element, or by a portion of a component (e.g., a processor, chip, or chip system) within the third network element, or by a logic module or software capable of implementing all or part of the functions of the third network element. In the sixth aspect and its possible implementations, the method is described as being executed by a third network element. In this method, the third network element receives a first message from a first network element, the first message including an identifier of a first machine learning (ML) model; the third network element receives a first request from a second network element, the first request including the identifier of the first ML model, the first request indicating that the second network element has the ability to use and / or monitor the first ML model; the third network element sends a fifth request to the first network element, the fifth request including the identifier of the first ML model and the identifier of the second network element, the fifth request indicating that the second network element has the ability to use and / or monitor the first ML model.

[0094] In this application, the first network element is an NWDAF network element containing MTLF, which is the model producer of the first ML model. The second network element is an NWDAF network element containing AnLF, which is the model consumer of the first ML model. The third network element is an NWDAF network element containing MTLF, which is the model proxy requester of the first ML model.

[0095] In this application, the first message is used to notify the model consumer of information about available ML models. The model producer sends the first message to the model consumer when it discovers or updates an ML model and determines that the ML model is useful to the model consumer.

[0096] For example, the first message is the Nnwdaf_MLModelProvision_Notify message. It can be understood that the first network element sends information about the first ML model to the second network element via the Nnwdaf_MLModelProvision_Notify message.

[0097] In this application, the first request and the fifth request are used to instruct the model consumer to have the ability to use and / or monitor the first ML model. When the model consumer decides to provide the model producer with analytical feedback information on monitoring the analytical accuracy of the first ML model and / or providing analytical results generated by the first ML model, the model consumer sends the first request to the model agent requester, and the model agent requester sends the fifth request to the model producer on behalf of the model consumer. The fifth request carries the identifier of the model consumer.

[0098] For example, the first request is the Nnwdaf_MLModelMonitor_Register message.

[0099] For example, the fifth request is the Nnwdaf_MLModelMonitor_Register message. The fifth request sent by the third network element to the first network element is a model monitoring registration request, which can be understood as sending a request to the first network element on behalf of the second network element, or as sending a request directly to the first network element, requesting model monitoring registration for the second network element.

[0100] Based on the above scheme, the third network element maintains the relationship between the ML model and the corresponding model producer, so that the third network element can act as an intermediary coordinator, responsible for receiving the first request from the second network element, and then sending the fifth request, namely the model monitoring registration request, to the first network element on behalf of the second network element, so that the second network element can obtain the model monitoring service.

[0101] In one possible implementation of the sixth aspect, before the third network element receives the first message from the first network element, the method further includes: the third network element receiving a third request from the second network element, the third request being used to request the first ML model; the third network element determining the first network element based on the third request, the first network element being the provider of the first ML model; the third network element sending a second request to the first network element, the second request including the identifier of the second network element, the second request being used to request the first ML model.

[0102] In one possible implementation of the sixth aspect, the second request includes the notification target address of the second network element and the notification target address of the third network element.

[0103] Based on the above scheme, the third network element carries the model consumer and its own notification target address in the second request. When the first network element sends the model notification message (first message), the third network element can also receive the first message, so that the third network element can maintain the association between the ML model and the corresponding model producer.

[0104] The seventh aspect of this application provides a communication method, which is executed by a first network element, or by some components (e.g., a processor, chip, or chip system) of the first network element, or by a logic module or software capable of implementing all or part of the functions of the first network element. In the seventh aspect and its possible implementations, the method is described as being executed by a first network element. In this method, the first network element receives a first request from a third network element. The first request includes an identifier of a second network element, an analysis identifier, and a notification target address of the second network element. The first request indicates that the third network element, on behalf of the second network element, requests the provision of a machine learning (ML) model corresponding to the analysis identifier. The first network element sends a first message through the notification target address. The first message includes an identifier of the ML model and a first interoperability identifier, which corresponds to the analysis identifier.

[0105] The first interoperability identifier includes a first vendor identifier list. Based on the first vendor identifier list, the second network element can obtain one or more AnLF network elements through the NRF network element and determine the target AnLF network element from them.

[0106] In this application, the first network element is an NWDAF network element containing MTLF, which is the model producer of the ML model. The second network element is an NWDAF network element containing AnLF, which is the model consumer of the ML model. Due to internal reasons (e.g., load balancing, graceful shutdown) or external triggers (e.g., user equipment (UE) mobility), the second network element needs to obtain one or more AnLF network elements through the NRF network element, and determine the fourth network element (target AnLF network element) from them, and transfer the analysis subscription to the fourth network element. If the fourth network element accepts the analysis subscription request, it will send an Nnwdaf_AnalyticsSubscription_Subscribe response containing the subscription association ID. The fourth network element can use the analysis context transfer request (Nnwdaf_AnalyticsInfo_ContextTransfer) to request and obtain the analysis context.

[0107] Based on the above scheme, the second network element can obtain one or more AnLF network elements through the NRF network element. The vendor to which these one or more AnLF network elements belong can obtain the ML model from the first network element. The second network element determines the fourth network element (i.e., the target AnLF network element) from the candidate one or more AnLF network elements. Therefore, after the analysis subscription is transferred to the fourth network element, the fourth network element can continue to use the ML model provided by the first network element, which can ensure service continuity.

[0108] The eighth aspect of this application provides a communication method, which is executed by a second network element, or by a portion of a component (e.g., a processor, chip, or chip system) within the second network element, or by a logic module or software capable of implementing all or part of the functions of the second network element. In the eighth aspect and its possible implementations, the method is described as being executed by a second network element. In this method, the second network element sends a first request to the third network element. The first request includes an analysis identifier and is used to request the machine learning (ML) model corresponding to the analysis identifier. The second network element receives a first message from the first network element. The first message includes an identifier for the ML model and a first interoperability identifier. The first interoperability identifier includes or is a list of first vendor identifiers, and the first interoperability identifier corresponds to the analysis identifier. The second network element sends a second request to the network storage function network element. The second request includes a list of second vendor identifiers, which is a subset of the first vendor identifier list. The second network element receives information from the fourth network element of the network storage function network element. The information of the fourth network element is used to identify the fourth network element. The vendor identifier of the fourth network element is one of the vendor identifiers in the second vendor identifier list. The second network element sends a third request to the fourth network element. The third request includes analysis subscription information corresponding to the analysis identifier.

[0109] In this application, the first network element is an NWDAF network element containing an MTLF, which is the model producer of the ML model. The second network element is an NWDAF network element containing an AnLF, which is the model consumer of the ML model. Due to internal reasons (e.g., load balancing, graceful shutdown) or external triggers (e.g., user equipment (UE) mobility), the second network element needs to find another suitable AnLF network element, i.e., the target AnLF network element, to transfer the analytics subscription. If the fourth network element accepts the analytics subscription request, it will send an Nnwdaf_AnalyticsSubscription_Subscribe response containing the subscription association ID. The fourth network element can use an analytics context transfer request (Nnwdaf_AnalyticsInfo_ContextTransfer) to request and obtain the analytics context.

[0110] Based on the above scheme, the first interoperability identifier of the first network element can determine which vendors' NWDAFs can request ML models provided by the first network element. The second network element can obtain one or more AnLF network elements through the NRF network element; the vendors to which these AnLF network elements belong can obtain ML models from the first network element. The second network element then determines the fourth network element (i.e., the target AnLF network element) from the candidate AnLF network elements. Therefore, after the analysis subscription is transferred to the fourth network element, the fourth network element can continue to use the ML model provided by the first network element, ensuring service continuity.

[0111] A ninth aspect of this application provides a communication system comprising a first network element and a second network element; wherein the first network element is used to send a first message to the second network element, the first message including an identifier of a first machine learning (ML) model and a first address; the second network element sends a first request to the first network element through the first address, the first request including the identifier of the first ML model, the first request being used to instruct the second network element to have the ability to use and / or monitor the first ML model; and the first network element receives the first request.

[0112] In one possible implementation of the ninth aspect, the communication system further includes: a third network element, which is used to send first indication information to the first network element, the first indication information being used to request the first address.

[0113] In one possible implementation of the ninth aspect, the communication system further includes: a first network element sending a second message to a second network element, the second message being used to monitor the first ML model; and the second network element receiving the second message.

[0114] In one possible implementation of the ninth aspect, the second message includes the monitoring registration identifier of the ML model.

[0115] The tenth aspect of this application provides a communication system comprising a first network element and a second network element; wherein the first network element is used to send a first message to the second network element, the first message including an identifier of a first machine learning (ML) model and second indication information, the second indication information being used to identify the first network element; the second network element sends a first request to the first network element, the first request including the identifier of the first ML model, the first request being used to indicate that the second network element has the ability to use and / or monitor the first ML model; the first network element receives the first request.

[0116] In one possible implementation of the tenth aspect, the communication system further includes a third network element for sending a second request to the first network element, the second request including the identifier of the second network element, the second request being for requesting the first ML model.

[0117] In one possible implementation of the tenth aspect, the communication system further includes: a first network element sending a second message to a second network element, the second message being used to monitor a first ML model; and the second network element receiving the second message.

[0118] In one possible implementation of the tenth aspect, the second message includes the monitoring registration identifier of the ML model.

[0119] The eleventh aspect of this application provides a communication system comprising a first network element, a second network element, and a third network element; wherein the first network element is configured to send a first message to the second network element, the first message including an identifier of a first machine learning (ML) model; the first network element is further configured to send a second message to the third network element, the second message including the identifier of the first ML model; the second network element is configured to send a first request to the third network element, the first request including the identifier of the first ML model, the first request indicating that the second network element has the capability to use and / or monitor the first ML model; the third network element sends a fifth request to the first network element, the fifth request including the identifier of the first ML model and the identifier of the second network element, the fifth request indicating that the second network element has the capability to use and / or monitor the first ML model. The first network element receives the fifth request.

[0120] In one possible implementation of the eleventh aspect, the communication system further includes: a first network element sending a third message to a second network element, the third message being used to monitor the first ML model; and the second network element receiving the third message.

[0121] In one possible implementation of the eleventh aspect, the third message includes the monitoring registration identifier of the ML model.

[0122] The twelfth aspect of this application provides a communication system comprising a first network element, a second network element, a third network element, and a fourth network element; wherein the second network element is used to send a first request to the third network element, the first request including an analysis identifier, the first request being used to request the provision of a machine learning (ML) model corresponding to the service corresponding to the analysis identifier; the third network element sends a fourth request to the first network element, the fourth request including an analysis identifier, an identifier of the second network element, and a notification target address of the second network element, the fourth request being used to indicate that the third network element, on behalf of the second network element, requests the provision of the ML model corresponding to the analysis identifier.

[0123] The first network element sends a first message to the second network element through the notification target address. The first message includes the identifier of the ML model and a first interoperability identifier. The first interoperability identifier includes a first vendor identifier list, and the first interoperability identifier corresponds to the analysis identifier. The second network element sends a second request to the network storage function network element. The second request includes a second vendor identifier list, which is a subset of the first vendor identifier list. The second network element receives information from a fourth network element from the network storage function network element. The information of the fourth network element is used to identify the fourth network element. The vendor identifier of the fourth network element is one of the vendor identifiers in the second vendor identifier list. The second network element sends a third request to the fourth network element. The third request is used to request the analysis subscription transfer.

[0124] The thirteenth aspect of this application provides a communication device, which is a first network element. The device includes a transceiver unit and a processing unit. The processing unit is used to determine a first message, which includes an identifier of a first machine learning (ML) model and a first address. The transceiver unit is used to send the first message to a second network element. The transceiver unit is also used to receive a first request through the first address, which includes the identifier of the first ML model. The first request is used to instruct the second network element to have the ability to use and / or monitor the first ML model.

[0125] In the thirteenth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the first aspect and achieve the corresponding technical effects, all of which can be referred to the first aspect and will not be repeated here.

[0126] The fourteenth aspect of this application provides a communication device, which is a first network element. The device includes a transceiver unit and a processing unit. The processing unit is used to determine a first message, which includes an identifier of a first machine learning (ML) model and second indication information, the second indication information being used to identify the first network element. The transceiver unit is used to send the first message to a second network element. The transceiver unit is also used to receive a first request, which includes the identifier of the first ML model and is used to instruct the second network element to have the ability to use and / or monitor the first ML model.

[0127] In the fourteenth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the second aspect and achieve the corresponding technical effects. For details, please refer to the second aspect, which will not be repeated here.

[0128] The fifteenth aspect of this application provides a communication apparatus, which is a first network element, comprising a transceiver unit and a processing unit; the transceiver unit is configured to receive a second request from a third network element, the second request including a notification target address of the second network element and a notification target address of the third network element, the second request being used to request a first machine learning (ML) model; the processing unit is configured to determine a first message, the first message including an identifier of the first ML model; the transceiver unit is further configured to send the first message through the notification target address of the second network element; the transceiver unit is further configured to send the first message through the notification target address of the third network element.

[0129] In the fifteenth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the third aspect and achieve the corresponding technical effects, all of which can be referred to the third aspect for details, and will not be repeated here.

[0130] The sixteenth aspect of this application provides a communication device, which is a second network element. The device includes a transceiver unit and a processing unit. The transceiver unit is used to receive a first message from a first network element. The first message includes an identifier of a first machine learning (ML) model and a first address. The processing unit is used to determine a first request. The first request includes the identifier of the first ML model. The first request is used to instruct the second network element to have the ability to use and / or monitor the first ML model. The transceiver unit is also used to send the first request through the first address.

[0131] In the sixteenth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the fourth aspect and achieve the corresponding technical effects. For details, please refer to the fourth aspect, which will not be repeated here.

[0132] The seventeenth aspect of this application provides a communication device, which is a second network element. The device includes a transceiver unit and a processing unit. The transceiver unit is used to receive a first message from a first network element. The first message includes an identifier of a first machine learning (ML) model and second indication information, which is used to identify the first network element. The processing unit is used to determine a first request. The first request includes the identifier of the first ML model and is used to instruct the second network element to have the ability to use and / or monitor the first ML model. The transceiver unit is also used to send the first request.

[0133] In the seventeenth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the fifth aspect and achieve the corresponding technical effects. For details, please refer to the fifth aspect, which will not be repeated here.

[0134] The eighteenth aspect of this application provides a communication device, which is a third network element. The device includes a transceiver unit and a processing unit. The transceiver unit is configured to receive a first message from a first network element, the first message including an identifier of a first machine learning (ML) model. The transceiver unit is also configured to receive a first request from a second network element, the first request including the identifier of the first ML model, the first request indicating that the second network element has the ability to use and / or monitor the first ML model. The processing unit is configured to determine a fifth request, the fifth request including the identifier of the first ML model and the identifier of the second network element, the fifth request indicating that the second network element has the ability to use and / or monitor the first ML model. The transceiver unit is also configured to send the fifth request to the first network element.

[0135] In the eighteenth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the sixth aspect and achieve the corresponding technical effects, all of which can be referred to the sixth aspect, and will not be repeated here.

[0136] The nineteenth aspect of this application provides a communication device, which is a first network element. The device includes a transceiver unit and a processing unit. The transceiver unit is used to receive a first request from a third network element. The first request includes an identifier of a second network element, an analysis identifier, and a notification target address of the second network element. The first request indicates that the third network element, on behalf of the second network element, requests the provision of a machine learning (ML) model corresponding to the analysis identifier. The transceiver unit is also used to send a first message through the notification target address. The first message includes an identifier of the ML model and a first interoperability identifier, which corresponds to the analysis identifier.

[0137] In the nineteenth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the seventh aspect and achieve the corresponding technical effects, all of which can be referred to the seventh aspect, and will not be repeated here.

[0138] A twentieth aspect of this application provides a communication device, which is a second network element. The device includes a transceiver unit and a processing unit. The transceiver unit is configured to send a first request to a third network element. The first request includes an analysis identifier and is used to request the provision of a machine learning (ML) model corresponding to the analysis identifier. The transceiver unit is also configured to receive a first message from a first network element. The first message includes an identifier of the ML model and a first interoperability identifier. The first interoperability identifier includes or may include a first vendor identifier list, and the first interoperability identifier corresponds to the analysis identifier. The transceiver unit is also configured to send a second request to a network storage function network element. The second request includes a second vendor identifier list, which is a subset of the first vendor identifier list. The transceiver unit is also configured to receive information from a fourth network element of the network storage function network element. The information of the fourth network element is used to identify the fourth network element. The vendor identifier of the fourth network element is one of the vendor identifiers in the second vendor identifier list. The transceiver unit is also configured to send a third request to the fourth network element. The third request includes analysis subscription information corresponding to the analysis identifier.

[0139] In the twentieth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the eighth aspect and achieve the corresponding technical effects, all of which can be referred to the eighth aspect, and will not be repeated here.

[0140] The twenty-first aspect of this application provides a communication device including at least one processor coupled to a memory; the memory is used to store a program or instructions; the at least one processor is used to execute the program or instructions to cause the device to implement the method described in any possible implementation of any of the first to eighth aspects. Optionally, the communication device may include the memory.

[0141] The 22nd aspect of this application provides a communication device including at least one logic circuit and an input / output interface; the logic circuit is used to perform the method described in any of the possible implementations of the first to eighth aspects described above.

[0142] The twenty-third aspect of this application provides a computer-readable storage medium for storing one or more computer-executable instructions, which, when executed by a processor, perform the method as described in any possible implementation of any of the first to eighth aspects described above.

[0143] The twenty-fourth aspect of this application provides a computer program product (or computer program) that, when executed by a processor, performs the method described in any possible implementation of any of the first to eighth aspects described above.

[0144] The twenty-fifth aspect of this application provides a chip or chip system including at least one processor for supporting a communication device in implementing the methods described in any possible implementation of any of the first to eighth aspects. For example, the chip may be a baseband chip, a modem chip, a SoC chip (such as an SoC chip containing a modem core), a SIP chip, or a communication module, etc.

[0145] In one possible design, the chip or chip system may further include a memory for storing program instructions and data necessary for the communication device. The chip system may be composed of chips or may include chips and other discrete devices. Optionally, the chip system may also include interface circuitry that provides program instructions and / or data to the at least one processor.

[0146] The technical effects of any of the design methods in aspects thirteen to twenty-five can be found in the technical effects of the different design methods in aspects one to eight above, and will not be repeated here. Attached Figure Description

[0147] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0148] Figure 1 This is a schematic diagram of a service-oriented architecture-based network architecture;

[0149] Figure 2 This is a schematic diagram of a network architecture based on a point-to-point interface;

[0150] Figure 3 An interactive schematic diagram of a communication method provided in an embodiment of this application;

[0151] Figure 4a This is another interactive schematic diagram of a communication method provided in an embodiment of this application;

[0152] Figure 4b This is another interactive schematic diagram of a communication method provided in an embodiment of this application;

[0153] Figure 5 This is another interactive schematic diagram of a communication method provided in an embodiment of this application;

[0154] Figure 6a This is another interactive schematic diagram of a communication method provided in an embodiment of this application;

[0155] Figure 6b This is another interactive schematic diagram of a communication method provided in an embodiment of this application;

[0156] Figure 7 This is a schematic diagram of one embodiment of the communication device in this application;

[0157] Figure 8 This is a schematic diagram of another embodiment of the communication device in this application;

[0158] Figure 9 This is a schematic diagram of another embodiment of the communication device in this application;

[0159] Figure 10 This is a schematic diagram of another embodiment of the communication device in this application. Detailed Implementation

[0160] First, some terms used in the embodiments of this application will be explained to facilitate understanding by those skilled in the art.

[0161] (1) Terminal device: can be a wireless terminal device that can receive network device scheduling and instruction information. The wireless terminal device can be a device that provides voice and / or data connectivity to the user, or a handheld device with wireless connection function, or other processing device connected to a wireless modem.

[0162] Terminal devices can communicate with one or more core networks or the Internet via a radio access network (RAN). Terminal devices can be mobile terminal devices, such as mobile phones (or "cellular" phones), computers, and data cards. For example, they can be portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile devices that exchange voice and / or data with the RAN. Examples include personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablets, and computers with wireless transceiver capabilities. Wireless terminal equipment can also be referred to as a system, subscriber unit, subscriber station, mobile station, mobile station (MS), remote station, access point (AP), remote terminal, access terminal, user terminal, user agent, subscriber station (SS), customer premises equipment (CPE), terminal, user equipment (UE), mobile terminal (MT), drone, etc. Terminal equipment can also be wearable devices and next-generation communication systems, such as terminal equipment in 5G communication systems or terminal equipment in future public land mobile networks (PLMNs).

[0163] (2) Network equipment: This can be equipment within a wireless network. For example, network equipment can be a radio access network (RAN) node (or device) that connects terminal devices to the wireless network, and can also be called a base station. Currently, some examples of RAN equipment include: generation Node B (gNodeB), transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), basestation controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved Node B, or home Node B (HNB)), base band unit (BBU), or wireless fidelity (Wi-Fi) access point (AP), etc. In addition, in a network structure, network equipment can include centralized unit (CU) nodes, distributed unit (DU) nodes, or RAN equipment including CU nodes and DU nodes.

[0164] In some implementations, the network equipment may also include satellites, aircraft, drones, and ground station equipment connected to satellites, aircraft, and drones.

[0165] Specifically, network devices can send configuration information to terminal devices (e.g., carried in scheduling messages and / or indication messages). The terminal devices then configure their networks based on this information, aligning the network configurations of the network devices and terminal devices. Alternatively, network configurations can be pre-set in both the network devices and the terminal devices to achieve alignment. In essence, "alignment" means that when there are interactive messages between the network devices and terminal devices, their understanding of the carrier frequency for sending and receiving interactive messages, the determination of the interactive message type, the meaning of the fields carried in the interactive messages, or other configurations of the interactive messages is consistent.

[0166] Furthermore, in other possible cases, the network device can be any other device that provides wireless communication functionality to the terminal device. The embodiments of this application do not limit the specific technology or device form used in the network device. For ease of description, the embodiments of this application are not limited.

[0167] In this application embodiment, the device for implementing the function of the network device can be the network device itself, or it can be a device capable of supporting the network device in implementing that function, such as a chip system, which can be installed in the network device. In the technical solutions provided in this application embodiment, the example of a network device being used to implement the function of the network device is used to describe the technical solutions provided in this application embodiment.

[0168] (3) Configuration and Pre-configuration: In this application, both configuration and pre-configuration are used. Configuration refers to the network device sending configuration information or parameter values ​​of some parameters to the terminal device through messages or signaling, so that the terminal device can determine the communication parameters or resources during transmission based on these values ​​or information. Pre-configuration is similar to configuration; it can be parameter information or parameter values ​​that the network device and the terminal device have negotiated in advance, or it can be parameter information or parameter values ​​that the network device or the terminal device uses as specified by the standard protocol, or it can be parameter information or parameter values ​​that are pre-stored in the network device or the terminal device. This application does not limit this.

[0169] Furthermore, these values ​​and parameters can be changed or updated.

[0170] (4) The terms "system" and "network" in the embodiments of this application can be used interchangeably. "At least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "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.

[0171] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers described above does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0172] (5) In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include sending directly through the air interface or sending indirectly through the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include receiving directly from YY through the air interface or receiving indirectly from YY through the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0173] In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via buses, wiring, or interfaces.

[0174] It is understandable that information may undergo necessary processing, such as encoding and modulation, between the source and destination, but the destination can understand the valid information from the source. Similar statements in this application can be interpreted in a similar way and will not be elaborated further.

[0175] (6) In the embodiments of this application, "instruction" may include direct instruction and indirect instruction, as well as explicit instruction and implicit instruction. The information indicated by a certain piece of information (as described below, the instruction information) is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is an association between the other information and the information to be instructed; or it can only indicate a part of the information to be instructed, while the other parts of the information to be instructed are known or pre-agreed upon. For example, the instruction can be implemented by using a pre-agreed (e.g., protocol predefined) arrangement order of various information, thereby reducing the instruction overhead to a certain extent. This application does not limit the specific method of instruction. It is understood that for the sender of the instruction information, the instruction information can be used to indicate the information to be instructed, and for the receiver of the instruction information, the instruction information can be used to determine the information to be instructed.

[0176] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, and the various methods / designs / implementations within each embodiment, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the various methods / designs / implementations within each embodiment are consistent and can be mutually referenced. The technical features in different embodiments and the various methods / designs / implementations within each embodiment can be combined to form new embodiments, methods, or implementations based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0177] (7) Federated learning (FL).

[0178] The Federated Learning (FL) framework consists of a central node and at least one distributed node. The dataset resides on the distributed nodes (e.g., clients). Each distributed node collects its local dataset, performs local training, and reports the local results (model or gradients) to the central node. The central node itself may not have a dataset; it can be responsible for fusing the training results from the distributed nodes to obtain a global model, which is then distributed back to the distributed nodes. The concept of Federated Learning effectively addresses the current challenges in AI development by enabling efficient model learning through collaboration between edge devices and the central server, while fully protecting user data privacy and security.

[0179] (8) Analysis ID.

[0180] An analysis identifier can be used to indicate an analysis task or service, or simply a service. This service is associated with a model; that is, the model can be used to execute the service. Alternatively, the analysis identifier is associated with a model; that is, the model is used to execute the service corresponding to the analysis identifier.

[0181] Alternatively, it can be understood that MTLF is associated with an analytics identifier, meaning that the model provided by the MTLF supports the execution of the service corresponding to that analytics identifier. For example, an MTLF can be associated with one or more analytics identifiers. This can be understood as the MTLF providing an ML model for the service corresponding to each of the one or more analytics identifiers. For instance, if MTLF1 is associated with analytics identifier 1 and analytics identifier 2, meaning MTLF1 corresponds to analytics identifier 1 and analytics identifier 2, then MTLF1 can provide an ML model for the service corresponding to analytics identifier 1, and an ML model for the service corresponding to analytics identifier 2.

[0182] (9) Vendor ID.

[0183] A vendor identifier can be used to identify an equipment vendor. A vendor identifier can correspond to one or more network elements (NFs), such as an NWDAF containing MTLFs. For example, MTLF1 and MTLF2 correspond to vendor identifier 1, meaning that MTLF1 and MTLF2 belong to the same vendor, and the vendor identifier for that vendor is vendor identifier 1.

[0184] For NF (Network Element), the vendor identifier corresponds to the vendor of that network element. It can also be understood as network element information (NFinformation), which identifies the vendor information of the network element.

[0185] (10) Interoperability indicator.

[0186] For example, an interoperability identifier may correspond to an MTLF, an analytics identifier, or an MLTF analytics identifier. Alternatively, it can be described as an interoperability identifier related to an MTLF, or an interoperability identifier related to an analytics identifier. Here, an interoperability identifier may also be called an interoperability indicator, a machine learning (ML) model interoperability identifier, or an ML model interoperability indicator.

[0187] Interoperability identifiers include either a list of vendors or a list of vendor identifiers, or are described as a list of NWDAF providers (or vendors). Vendors in the first vendor identifier list are permitted to obtain models from MTLF, or vendors in the vendor identifier list are permitted to retrieve or use ML models provided by MTLF, or vendors in the first vendor identifier list are able to obtain models from MTLF, or vendors in the vendor identifier list are able to retrieve or use ML models provided by MTLF. Interoperability identifiers also indicate that MTLF supports vendors requesting ML models provided by MTLF for NWDAF requests from vendors in the vendor identifier list.

[0188] For example, analysis identifier 1 is associated with model 1, meaning model 1 is used to execute the service corresponding to analysis identifier 1. Analysis identifier 1 is also associated with interoperability identifier 1, meaning model 1 is associated with interoperability identifier 1. Assuming interoperability identifier 1 includes the identifier of vendor 1 and the identifier of vendor 2, model 1 can be provided to vendor 1 and vendor 2. Alternatively, it can be understood that if the vendor of the NWDAF is vendor 1 or vendor 2, then the NWDAF can use model 1.

[0189] For example, an MTLF may have one or more interoperability identifiers. If it has multiple interoperability identifiers, these multiple interoperability identifiers may correspond to different analytics identifiers. For example, MTLF1 corresponds to analytics identifier 1 and analytics identifier 2, where interoperability identifier 1 corresponds to analytics identifier 1 and interoperability identifier 2 corresponds to analytics identifier 2.

[0190] The following description uses the application of this application to fifth-generation (5G) communication as an example. However, the method shown in this application is not limited to 5G communication systems, but can also be applied to other communication systems, such as future communication systems. This communication system includes at least one network device and / or at least one terminal device.

[0191] Figure 1 This is a schematic diagram of a 5G network architecture based on a service-oriented architecture. Figure 1 The 5G network architecture shown may include terminal devices, access network devices, and core network (CN) devices. Terminal devices access the data network (DN) through access network devices and core network devices. The core network devices include various network functions (NFs) or network elements, such as some or all of the following network elements: UDM network element, UDR network element, NEF network element (not shown in the figure), 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, NWDAF network element, network repository function (NRF) network element (not shown in the figure), and location management function (LMF) network element (not shown in the figure).

[0192] Access network equipment can be radio access network (RAN) equipment. Examples include: base stations, evolved NodeBs (eNodeBs), transmission reception points (TRPs), next-generation NodeBs (gNBs) in 5G mobile communication systems, base stations in future mobile communication systems, or access nodes in wireless fidelity (WiFi) systems. It can also be modules or units that perform some of the functions of a base station; for example, it can be a central unit (CU) or a distributed unit (DU). RAN equipment can be macro base stations, micro base stations, indoor stations, relay nodes, or donor nodes. The embodiments of this application do not limit the specific technologies or equipment forms used in the RAN equipment.

[0193] Terminal devices can be user equipment (UE), mobile stations, mobile terminals, etc. They 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 include mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, urban air mobility vehicles (such as drones and helicopters), ships, robots, robotic arms, and smart home devices.

[0194] Access network equipment and terminal equipment can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of the access network equipment and terminal equipment.

[0195] The core network equipment involved in this application is described below:

[0196] The AMF (Agency Flow Management) network element includes functions such as mobility management and access authentication / authorization. It is also responsible for transmitting user policies between terminal devices and the PCF (Programmable Flow Function). The SMF (Sustainable Flow Management) network element includes functions such as session management, execution of PCF-issued control policies, UPF (User Flow Filter) selection, and Internet Protocol (IP) address allocation for terminal devices. The UPF (User Flow Filter) network element, as the interface with the data network, includes functions such as user plane data forwarding, session / flow-level billing statistics, and bandwidth limiting. The UDM (User Flow Management) network element includes functions such as managing subscription data and user access authorization. The UDR (User Flow Filter) network element includes functions such as storing and retrieving subscription data, policy data, and application data. The NEF (Network Flow Filter) network element is used to support the opening of capabilities and events. The AF (Application Flow Filter) network element transmits application-side requirements to the network side, such as Quality of Service (QoS) requirements or user state event subscriptions. AF can be a third-party functional entity or an application server deployed by the operator. The PCF (Programmable Flow Function) network element includes policy control functions such as billing at the session and service flow levels, QoS bandwidth assurance and mobility management, and terminal device policy decisions. NRF network elements can be used to provide network element discovery functionality, providing network element information corresponding to the network element type based on requests from other network elements. NRF network elements also provide network element management services, such as network element registration, updates, deregistration, and network element status subscription and push.

[0197] The NWDAF (Network Data Assistance) element is primarily used to collect data (including one or more of the following: terminal device data, access network device data, core network element data, and third-party application device data). This data can be data from the terminal device, access network device, core network element, or third-party application device itself, or data from the terminal device on that access network device, core network element, or third-party application device. The collected data is then analyzed, and the analysis results are output for use by network, network management equipment, and application execution strategy decisions. NWDAF can utilize machine learning models for data analysis.

[0198] 3GPP separates the training and inference functions of NWDAF (Non-Data Written Aid). An NWDAF can support only model training, only data inference, or both. An NWDAF supporting model training can be called a training NWDAF, or an NWDAF containing a model training logical function (MTLF) (MTLF element for short). A training NWDAF can train a model based on acquired data to obtain a trained ML model. An NWDAF supporting data inference can be called an inference NWDAF, or an NWDAF containing an analytics logical function (AnLF) (AnLF element for short). An inference NWDAF can input input data into the trained ML model to obtain analysis results or inference data.

[0199] In this embodiment, a training NWDAF refers to an NWDAF that at least supports model training functionality. As a possible implementation, a training NWDAF can also support data inference functionality. An inference NWDAF refers to an NWDAF that at least supports data inference functionality. As a possible implementation, an inference NWDAF can also support model training functionality. If an NWDAF supports both model training and data inference functionality, then the NWDAF can be called a training NWDAF, an inference NWDAF, a training-inference NWDAF, or simply an NWDAF. In this embodiment, an NWDAF can be a separate network element or can be co-located with other network elements, such as being placed in a PCF network element or an AMF network element.

[0200] An ADRF network element, or simply ADRF, is used to store model-related data. This data can be generated by the AnLF. The ADRF can provide model-related data to the MTLF upon request. The ADRF... Figure 1 or Figure 2 Not shown in the image.

[0201] The LMF (Local Position Controller) network element is used to manage the location information of terminal devices. It can calculate or verify the location of the terminal devices and / or estimate their speed, providing the accuracy of the estimation. The LMF network element can receive location requests from the AMF (Agency Position Controller) network element via the Nlmf interface. The granularity of the terminal's location calculated by the LMF network element can be one or more of the following: longitude, latitude, altitude, cell, and Global Positioning System (GPS).

[0202] A Domain Provider (DN) is a network located outside of the carrier's network. A carrier's network can connect to multiple DNs, and various services can be deployed on a DN, providing data and / or voice services to terminal devices. For example, a DN might be the private network of a smart factory. Sensors installed in the workshop can act as terminal devices, and a control server for these sensors is deployed within the DN. The control server provides services to the sensors. Sensors can communicate with the control server, receive instructions from it, and transmit the collected sensor data back to the control server accordingly. Another example is a DN serving as an internal office network for a company. Employees' mobile phones or computers can act as terminal devices, accessing information and data resources on the company's internal office network.

[0203] It is understood that the above network elements are examples of one implementation method. This application does not exclude the possibility that network elements or devices with the above network element functions may have other names or other forms in 6G or later wireless communication systems.

[0204] Figure 1 Nudr, Npcf, Namf, Nudm, Nsmf, Naf, and Nnwdaf are the service interfaces provided by UDR, PCF, AMF, UDM, SMF, AF, and NWDAF, respectively, used to call the corresponding service operations. N1, N2, N3, N4, and N6 are interface sequence numbers, and their meanings are as follows:

[0205] 1) N1: The interface between the AMF network element and the terminal device, which can be used to transmit non-access stratum (NAS) signaling (such as QoS rules from the AMF network element) to the terminal device.

[0206] 2) N2: The interface between the AMF network element and the access network equipment, which can be used to transmit radio bearer control information from the core network side to the access network equipment.

[0207] 3) N3: The interface between the access network equipment and the UPF network element, mainly used to transmit uplink and downlink user plane data between the access network equipment and the UPF network element.

[0208] 4) N4: The interface between SMF network elements and UPF network elements. It can be used to transmit information between the control plane and the user plane, including the distribution of forwarding rules, QoS rules, traffic statistics rules, etc. from the control plane to the user plane, as well as the reporting of information from the user plane.

[0209] 5) N6: The interface between the UPF network element and the DN, used to transmit uplink and downlink user data streams between the UP network element F and the DN.

[0210] In addition, Figure 1In the architecture shown, Nadrf can serve as a service interface for ADRF.

[0211] Figure 2 This is a schematic diagram of a 5G network architecture based on a point-to-point interface. For a description of the functions of the network elements, please refer to [reference needed]. Figure 1 The functions of the corresponding network elements will not be described in detail here. Figure 2 and Figure 1 The main difference is: Figure 1 The interfaces between the various control plane network elements are service-oriented interfaces. Figure 2 The interfaces between the various control plane network elements are point-to-point interfaces.

[0212] exist Figure 2 In the architecture shown, the interface names and functions between the various network elements in the core network are as follows:

[0213] 1) N5: The interface between AF network element and PCF network element, which can be used for application service request distribution and network event reporting.

[0214] 2) N7: The interface between PCF network elements and SMF network elements, which can be used to issue protocol data unit (PDU) session granularity and service data flow granularity control strategies.

[0215] 3) N8: The interface between the AMF network element and the UDM network element. It can be used by the AMF network element to obtain access and mobility management related subscription data and authentication data from the UDM network element, as well as by the AMF network element to register terminal device current mobility management related information with the UDM network element.

[0216] 4) N9: User plane interface between UPF network elements, used to transmit uplink and downlink user data streams between UPF network elements.

[0217] 5) N10: The interface between the SMF network element and the UDM network element. It can be used for the SMF network element to obtain session management-related subscription data from the UDM network element, and for the SMF network element to register terminal device current session-related information with the UDM network element.

[0218] 6) N11: The interface between SMF network elements and AMF network elements, which can be used to transmit PDU session tunnel information between access network devices and UPF network elements, transmit control messages sent to terminal devices, and transmit radio resource control information sent to access network devices, etc.

[0219] 7) N15: The interface between PCF network elements and AMF network elements, which can be used to issue terminal equipment policies and access control related policies.

[0220] 8) N23: The interface between the PCF network element and the NWDAF network element. The NWDAF network element can collect data from the PCF network element through this interface. It should be noted that the NWDAF network element can also have interfaces with other devices (such as AMF network elements, UPF network elements, access network devices, terminal devices, etc.), which are not fully shown in the figure.

[0221] 9) N35: The interface between UDM network elements and UDR network elements, which can be used by UDM network elements to obtain user subscription data information from UDR network elements.

[0222] 10) N36: The interface between PCF network elements and UDR network elements, which can be used by PCF network elements to obtain policy-related contract data and application data related information from UDR network elements.

[0223] It is understood that the aforementioned network element or function can be a network component in a hardware device, a software function running on dedicated hardware, or a virtualization function instantiated on a platform (e.g., a cloud platform). As one possible implementation method, the aforementioned network element or function can be implemented by a single device, multiple devices working together, or a functional module within a single device; this application does not specifically limit this.

[0224] To achieve intelligent mobile networks, NWDAF network elements are defined to provide intelligent analytics services. Among them, the MTLF network element is responsible for training, updating, and managing ML models to improve their accuracy and adaptability. The AnLF network element is responsible for using the trained ML models for inference analysis, providing decision support for network operations. Each NWDAF instance, regardless of whether it contains AnLF or MTLF network elements, needs to be registered with the network repository function (NRF) network element. During registration, in addition to providing basic network function (NF) profile information, the service types supported by the NWDAF instance (such as analytics exposure services or ML model services) and the list of supported analytics IDs must be specified.

[0225] AnLF network elements, acting as model consumers of ML models, can use NRF queries to discover the first MTLF network element that meets their needs. They then send a model subscription request to that first MTLF network element and receive a corresponding model notification message, thereby acquiring the corresponding ML model. After acquiring the ML model, the model consumer can send a model monitoring registration request to the ML model's model producer to obtain accuracy monitoring for that ML model.

[0226] Optionally, when the AnLF network element begins using an ML model and monitors the accuracy of the analysis generated by that ML model for a given Analytics ID, it can register with the first MTLF network element. Assume the AnLF network element obtained the ML model in a previous interaction with the first MTLF network element, such as using the Nnwdaf_MLModelInfo_Request service or the Nnwdaf_MLModelProvision_Subscribe service. This registration enables the first MTLF network element to recognize that the AnLF network element is using a given ML model for a specific Analytics ID and that the AnLF network element supports the ability to monitor the accuracy of the corresponding analysis.

[0227] Optionally, the first MTLF network element can subscribe to the AnLF network element, which establishes an existing Nnwdaf_MLModelMonitor service to receive notifications of the accuracy of analyses generated for a specific Analytics ID for a given ML model. The AnLF network element can generate accuracy information in various ways: for example, by comparing the ML model's predictions with its corresponding ground truth data, comparing changes in the internal configuration of the analytics ID generation, or by referencing previously existing records of the analytics accuracy information.

[0228] In summary, when an AnLF network element starts using an ML model, it can monitor the analytical accuracy of the ML model and / or provide analytical feedback for the analyses generated by the ML model. It registers with the first MTLF network element, which is responsible for training / updating this ML model. When an AnLF network element stops using the ML model or monitors the accuracy of the analyses generated by the ML model for the Analytics ID, it will deregister with the first MTLF network element.

[0229] However, in some scenarios, while the first MTLF element can provide model notification messages for the ML model, it may not be the model producer for that ML model. For example, after receiving a model subscription request, the first MTLF element determines that the ML model needs to be obtained through FL (Model Flow). The first MTLF element will then send a model subscription request to the central server of FL (i.e., the second MTLF) on behalf of the AnLF element, thereby obtaining the corresponding model notification message. In this case, the first MTLF element acts as the model proxy requester for that ML model, while the second MTLF element acts as the model producer. The model consumer cannot register the model it uses with the correct model producer or monitor the accuracy of the ML model analysis.

[0230] It should be noted that in scenarios involving model proxy requesters, there are two possible ways for model consumers to obtain model notification messages.

[0231] In one possible implementation, after receiving a model subscription request, the model producer directly sends a model notification message to the model consumer. Specifically, the model subscription request carries the notification target address of the model consumer.

[0232] In one possible implementation, after receiving a model subscription request, the model producer sends a model notification message to the model proxy requester, who then forwards the message to the model consumer. Specifically, the model subscription request carries the notification target address of the model proxy requester.

[0233] Based on the above Figure 1 and Figure 2 Based on the network system architecture shown and the content described above, this application provides several possible communication methods and corresponding communication systems, enabling model producers to obtain the analysis accuracy of the ML model provided by the model consumer, and / or provide analysis feedback information on the analysis results generated for the ML model, thereby monitoring or training and updating the ML model.

[0234] The network elements involved in this application embodiment include the aforementioned first MTLF network element, second MTLF network element, and AnLF network element. Among them, the first network element involved in this system is the second MTLF network element, that is, the first network element is the model producer of the first ML model.

[0235] In one possible implementation, the first network element is an FL server, and the first ML model is an ML model trained based on the first MTLF network element and at least one other network element in collaboration.

[0236] The second network element involved in this system is the AnLF network element, which is the model consumer of the first ML model.

[0237] The third network element involved in this system is the first MTLF network element, which is the model proxy requester of the first ML model.

[0238] Model producers can receive model monitoring registration requests from model consumers through various means (such as the Nnwdaf_MLModelMonitor_Register message), which will be described in detail below with reference to the accompanying figures.

[0239] First, the model consumer obtains the first address of the model producer from the model notification message. This first address is used to receive model monitoring registration requests.

[0240] This application provides a communication method; please refer to [link / reference]. Figure 3 . Figure 3This application illustrates the method by using a first network element and other network elements (such as a second network element and / or a third network element) as the execution entities in this interaction illustration, but it does not limit the execution entities of this interaction illustration. For example, Figure 3 The first network element can be a network device or server, or it can be a chip, baseband chip, modem chip, system-on-chip (SoC) chip containing a modem core, system-in-package (SIP) chip, communication module, chip system, processor, logic module, or software in the network device or server; similarly, Figure 3 The second network element can be a network device or server, or it can be a chip, baseband chip, modem chip, SoC chip containing a modem core, SIP chip, communication module, chip system, processor, logic module, or software in the network device or server; similarly, Figure 3 The third network element can be a network device or server, or it can be a chip, baseband chip, modem chip, SoC chip containing a modem core, SIP chip, communication module, chip system, processor, logic module or software in a network device or server.

[0241] In this application, when referring to a network device, it may refer to the network device itself, or to the chips, communication modules, integrated circuits, processors, logic modules, or software within the network device used to implement the communication methods provided in this application, and this application does not impose any specific limitations. When referring to a server, it may refer to the server itself, or to the chips, communication modules, integrated circuits, processors, logic modules, or software within the server used to implement the communication methods provided in this application, and this application does not impose any specific limitations.

[0242] like Figure 3 As shown, one communication method in this application embodiment includes:

[0243] 301. The second network element sends a third request to the third network element; correspondingly, the third network element receives the third request.

[0244] For example, the second network element can be a model consumer. The model consumer needs to obtain specific ML model information in order to provide analysis services (Nnwdaf_AnalyticsSubscription). It can be understood that the model consumer uses the ML model corresponding to the obtained ML model information to perform the analysis service.

[0245] Optionally, the third request is a message used to subscribe to a specific ML model or model type. The third request is the Nnwdaf_MLModelProvision_Subscribe message. It can be understood that the second network element requests to subscribe to an ML model from the third network element via the Nnwdaf_MLModelProvision_Subscribe message.

[0246] Optionally, the third request is a message used to obtain specific ML model information. The third request is the Nnwdaf_MLModelInfo_Request message. It can be understood that the second network element obtains specific ML model information from the third network element through the Nnwdaf_MLModelInfo_Request message.

[0247] Specifically, the third request includes an analysis identifier (ID) or a list(s) of analysis IDs, which indicates the analysis ID(s) associated with the ML model that needs to be subscribed to / obtained, so as to accurately provide relevant model information.

[0248] Specifically, the third request also includes the notification target address of the second network element, which is used to receive model notification messages from the subscribed ML model.

[0249] For example, the model notification message is the Nnwdaf_MLModelProvision_Notify message.

[0250] In event notifications, the notification target address (+notification association ID) ensures that notifications received from the event provider can be associated with a specific subscription. Each subscription is bound to a unique notification target address (+notification association ID). The notification target address specifies the specific location or entity receiving the event notification. The notification association ID, as a supplement to the notification target address, is used to further distinguish multiple different subscriptions or sessions that may exist under the same address. Each notification target address (+notification association ID) is associated with a set of related event IDs.

[0251] For example, you can receive a subscribed notification message by specifying the "target address". Alternatively, you can receive a subscribed notification message by specifying the "target address" and a specific notification association ID.

[0252] For example, an NF consumer subscribes to notifications from an NF producer on behalf of other NFs. In this case, the NF consumer needs to include the notification target address (+notification association ID) on behalf of the other NFs in the subscription request, so that the NF producer can directly send notifications related to the event ID to these specified addresses.

[0253] Optionally, the third request may also include first indication information, which is used to request a first address of the first network element. This first address is the callback Uniform Resource Identifier (callback URI) of the first network element. The second network element may use or send a model monitoring registration request based on this callback URI. It can be understood that the second network element sends the model monitoring registration request to the callback URI.

[0254] For example, the model monitoring registration request is an Nnwdaf_MLModelMonitor_Register message.

[0255] In one implementation, the first instruction information is a "model monitoring registration instruction", which is used to instruct the second network element to send a model monitoring registration request to the model producer of the ML model after obtaining the ML model. Therefore, the model producer (the first network element) needs to provide a specific address, namely the first address.

[0256] In another implementation, the first indication information is a "model monitoring capability indication," which indicates that the second network element has the ability to provide accuracy information for the analysis results generated by the ML model, and / or to provide analytical feedback information for the analysis results generated by the ML model. Therefore, the model producer (the first network element) can provide this first address to monitor the ML model.

[0257] Optionally, the third request may also include parameters such as the required ML model filtering information in order to accurately select the desired ML model.

[0258] 302. The third network element sends a second request to the first network element; correspondingly, the first network element receives the second request.

[0259] In this application, after receiving the third request, the third network element determines the first network element based on the content of the third request. The first network element is the model provider of the ML model required by the request, i.e., the model producer.

[0260] For example, the third network element identifies that the requested ML model in the third request needs to be obtained using a federated learning (FL) mechanism, but the third network element itself does not have the capability to act as an FL server, i.e., it cannot generate the ML model, and needs a third party (e.g., an NF with federated learning capabilities) to provide the ML model. Therefore, the third network element finds a suitable FL server to act as the first network element.

[0261] The third network element sends a second request to the first network element. The second request is to obtain the ML model on behalf of the second network element.

[0262] In one possible implementation, the second request is an Nnwdaf_MLModelProvision_Subscribe message used to subscribe to an ML model.

[0263] In another possible implementation, the second request is an Nnwdaf_MLModelInfo_Request message used to obtain ML model information.

[0264] Specifically, the second request includes an analysis ID(s) that indicates the analysis ID(s) associated with the ML model that needs to be subscribed to / obtained, in order to accurately provide relevant model information.

[0265] Optionally, the second request includes the aforementioned first instruction information for requesting the first address.

[0266] Optionally, the second request may also include the identifier of the third network element (NF Instance Identifier, NF ID).

[0267] Optionally, the second request may also include the identifier (AnLF NF ID) of the second network element, which indicates that the second request is a model subscription request sent by the third network element on behalf of the second network element, and the model consumer of the ML model is the second network element.

[0268] In this embodiment, the second request carries the notification target address of the second network element, which is used by the first network element to directly send the model notification message to the second network element.

[0269] 303. The first network element sends a first message to the second network element. The first message includes the identifier (MLmodel Identifier, model ID) of the first ML model and the first address. Correspondingly, the second network element receives the first message.

[0270] The first network element determines that the first ML model is the ML model requested in the second request.

[0271] Optionally, the first network element determines the first ML model that provides the corresponding analysis service based on the list of analysis IDs carried in the second request.

[0272] Optionally, the second request is an Nnwdaf_MLModelProvision_Subscribe message, used to subscribe to an ML model. The first network element verifies the second network element based on the AnLF NF ID and decides to accept the subscription.

[0273] Optionally, the second request is an Nnwdaf_MLModelInfo_Request message used to obtain ML model information. The first network element decides to provide this ML model information.

[0274] In this embodiment, the first message includes a first address.

[0275] Optionally, if the second request is a model substitution request, then the first network element carries the aforementioned first address in the first message. It can be understood that the second request is a request for the model by the third network element on behalf of the model consumer. That is, the model consumer (second network element) requesting the ML model is different from the requester (third network element) that sends the second request to the first network element.

[0276] For example, based on the fact that the second request carries the identifier (AnLF ID) of the second network element or notification-related information, the second request is determined to be a model substitution request.

[0277] Optionally, if the second request carries the aforementioned first instruction information, then the first network element will carry the aforementioned first address in the first message.

[0278] The first network element sends a first message to the second network element via the notification target address of the second network element carried in the second request. The first message is used to provide the model consumer with available ML model information, which is the ML model required by the second network element. It can be understood that the first network element sends this first message to the notification target address of the second network element.

[0279] For example, the first message is the Nnwdaf_MLModelProvision_Notify message.

[0280] In one implementation, during transmission, the first network element encapsulates the first message to be sent into a data packet. The data packet contains the source address (i.e., the address of the first network element), the destination address (i.e., the notification target address of the second network element), the data content of the first message itself, and possible control information (such as sequence number, checksum, etc.). The first network element then sends the data packet to the next node according to the routing policy, eventually reaching the second network element.

[0281] Specifically, the first message includes the model ID of the first ML model, used to identify the first ML model. For example, the second network element uses this identifier to search for and download the first ML model from the corresponding model repository or model distribution platform. It can be understood that the first message includes a message about the first ML model, and this message includes the identifier of the first ML model.

[0282] Optionally, the first message may also include the file storage address of the first ML model (e.g., a uniform resource locator (URL) or a fully qualified domain name (FQDN)), or the analytics data repository functional (ADRF) ID or ADRF set ID. When the ML model information includes ADRF or ADRF set ID, it may also include a storage transaction ID. It is understood that the first message may also include other content, and this application does not limit this.

[0283] 304. The second network element sends a first request to the first network element, the first request including the identifier (modelID) of the first ML model; correspondingly, the second network element receives the first request.

[0284] After receiving the first message, the second network element obtains the first ML model based on the content of the first message. Then, the second network element decides to provide the model producer (the first network element) with analytical feedback information to monitor the analytical accuracy of the first ML model and / or to provide analytical results generated by the first ML model.

[0285] The second network element sends a first request to the first network element through a first address. The first request includes the model ID of the first ML model, which is used to indicate that the second network element has the ability to use and / or monitor the first ML model.

[0286] For example, the first request is the Nnwdaf_MLModelMonitor_Register message, which is the aforementioned model monitoring registration request.

[0287] Specifically, the second network element encapsulates the first request to be sent into a data packet. The data packet contains the source address (i.e., the address of the second network element), the destination address (i.e., the first address), the data content of the first request itself (such as service operations, operation semantics, etc.), and possible control information (such as sequence number, checksum, etc.). Next, the second network element sends the data packet to the next node according to the routing policy, and finally it reaches the first network element.

[0288] Specifically, the first request also includes the identifier (AnLF ID) of the second network element.

[0289] 305. The first network element sends a second message to the second network element; correspondingly, the first network element receives the second message.

[0290] Upon receiving the first request, which includes the identifier (AnLF ID) of the second network element, indicating that the second network element is monitoring the accuracy of the first ML model, the first network element sends a second message to the second network element to obtain accuracy information of the monitored ML model. This second message is a response to the first request.

[0291] For example, the second message is the Nnwdaf_MLModelMonitor_Subscribe message. It can be understood that the first network element obtains the accuracy information of the monitored ML model from the second network element through the Nnwdaf_MLModelMonitor_Subscribe message. This includes, for example, the ML model's performance metrics (accuracy, recall, etc.), response time, memory usage, CPU utilization, etc.

[0292] Specifically, the second message includes the ML Model monitoring registration ID.

[0293] Specifically, the second message includes the identifier of the monitored ML model, i.e., the model ID of the first ML model.

[0294] Specifically, the second message includes the notification target address of the first network element, used to receive accuracy information and / or analysis feedback information of the ML model analysis results.

[0295] Optionally, the second message may also include the accuracy metrics to be monitored, optional reporting thresholds, analysis ID, analysis reporting target, or analysis filters for the reporting period.

[0296] 306. Second network element monitoring first ML model.

[0297] Specifically, the second network element is based on the second message monitoring first ML model.

[0298] For example, model monitoring services can track the performance of ML models in real-time during practical applications. This includes key metrics such as the model's accuracy, response speed, and resource consumption. Continuous monitoring allows for the timely detection of performance degradation or abnormal behavior, ensuring system stability and reliability.

[0299] In this application, the first network element conveys the destination address of the model monitoring registration request to the second network element by carrying the first address in the first message, thereby avoiding the failure of sending the model registration request and ensuring that the second network element can obtain the required model monitoring service.

[0300] It should be understood that Figure 3The scenario shown involves three network elements: a first network element as the model producer, a second network element as the model consumer, and a third network element as the model proxy. However, this solution is not limited to this scenario and is also applicable in other scenarios, such as scenarios where multiple third network elements participate in forwarding model subscription requests or proxying models, or scenarios where no third network element is needed and the second network element directly sends a model subscription request to the first network element. For example, when the second network element directly sends a model subscription request (first request) to the first network element, the first network element can also carry the first address in the response model notification message (first message) to ensure the integrity and effectiveness of the communication link.

[0301] Second, the model consumer obtains information about the model producer from the model notification message, enabling the model consumer to discover the model producer and send a model monitoring registration request to the model producer.

[0302] In one possible implementation, the model consumer receives a model notification message containing information about the model producer, which is sent directly to it by the model producer.

[0303] Please see Figure 4a One communication method in this application embodiment includes:

[0304] 401. The second network element sends a third request to the third network element; correspondingly, the third network element receives the third request.

[0305] For example, the model consumer (the second network element) needs to obtain specific ML model information in order to provide analysis services (Nnwdaf_AnalyticsSubscription). It can be understood that the model consumer uses the ML model corresponding to the obtained ML model information to execute and analyze the service. The second network element sends a third request to the third network element.

[0306] Optionally, the third request is a message used to subscribe to a specific ML model or model type. The third request is the Nnwdaf_MLModelProvision_Subscribe message. It can be understood that the second network element requests to subscribe to an ML model from the third network element via the Nnwdaf_MLModelProvision_Subscribe message.

[0307] Optionally, the third request is a message used to obtain specific ML model information. The third request is the Nnwdaf_MLModelInfo_Request message. It can be understood that the second network element obtains specific ML model information from the third network element through the Nnwdaf_MLModelInfo_Request message.

[0308] Specifically, the third request includes a list(s) of analytics IDs, which indicates the list of analytics IDs associated with the ML model that needs to be subscribed to / obtained, in order to accurately provide relevant model information.

[0309] Specifically, the third request also includes the notification target address of the second network element, which is used to receive model notification messages from the subscribed ML model. The model notification message is the Nnwdaf_MLModelProvision_Notify message.

[0310] Optionally, the third request may also include parameters such as the required ML model filtering information in order to accurately select the desired ML model.

[0311] 402. The third network element sends a second request to the first network element; correspondingly, the first network element receives the second request.

[0312] Step 402 in this embodiment is the same as described above. Figure 3 Step 302 in the illustrated embodiment is similar and will not be described in detail here.

[0313] It should be noted that the second request in this embodiment does not carry... Figure 3 The first instruction information in the illustrated embodiment.

[0314] 403. The first network element sends a first message to the second network element, the first message including the identifier (modelID) of the first ML model; correspondingly, the second network element receives the first message.

[0315] For example, the first network element decides to accept the subscription request of the second network element and sends a first message to the second network element through the notification target address of the second network element.

[0316] For example, the first message is the Nnwdaf_MLModelProvision_Notify message.

[0317] Specifically, the first message includes the identifier (model ID) of the first ML model. The identifier of the first ML model is used to identify the first ML model. The second network element can obtain the first ML model based on or using the identifier of the first ML model.

[0318] In this embodiment of the application, optionally, the first message further includes second indication information, which is used to identify the first network element. This second indication information is information about the first network element. The second network element can send a network element discovery service request to the NRF network element based on the second indication information to obtain one or more pieces of information from the first network element's NF profile. For example, the interoperability identifier of the second network element.

[0319] Optionally, the first network element receives the second request (as described in step 402). Optionally, the first network element determines that the second request is an ML model acquisition request sent by the third network element on behalf of the second network element to the first network element. In this case, the first message also includes second indication information. It can be understood that the purpose of the second request is for the third network element to request a model on behalf of the model consumer (the second network element). That is, the model consumer (the second network element) of the requested ML model is different from the requester (the third network element) that sent the second request to the first network element. For example, the first network element can determine that the second request is an ML model acquisition request sent by the third network element on behalf of the second network element to the first network element based on information included in the second request, such as the first network element identifier.

[0320] Optionally, the second instruction information includes one or more of the following:

[0321] The network function instance identifier (NFID) of the first network element;

[0322] The first network element's Internet Protocol (IP) address can be an IPv4 address, an IPv6 address, or an IPv6 prefix.

[0323] The port number of the first network element; or,

[0324] The fully qualified domain name (FQDN) of the first network element.

[0325] In one possible implementation, the first network element does not carry the second indication information in the data content of the first message. The second network element determines the information of the first network element through the certificate in the first message. Specifically, the second network element determines the first network element's information based on the transport layer security (TLS) session information corresponding to the first message. In step 403, the first network element is the client of the TLS session, and the second network element is the server of the first message. The second network element determines one or more of the following information of the first network element based on the TLS certificate of the TLS session client: NF ID, IP address, port number, or FQDN, etc.

[0326] Optionally, the first message may also include the file storage address of the first ML model (e.g., a Uniform Resource Locator (URL) or a Fully Qualified Domain Name (FQDN)), or the Analytics Data Storage Function (ADRF) ID or ADRF set ID. When the ML model information includes ADRF or ADRF set ID, it may also include a storage transaction ID. It is understood that the first message may also include other content, and this application does not limit this.

[0327] 404. The second network element sends a fourth request to the NRF network element, the fourth request including the second indication information; accordingly, the NRF network element receives the fourth request.

[0328] After receiving the first message, the second network element obtains the first ML model based on the content of the first message. Then, the second network element decides to obtain the model producer information of the first ML model through the NRF network element. This allows it to provide the model producer with analytical feedback information to monitor the analytical accuracy of the first ML model and / or to provide analytical results generated by the first ML model.

[0329] The second network element sends a fourth request to the NRF network element. This fourth request is used to discover the desired NF instance. It should be understood that the NF instance has already been registered with the NRF network element.

[0330] For example, the fourth request is an Nnrf_NFDiscovery_Request message.

[0331] Specifically, the fourth request includes the second instruction information, namely the NF ID, IP address, port number or FQDN of the first network element.

[0332] 405. The NRF network element sends the first configuration file to the second network element, and the second network element receives the first configuration file accordingly.

[0333] The NRF network element determines the network element to be discovered, i.e., the first network element, based on one or more of the following: the NF ID, IP address, port number, or FQDN of the first network element. The NRF network element then sends the first NF profile to the second network element.

[0334] Optionally, the first configuration file is carried in the response message of the Nnrf_NFDiscovery_Request message.

[0335] Specifically, the first configuration file includes one or more configuration information for the first network element.

[0336] 406. The second network element sends a first request to the first network element, the first request including the identifier (modelID) of the first ML model; correspondingly, the second network element receives the first request.

[0337] The second network element sends a first request to the first network element based on the first configuration file.

[0338] For example, during transmission, the second network element obtains the first address of the first network element based on one or more configuration information of the first network element, as well as the first network element's NF ID, IP address, port number, or FQDN, etc. The second network element encapsulates the first request to be sent into a data packet. The data packet contains the source address (i.e., the address of the second network element), the destination address (i.e., the first address), the data content of the first request itself, and possible control information (such as sequence number, checksum, etc.). Next, the second network element sends the data packet to the next node according to the routing policy, and finally it reaches the first network element.

[0339] For details regarding the function and specific content of the first request, please refer to the foregoing. Figure 3 The description of the first request mentioned in the illustrated embodiment will not be repeated here.

[0340] 407. The first network element sends a second message to the second network element; correspondingly, the first network element receives the second message.

[0341] 408. Second network element monitoring first ML model.

[0342] Steps 407 to 408 in this embodiment are the same as those described above. Figure 3 Steps 305 to 306 in the illustrated embodiment are similar and will not be described in detail here.

[0343] In one possible implementation, the model consumer receives a model notification message containing information about the model producer from a third network element.

[0344] like Figure 4b As shown, steps 403a and 403b replace the aforementioned Figure 4a Step 403 in the illustrated embodiment. Specifically, Figure 4a Step 403 can be broken down into two independent steps, namely step 403a and step 403b.

[0345] Figure 4b In the embodiment shown, in step 402, the second request carries the notification target address of the third network element, which is used to receive the model notification message sent by the first network element.

[0346] 403a. The first network element sends a first message to the third network element, the first message including the identifier (model ID) of the first ML model; correspondingly, the third network element receives the first message.

[0347] The first network element sends a first message to the third network element through the notification target address of the third network element. The first message carries the model ID.

[0348] Optionally, the first network element may also carry the aforementioned second instruction information, i.e., the information of the first network element, in the first message.

[0349] 403b. The third network element sends a third message to the second network element, the third message including the identifier (model ID) of the first ML model and the second indication information; accordingly, the second network element receives the third message.

[0350] After receiving the first message, the third network element, based on the information from steps 401 to 402, determines that the first message is a model notification message sent by the model producer (first network element) to the model consumer (second network element), and decides to send a third message to the second network element. This can be understood as sending the model notification message to the model consumer on behalf of the model producer.

[0351] In one possible implementation, the first message carries second indication information to identify the first network element. The third network element can directly forward the first message to the second network element.

[0352] In one possible implementation, the first message received by the third network element does not carry the second indication information. The third network element determines the information of the first network element through the certificate in the first message, such as determining one or more of the following information of the first network element through the TLS certificate: NF ID, IP address, port number, or FQDN, etc. The third network element combines this information with the information in the first message to generate a third message. This third message is then sent to the second network element.

[0353] In this application, the second network element determines the source of the first message based on the first message, that is, determines the information of the model producer (first network element), and sends a model monitoring registration request to the corresponding model producer in conjunction with the NRF network element, so that the second network element can obtain the required model monitoring service.

[0354] Third, the model proxy requester maintains the association between the ML model and the model producer of the ML model, and sends model monitoring registration requests to the model producer on behalf of the model consumer.

[0355] Please see Figure 5 One communication method in this application embodiment includes:

[0356] 501. The second network element sends a third request to the third network element; correspondingly, the third network element receives the third request.

[0357] Step 501 in this embodiment is the same as the aforementioned Figure 4a Step 401 in the illustrated embodiment is similar and will not be described in detail here.

[0358] 502. The third network element sends a second request to the first network element, the second request including the notification target address of the second network element and the notification target address of the third network element; accordingly, the first network element receives the second request.

[0359] In this application, after receiving the third request, the third network element determines the first network element based on the content of the third request. The first network element is the model provider of the ML model required by the request, i.e., the model producer.

[0360] The third network element sends a second request to the first network element. The second request is to obtain the ML model on behalf of the second network element.

[0361] Optionally, the second request is an Nnwdaf_MLModelProvision_Subscribe message used to subscribe to an ML model.

[0362] Optionally, the second request is an Nnwdaf_MLModelInfo_Request message used to obtain ML model information.

[0363] Specifically, the second request includes a list of analytics IDs that indicate the list of analytics IDs associated with the ML model that needs to be subscribed to / obtained, so as to accurately provide relevant model information.

[0364] The second request also includes the identifier of the third network element (NF Instance Identifier, NF ID).

[0365] In this embodiment, a model information acquisition instruction is added to the second request. This means that the third network element not only sends the model subscription request on behalf of the second network element, but also acquires the model notification message.

[0366] Specifically, the second request carries the notification target address of the second network element and the notification target address of the third network element.

[0367] 503a. The first network element sends a first message to the third network element, the first message including the identifier (model ID) of the first ML model; correspondingly, the second network element receives the first message.

[0368] The first network element decides to accept the subscription request from the second network element, and sends a first message to the third network element through the notification target address of the third network element. This first message provides the model consumer with available ML model information, which is the ML model required by the second network element. It can be understood that the first network element sends this first message to the notification target address of the third network element.

[0369] For example, the first message is the Nnwdaf_MLModelProvision_Notify message.

[0370] Specifically, the first message includes the model ID of the first ML model.

[0371] Optionally, the first message also carries the NF ID of the first network element.

[0372] Optionally, if the first message does not carry the NF ID of the first network element, the third network element determines the NF ID through the context.

[0373] For example, the third network element determines, through the information in step 502, that the model producer of the ML model indicated in the model notification message is the recipient of the model subscription request sent in step 502, and determines the NF ID of the recipient.

[0374] Optionally, the third network element determines the NF ID of the first network element through the certificate in the first message. Specifically, the third network element uses the TLS session information corresponding to the first message. In step 503a, the first network element is the client of the TLS session, and the third network element is the server of the first message. The third network element determines one or more of the following information of the first network element based on the TLS certificate of the client of the TLS session: NF ID, IP address, port number, or FQDN, etc.

[0375] In this embodiment, the third network element maintains the association between the first ML model and the model producer, that is, the association between the model ID and the NF ID. This can be understood as the third network element recording the model IDs of one or more ML models locally on the device, as well as the NF ID corresponding to each model ID, to indicate the model provider corresponding to the ML model, including the first ML model and its model provider.

[0376] Optionally, the first message may also include the file storage address of the first ML model (e.g., a Uniform Resource Locator (URL) or a Fully Qualified Domain Name (FQDN)), or the Analytics Data Storage Function (ADRF) ID or ADRF set ID. When the ML model information includes ADRF or ADRF set ID, it may also include a storage transaction ID. It is understood that the first message may also include other content, and this application does not limit this.

[0377] 503b. The first network element sends a first message to the second network element, the first message including the modelID of the first ML model; correspondingly, the second network element receives the first message.

[0378] Similarly, the first network element sends a first message to the second network element through the notification target address of the second network element. It can be understood that the first network element sends this first message to the notification target address of the second network element.

[0379] 504. The second network element sends a first request to the third network element, the first request including the modelID of the first ML model; correspondingly, the third network element receives the first request.

[0380] After receiving the first message, the second network element obtains the first ML model based on the content of the first message. Then, the second network element decides to provide the model producer (the first network element) with analytical feedback information to monitor the analytical accuracy of the first ML model and / or to provide analytical results generated by the first ML model.

[0381] In this embodiment, the second network element does not have information about the model producer (the first network element). Therefore, the second network element decides to send a first request to the third network element, instructing the second network element to have the ability to use and / or monitor the first ML model.

[0382] For example, the first request is the Nnwdaf_MLModelMonitor_Register message, which is the aforementioned model monitoring registration request.

[0383] Specifically, the first request includes the model ID of the first ML model.

[0384] Optionally, the first request may also include the identifier of the second network element (AnLF NF ID).

[0385] 505. The third network element determines the model provider (i.e., the model producer) corresponding to the model ID.

[0386] After receiving the first request, the third network element matches the model ID of the first ML model carried in the first request with the association between the locally maintained ML model and the model producer to determine that the model producer corresponding to the first ML model is the first network element.

[0387] 506. The third network element sends a fifth request to the first network element. The fifth request includes the model ID and the identifier of the second network element. Accordingly, the first network element receives the fifth request.

[0388] After determining the model producer (first network element) corresponding to the first ML model, the third network element sends a fifth request to the first network element on behalf of the second network element. This request is used to instruct the second network element to have the ability to use and / or monitor the first ML model, i.e., a model monitoring registration request.

[0389] For example, the fifth request is the Nnwdaf_MLModelMonitor_Register message.

[0390] Specifically, the fifth request includes the model ID of the first ML model and the identifier of the second network element, which indicates that the fifth request is a model monitoring registration request sent on behalf of the second network element.

[0391] 507. The first network element sends a second message to the second network element; correspondingly, the second network element receives the second message.

[0392] 508. Second network element monitoring first ML model.

[0393] Steps 507 to 508 in this embodiment are the same as those described above. Figure 4a Steps 407 to 408 in the illustrated embodiment are similar and will not be described in detail here.

[0394] In this application, the third network element obtains the first message sent by the first network element to the second network element and locally maintains the association between the ML model and the corresponding model producer. When the third network element receives the model monitoring registration request from the model consumer (the second network element), it can match the information maintained locally to determine the model producer (the first network element) of the ModelID in the model monitoring registration request. Then, it sends the model monitoring registration request to the first network element on behalf of the second network element, enabling the second network element to obtain the model monitoring service.

[0395] In one possible implementation, in a communication scenario involving three network elements (such as the aforementioned first, second, and third network elements), the model consumer may transfer the analysis subscription from the source AnLF network element (i.e., the second network element) to the target AnLF network element (the fourth network element).

[0396] For example, if the source AnLF network element determines that it is in an overloaded state, or close to or exceeding the service limit, or the source AnLF network element is preparing to shut down and stop providing services, then the source AnLF determines that it needs to select a target AnLF.

[0397] Currently, source AnLF network elements need to use the network element discovery process to discover target AnLF network elements. However, because the NRF network element does not know the vendor information of the AnLF that the source AnLF network element expects to discover, it cannot accurately select or return the AnLF from the vendor the source AnLF expects. For example, the source AnLF may expect to discover an AnLF from a specific vendor that can use the ML model it is currently using. Therefore, the source AnLF cannot accurately select the target AnLF network element that supports the model used by the source AnLF. This means that the target AnLF network element may not be able to use the analysis context obtained from the source AnLF network element. In other words, it cannot be understood that there is no guarantee that the AnLF network element discovered by the network element discovery process supports the use of the analysis context obtained from the source AnLF network element, which leads to analysis context transfer failure, affects the continuity of analysis services, and causes network failure.

[0398] To address the aforementioned issues, this application provides a communication method in which the source AnLF network element obtains the interoperability identifier corresponding to the ML model being used from the model notification message, and discovers a suitable target AnLF network element through the interoperability identifier.

[0399] Please see Figure 6a One communication method in this application embodiment includes:

[0400] 601. The second network element sends a first request to the third network element; correspondingly, the third network element receives the first request.

[0401] For example, the model consumer (the second network element) needs to obtain specific ML model information in order to provide analysis services (Nnwdaf_AnalyticsSubscription). It can be understood that the model consumer uses the ML model corresponding to the obtained ML model information to execute and analyze the service.

[0402] Optionally, the first request is a message used to subscribe to a specific ML model or model type. The second request is an Nnwdaf_MLModelProvision_Subscribe message. It can be understood that the second network element requests to subscribe to an ML model from the third network element via the Nnwdaf_MLModelProvision_Subscribe message.

[0403] Optionally, the first request is a message used to obtain specific ML model information. The third request is an Nnwdaf_MLModelInfo_Request message. It can be understood that the second network element obtains specific ML model information from the third network element through the Nnwdaf_MLModelInfo_Request message.

[0404] Specifically, the first request includes an analysis identifier (ID) or a list(s) of analysis IDs, indicating that the ML model corresponding to the analysis ID(s) needs to be subscribed to / retrieved.

[0405] Specifically, the first request also includes the notification target address of the second network element, which is used to receive model notification messages of the subscribed ML model. This type of notification message is the Nnwdaf_MLModelProvision_Notify message.

[0406] Optionally, the third request may also include parameters such as the required ML model filtering information in order to accurately select the desired ML model.

[0407] 602. The third network element sends a fourth request to the first network element; correspondingly, the first network element receives the fourth request.

[0408] In this application, after receiving the first request, the third network element determines the first network element based on the content of the first request. The first network element is the model provider of the ML model corresponding to the service corresponding to the analysis identifier, i.e., the model producer.

[0409] For example, the third network element identifies that the ML model requested in the first request needs to be obtained using a federated learning mechanism, but the third network element itself does not have the capability to act as a FL server, that is, it cannot generate the ML model, and needs a third party (e.g., an NF with federated learning capabilities) to provide the ML model. Therefore, the third network element finds a suitable FL server to act as the first network element.

[0410] The third network element sends a fourth request to the first network element, the fourth request indicating that the third network element, on behalf of the second network element, requests the provision of the machine learning (ML) model corresponding to the analysis identifier;

[0411] Specifically, the fourth request includes analyzing ID(s).

[0412] Specifically, the fourth request also includes the identifier (AnLF NF ID) of the second network element, which indicates that the fourth request is a model subscription request sent by the third network element on behalf of the second network element, and the model consumer of the ML model is the second network element.

[0413] Specifically, the fourth request includes the notification target address of the second network element, which is used by the first network element to directly send the model notification message to the second network element.

[0414] Optionally, the fourth request may also include the identifier (NF ID) of the third network element.

[0415] 603. The first network element sends a first message to the second network element; correspondingly, the second network element receives the first message.

[0416] The first network element sends the first message to the second network element through the target address of the second network element.

[0417] Specifically, the first message includes the unique ML modelIdentifier associated with the analysis.

[0418] In this embodiment, the first message includes a first interoperability identifier.

[0419] For example, the first network element sends a model notification (Nnwdaf_MLModelProvision_Notify) message to the second network element. The model notification message includes information about the ML model and a first interoperability identifier. The ML model information includes the identifier of the ML model, which is used to provide the service corresponding to the analysis identifier. The first interoperability identifier includes or is a list of first vendor identifiers. The vendor identifier belongs to an AnLF network element in the first vendor identifier list, and is an AnLF network element that is allowed to retrieve the ML model corresponding to the analysis ID from the first network element (MTLF network element). Alternatively, it can be understood that vendors in the first vendor identifier list are allowed to retrieve or use the ML model provided by the first network element. Alternatively, it can be understood that vendors in the first vendor identifier list are allowed to retrieve or use the ML model corresponding to the analysis ID provided by the first network element. Alternatively, it can be understood that the NWDAF network element corresponding to a vendor in the first vendor identifier list is allowed to retrieve or use the ML model provided by the first network element.

[0420] As one possible implementation, the ML model information may also include the 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 the ML model information includes an ADRF or ADRF set ID, it may also include a storage transaction ID). It is understood that the model notification message may also include other content, and this application does not limit this.

[0421] Accordingly, the second network element obtains the ML model based on the information in the ML model, and uses the ML model to provide the service consumption network element with the service corresponding to the analysis identifier.

[0422] 604. The second network element needs to be selected as the target AnLF network element.

[0423] For example, if the second network element determines that it is in an overloaded state, or close to or exceeds the service limit, or the second network element is preparing to shut down and stop providing services, then the second network element determines that it needs to select a target AnLF network element.

[0424] 605. The second network element sends a second request to the NRF network element; correspondingly, the NRF network element receives the second request.

[0425] The second request includes a second list of vendor identifiers. It is understood that the second list of vendor identifiers may include one or more vendor identifiers.

[0426] The second request is used to discover AnLF network elements, or to discover NWDAF network elements containing AnLF. For example, the second request may include a desired service name, such as analytics subscription.

[0427] The second request includes a second vendor identifier list, which is a subset of the first vendor identifier list. The NRF network element selects AnLF network elements whose vendor identifiers belong to the second vendor identifier list; that is, the vendor identifier of the fourth network element is one of the vendor identifiers in the second vendor identifier list, or it can be described as the vendor identifier of the fourth network element belonging to the second vendor identifier list.

[0428] Alternatively, as another possible implementation, the second request includes a first interoperability identifier, which may include or be a list of first vendor identifiers. Or, it can be understood that the second request includes a list of first vendor identifiers.

[0429] 606. The NRF network element sends information about the fourth network element to the second network element; correspondingly, the second network element receives the information about the fourth network element.

[0430] For example, the NRF network element sends a response message to the second network element regarding the second request. The response message includes information about one or more AnLFs. The second network element selects a fourth network element, which is one of the aforementioned one or more AnLF network elements, i.e., the target AnLF network element. The vendor identifier of the fourth network element is one of the vendor identifiers in the second vendor identifier list.

[0431] Optionally, the second network element verifies whether the vendor identifier of the AnLF network element provided by the NRF network element belongs to the second vendor identifier list. For example, if the information of the first AnLF network element sent by the NRF network element includes the vendor identifier of the first AnLF network element, the second network element can verify whether the vendor identifier belongs to the second vendor identifier list. If so, the second network element can select the first AnLF network element as the target AnLF network element. If the vendor identifiers of multiple AnLF network elements all belong to the second vendor identifier list, the second network element can randomly select or combine other information to select a target AnLF network element from the multiple AnLF network elements.

[0432] For example, if the second request includes a second vendor identifier list, which includes the identifiers of vendor 1 and vendor 2, the NRF network element selects an AnLF network element whose vendor identifiers are the identifiers of vendor 1 and / or vendor 2.

[0433] 607. The second network element sends a third request to the fourth network element; correspondingly, the fourth network element receives the third request.

[0434] The third request is used to send the (previous) analytics subscription information to the target NWDAF. The fourth network element decides whether to send an analytics subscription transfer request to the second network element.

[0435] For example, the second network element determines the fourth network element based on the message received from the fourth network element and sends an analytics subscription message to the fourth network element. The second network element uses the Nnwdaf_AnalyticsSubscription_Subscribe service to send an analytics subscription request to the target NWDAF, including information about previous analytics subscriptions. This analytics subscription information includes one or more of the following: (NWDAF ID, analytics ID, SUPI, analytics filter information for UE-related analytics, subscription association ID, analytics accuracy request information related to the requested analytics subscription). If the fourth network element accepts the analytics subscription request, it will send an Nnwdaf_AnalyticsSubscription_Subscribe response containing the subscription association ID. The fourth network element can use an analytics context transfer request (Nnwdaf_AnalyticsInfo_ContextTransfer) to request and obtain the analytics context.

[0436] In one example, when the second network element detects that the response message includes information about a fourth network element, the second network element sends an analytics subscription message to that fourth network element, which includes the previous analytics subscription information. This fourth network element is the target AnLF network element.

[0437] In another example, when the second network element discovers that the response message includes information from multiple fourth network elements, the second network element sends an analysis subscription message to the target AnLF network element, which includes previous analysis subscription information. Here, the target AnLF network element is one of the multiple fourth network elements. This application does not limit the specific method by which the second network element determines the target AnLF network element from the multiple fourth network elements.

[0438] In one possible implementation, the second network element discovers or obtains the interoperability identifier of the first network element through the NRF network element.

[0439] like Figure 6b As shown, steps 603a, 603b, or 603c replace the aforementioned steps. Figure 6a Step 603 in the illustrated embodiment. Specifically, Figure 6a Step 603 can be broken down into three independent steps: step 603a, step 603b, and step 603c. Steps 603a, 603b, and 603c will be described in detail below.

[0440] 603a. The first network element sends a first message to the second network element; correspondingly, the second network element receives the first message.

[0441] The first network element sends the first message to the second network element through the target address of the second network element.

[0442] Specifically, the first message includes a unique ML model identifier associated with the analysis identifier.

[0443] In this embodiment, the first message includes information about the first network element.

[0444] For example, the first network element sends a model notification (Nnwdaf_MLModelProvision_Notify) message to the second network element. The model notification message includes information about the ML model and information about the first network element. The ML model information includes an identifier for the ML model, which is used to provide services corresponding to the analysis identifier.

[0445] Optionally, the information of the first network element includes one or more of the following:

[0446] Network Function Instance Identifier (NF ID) of the first network element;

[0447] The first network element's Internet Protocol (IP) address can be an IPv4 address, an IPv6 address, or an IPv6 prefix.

[0448] The port number of the first network element; or,

[0449] The fully qualified domain name (FQDN) of the first network element.

[0450] In one possible implementation, the first message received by the second network element does not carry information about the first network element. The second network element determines the information about the first network element through the certificate in the first message. For example, it can determine one or more of the following information about the first network element through the TLS certificate: NF ID, IP address, port number or FQDN, etc.

[0451] 603b. The second network element sends a fifth request to the NRF network element; correspondingly, the NRF network element receives the fifth request.

[0452] After receiving the first message, the second network element obtains the first ML model based on the content of the first message. Then, the second network element decides to obtain the model producer information of the first ML model through the NRF network element.

[0453] The second network element sends a fifth request to the NRF network element. The fifth request is used to discover the desired NF instance.

[0454] For example, the fifth request is an Nnrf_NFDiscovery_Request message.

[0455] Specifically, the fifth request includes information about the first network element, such as the first network element's NF ID, IP address, port number, or FQDN.

[0456] The 603c.NRF network element sends the first configuration file to the second network element, and the second network element receives the first configuration file accordingly.

[0457] Optionally, the first NF profile is carried in the response message of the Nnrf_NFDiscovery_Request message.

[0458] Specifically, the first configuration file includes one or more configuration information for the first network element.

[0459] In this embodiment, the first configuration file includes the interoperability identifier corresponding to the first network element, i.e., the aforementioned Figure 6a The first interoperability identifier in the process.

[0460] In this application, the second network element provides analysis services to the system using the ML model provided by the first network element. When the second network element needs to determine a target AnLF network element due to internal reasons (e.g., load balancing, graceful shutdown) or external triggers (e.g., user equipment (UE) mobility), the second network element can obtain one or more AnLF network elements through the NRF network element. The vendor to which these one or more AnLF network elements belong can obtain the ML model from the first network element. The second network element then determines the fourth network element (i.e., the target AnLF network element) from the candidate one or more AnLF network elements. Therefore, after the analysis subscription is transferred to the fourth network element, the fourth network element can continue to use the ML model provided by the first network element, ensuring service continuity.

[0461] Please see Figure 7 This application provides a communication device 700, which can realize the functions of the first network element (or second network element, or third network element) in the above method embodiments, and therefore can also achieve the beneficial effects of the above method embodiments. In this application embodiment, the communication device 700 can be the first network element (or second network element, or third network element), or it can be an integrated circuit or component inside the first network element (or second network element, or third network element), such as a chip, baseband chip, modem chip, SoC chip (e.g., an SoC chip containing a modem core), SIP chip, communication module, chip system, processor, etc.

[0462] It should be noted that the transceiver unit 702 may include a transmitting unit and a receiving unit, which are used to perform transmitting and receiving respectively.

[0463] In one possible implementation, when the device 700 is for performing Figure 3 When the method executed by the first network element in the relevant embodiments is implemented, the device 700 includes a processing unit 701 and a transceiver unit 702; the processing unit 701 is used to determine a first message, the first message including the identifier of a first machine learning (ML) model and a first address; the transceiver unit 702 is used to send the first message to the second network element; the transceiver unit 702 is also used to receive a first request through the first address, the first request including the identifier of the first ML model, the first request being used to instruct the second network element to have the ability to use and / or monitor the first ML model.

[0464] In one possible implementation, when the device 700 is for performing Figure 4aWhen the method executed by the first network element in the relevant embodiments is implemented, the device 700 includes a processing unit 701 and a transceiver unit 702; the processing unit 701 is used to determine a first message, the first message including the identifier of a first machine learning ML model and second indication information, the second indication information being used to identify the first network element; the transceiver unit 702 is used to send the first message to the second network element; the transceiver unit 702 is also used to receive a first request, the first request including the identifier of the first ML model, the first request being used to instruct the second network element to have the ability to use and / or monitor the first ML model.

[0465] In one possible implementation, when the device 700 is for performing Figure 5 When the method executed by the first network element in the relevant embodiments is implemented, the device 700 includes a processing unit 701 and a transceiver unit 702; the transceiver unit 702 is used to receive a second request from a third network element, the second request including a notification target address of the second network element and a notification target address of the third network element, the second request being used to request a first machine learning (ML) model; the processing unit 701 is used to determine a first message, the first message including an identifier of the first ML model; the transceiver unit 702 is also used to send the first message through the notification target address of the second network element; the transceiver unit 702 is also used to send the first message through the notification target address of the third network element.

[0466] In one possible implementation, when the device 700 is for performing Figure 3 When the second network element executes the method in the relevant embodiments, the device 700 includes a processing unit 701 and a transceiver unit 702; the transceiver unit 702 is used to receive a first message from the first network element, the first message including the identifier of a first machine learning (ML) model and a first address; the processing unit 701 is used to determine a first request, the first request including the identifier of the first ML model, the first request being used to instruct the second network element to have the ability to use and / or monitor the first ML model; the transceiver unit 702 is also used to send the first request through the first address.

[0467] In one possible implementation, when the device 700 is for performing Figure 4a When the second network element executes the method in the relevant embodiments, the device 700 includes a processing unit 701 and a transceiver unit 702; the transceiver unit 702 is used to receive a first message from the first network element, the first message including an identifier of a first machine learning (ML) model and second indication information, the second indication information being used to identify the first network element; the processing unit 701 is used to determine a first request, the first request including the identifier of the first ML model, the first request being used to indicate that the second network element has the ability to use and / or monitor the first ML model; the transceiver unit 702 is also used to send the first request.

[0468] In one possible implementation, when the device 700 is for performing Figure 5 When the method executed by the third network element in the relevant embodiments is implemented, the device 700 includes a processing unit 701 and a transceiver unit 702; the transceiver unit 702 is used to receive a first message from the first network element, the first message including the identifier of the first machine learning (ML) model; the transceiver unit 702 is also used to receive a first request from the second network element, the first request including the identifier of the first ML model, the first request being used to instruct the second network element to have the ability to use and / or monitor the first ML model; the processing unit 701 is used to determine to forward the first request to the first network element; the transceiver unit 702 is also used to send a fifth request to the first network element, the fifth request including the identifier of the first ML model and the identifier of the second network element, the fifth request being used to instruct the second network element to have the ability to use and / or monitor the first ML model.

[0469] In one possible implementation, when the device 700 is for performing Figure 6a When the method executed by the first network element in the relevant embodiments is used, the device 700 includes a processing unit 701 and a transceiver unit 702; the transceiver unit 702 is used to receive a first request from a third network element, the first request including the identifier of the second network element, the analysis identifier, and the notification target address of the second network element, the first request indicating that the third network element requests the provision of a machine learning (ML) model corresponding to the analysis identifier on behalf of the second network element; the transceiver unit 702 is also used to send a first message through the notification target address, the first message including the identifier of the ML model and a first interoperability identifier, the first interoperability identifier corresponding to the analysis identifier.

[0470] In one possible implementation, when the device 700 is for performing Figure 6a When the method executed by the second network element in the relevant embodiments is implemented, the device 700 includes a processing unit 701 and a transceiver unit 702; the transceiver unit 702 is used to send a first request to a third network element, the first request including an analysis identifier, the first request being used to request the provision of a machine learning (ML) model corresponding to the analysis identifier; the transceiver unit 702 is also used to receive a first message from a first network element, the first message including an identifier of the ML model and a first interoperability identifier, the first interoperability identifier including a first vendor identifier list, the first interoperability identifier corresponding to the analysis identifier; the transceiver unit 702 is also used to send a second request to a network storage function network element, the second request including a second vendor identifier list, the second vendor identifier list being a subset of the first vendor identifier list; the transceiver unit 702 is also used to receive information from a fourth network element from the network storage function network element, the information of the fourth network element being used to determine the fourth network element; wherein, the vendor identifier of the fourth network element is one of the second vendor identifier lists; the transceiver unit 702 is also used to send a third request to the fourth network element, the third request including analysis subscription information corresponding to the analysis identifier.

[0471] In one possible design, when the communication device 700 is a terminal device or a communication module within a terminal, the function of the processing unit 701 can be implemented by one or more processors. Specifically, the processor may include a modem chip, a SoC chip (such as a SoC chip containing a modem core), or a SIP chip. The function of the transceiver unit 702 can be implemented by transceiver circuitry.

[0472] In one possible design, when the communication device 700 is a circuit or chip in a terminal responsible for communication functions, such as a modem chip, a SoC chip, or a SoC chip or SIP chip containing a modem core, the function of the processing unit 701 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the transceiver unit 702 can be implemented by the interface circuitry or data transceiver circuitry on the aforementioned chip.

[0473] It should be noted that the information execution process of the unit of the above-mentioned communication device 700 can be specifically described in the method embodiment shown above in this application, and will not be repeated here.

[0474] Please see Figure 8 This is another schematic structural diagram of the communication device 800 provided in this application. The communication device 800 includes a logic circuit 801 and an input / output interface 802. The communication device 800 can be a chip or an integrated circuit.

[0475] in, Figure 7 The transceiver unit 702 shown can be a communication interface, which can be... Figure 8 The input / output interface 802 may include an input interface and an output interface. Alternatively, the communication interface may also be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0476] In one possible implementation, when the device 800 is for performing Figure 3 When the method executed by the first network element in the relevant embodiments is executed, the logic circuit 801 is used to determine the first message, which includes the identifier of the first machine learning (ML) model and the first address; the input / output interface 802 is used to send the first message to the second network element; the input / output interface 802 is also used to receive the first request through the first address, which includes the identifier of the first ML model, and the first request is used to instruct the second network element to have the ability to use and / or monitor the first ML model.

[0477] In one possible implementation, when the device 800 is for performing Figure 4aWhen the method executed by the first network element in the relevant embodiments is implemented, the device 800 includes a logic circuit 801 and an input / output interface 802; the logic circuit 801 is used to determine a first message, the first message including an identifier of a first machine learning (ML) model and second indication information, the second indication information being used to identify the first network element; the input / output interface 802 is used to send the first message to the second network element; the input / output interface 802 is also used to receive a first request, the first request including the identifier of the first ML model, the first request being used to indicate that the second network element has the ability to use and / or monitor the first ML model.

[0478] In one possible implementation, when the device 800 is for performing Figure 5 When the method executed by the first network element in the relevant embodiments is implemented, the device 800 includes a logic circuit 801 and an input / output interface 802; the input / output interface 802 is used to receive a second request from a third network element, the second request including a notification target address of the second network element and a notification target address of the third network element, the second request being used to request a first machine learning (ML) model; the logic circuit 801 is used to determine a first message, the first message including an identifier of the first ML model; the input / output interface 802 is also used to send the first message through the notification target address of the second network element; the input / output interface 802 is also used to send the first message through the notification target address of the third network element.

[0479] In one possible implementation, when the device 800 is for performing Figure 3 When the second network element executes the method in the relevant embodiments, the device 800 includes a logic circuit 801 and an input / output interface 802; the input / output interface 802 is used to receive a first message from the first network element, the first message including the identifier of a first machine learning (ML) model and a first address; the logic circuit 801 is used to determine a first request, the first request including the identifier of the first ML model, the first request being used to indicate that the second network element has the ability to use and / or monitor the first ML model; the input / output interface 802 is also used to send the first request through the first address.

[0480] In one possible implementation, when the device 800 is for performing Figure 4a When the second network element executes the method in the relevant embodiments, the device 800 includes a logic circuit 801 and an input / output interface 802; the input / output interface 802 is used to receive a first message from the first network element, the first message including an identifier of a first machine learning (ML) model and second indication information, the second indication information being used to identify the first network element; the logic circuit 801 is used to determine a first request, the first request including the identifier of the first ML model, the first request being used to indicate that the second network element has the ability to use and / or monitor the first ML model; the input / output interface 802 is also used to send the first request.

[0481] In one possible implementation, when the device 800 is for performing Figure 5 When the method executed by the third network element in the relevant embodiments is implemented, the device 800 includes a logic circuit 801 and an input / output interface 802; the input / output interface 802 is used to receive a first message from the first network element, the first message including the identifier of a first machine learning (ML) model; the input / output interface 802 is also used to receive a first request from the second network element, the first request including the identifier of the first ML model, the first request being used to indicate that the second network element has the ability to use and / or monitor the first ML model; the logic circuit 801 is used to determine to forward the first request to the first network element; the input / output interface 802 is also used to send a fifth request to the first network element, the fifth request including the identifier of the first ML model and the identifier of the second network element, the fifth request being used to indicate that the second network element has the ability to use and / or monitor the first ML model.

[0482] In one possible implementation, when the device 800 is for performing Figure 6a When the method executed by the first network element in the relevant embodiments is implemented, the device 800 includes a logic circuit 801 and an input / output interface 802; the input / output interface 802 is used to receive a first request from a third network element, the first request including the identifier of the second network element, an analysis identifier, and a notification target address of the second network element, the first request indicating that the third network element requests the provision of a machine learning (ML) model corresponding to the analysis identifier on behalf of the second network element; the input / output interface 802 is also used to send a first message through the notification target address, the first message including the identifier of the ML model and a first interoperability identifier, the first interoperability identifier corresponding to the analysis identifier.

[0483] In one possible implementation, when the device 800 is for performing Figure 6aWhen the method executed by the second network element in the relevant embodiments is implemented, the device 800 includes a logic circuit 801 and an input / output interface 802; the input / output interface 802 is used to send a first request to a third network element, the first request including an analysis identifier, the first request being used to request the provision of a machine learning (ML) model corresponding to the analysis identifier; the input / output interface 802 is also used to receive a first message from a first network element, the first message including an identifier of the ML model and a first interoperability identifier, the first interoperability identifier including a first vendor identifier list, the first interoperability identifier corresponding to the analysis identifier; the input / output interface 802 is also used to send a second request to a network storage function network element, the second request including a second vendor identifier list, the second vendor identifier list being a subset of the first vendor identifier list; the input / output interface 802 is also used to receive information from a fourth network element of the network storage function network element, the information of the fourth network element being used to determine the fourth network element; wherein, the vendor identifier of the fourth network element is one of the second vendor identifier lists; the input / output interface 802 is also used to send a third request to the fourth network element, the third request including analysis subscription information corresponding to the analysis identifier.

[0484] The logic circuit 801 and the input / output interface 802 can also perform other steps executed by the first network element, the second network element, or the third network element in any embodiment and achieve corresponding beneficial effects, which will not be elaborated here.

[0485] In one possible implementation, Figure 7 The processing unit 701 shown can be Figure 8 The logic circuit 801 in the middle.

[0486] Optionally, the logic circuit 801 can be a processing device, the functions of which can be partially or entirely implemented in software.

[0487] Optionally, the processing apparatus may include a memory and a processor, wherein the memory is used to store a computer program, and the processor reads and executes the computer program stored in the memory to perform the corresponding processing and / or steps in any of the method embodiments.

[0488] Optionally, the processing device may consist of only a processor. A memory for storing computer programs is located outside the processing device, and the processor is connected to the memory via circuitry / wires to read and execute the computer programs stored in the memory. The memory and processor may be integrated together or physically independent of each other.

[0489] Optionally, the processing device may be one or more chips, or one or more integrated circuits. For example, the processing device may be one or more field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system on-chips (SoCs), central processing units (CPUs), network processors (NPs), digital signal processors (DSPs), microcontroller units (MCUs), programmable logic controllers (PLDs), or other integrated chips, or any combination of the above chips or processors.

[0490] Please see Figure 9 The communication device 900 provided in the above embodiments of this application can specifically be the communication device that serves as a terminal device in the above embodiments. Figure 9 The example shown illustrates how a terminal device can be implemented through a terminal device (or a component within a terminal device).

[0491] The present invention provides a possible logical structure diagram of the communication device 900, which may include, but is not limited to, at least one processor 901 and a communication port 902.

[0492] in, Figure 7 The transceiver unit 702 shown can be a communication interface, which can be... Figure 9 The communication port 902 in the diagram may include an input interface and an output interface. Alternatively, the communication port 902 may also be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0493] Further optionally, the device may also include at least one of a memory 903 and a bus 904. In the embodiments of this application, the at least one processor 901 is used to control the operation of the communication device 900.

[0494] Furthermore, the processor 901 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, etc. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0495] It should be noted that, Figure 9 The communication device 900 shown can be used to implement the steps implemented by the terminal device in the aforementioned method embodiments, and to achieve the corresponding technical effects of the terminal device. Figure 9 The specific implementation of the communication device shown can be referred to the description in the foregoing method embodiments, and will not be repeated here.

[0496] Please see Figure 10 The above-described embodiments of the communication device 1000 provided as an example of the present application are schematic diagrams of its structure. Specifically, the communication device 1000 can be a network device as described in the above embodiments. Figure 10 The example shown illustrates a network device implemented through a network device (or a component within a network device). The structure of this communication device can be referenced. Figure 10 The structure shown.

[0497] The communication device 1000 includes at least one processor 1011 and at least one network interface 1014. Optionally, the communication device further includes at least one memory 1012, at least one transceiver 1013, and one or more antennas 1015. The processor 1011, memory 1012, transceiver 1013, and network interface 1014 are connected, for example, via a bus. In this embodiment, the connection may include various interfaces, transmission lines, or buses, etc., and this embodiment is not limited thereto. The antenna 1015 is connected to the transceiver 1013. The network interface 1014 enables the communication device to communicate with other communication devices through a communication link. For example, the network interface 1014 may include a network interface between the communication device and core network equipment, such as an S1 interface; the network interface may also include a network interface between the communication device and other communication devices (e.g., other network devices or core network equipment), such as an X2 or Xn interface.

[0498] in, Figure 5 The transceiver unit 502 shown can be a communication interface, which can be... Figure 10 The network interface 1014 may include an input interface and an output interface. Alternatively, the network interface 1014 may also be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0499] The processor 1011 is primarily used to process communication protocols and communication data, control the entire communication device, execute software programs, and process data from the software programs, for example, to support the communication device in performing the actions described in the embodiments. The communication device may include a baseband processor and a central processing unit (CPU). The baseband processor is primarily used to process communication protocols and communication data, while the CPU is primarily used to control the entire terminal device, execute software programs, and process data from the software programs. Figure 10 The processor 1011 can integrate the functions of a baseband processor and a central processing unit. Those skilled in the art will understand that the baseband processor and the central processing unit can also be independent processors interconnected via technologies such as buses. Those skilled in the art will understand that a terminal device can include multiple baseband processors to adapt to different network standards, and a terminal device can include multiple central processing units to enhance its processing capabilities. The various components of the terminal device can be connected via various buses. The baseband processor can also be described as a baseband processing circuit or a baseband processing chip. The central processing unit can also be described as a central processing circuit or a central processing chip. The function of processing communication protocols and communication data can be built into the processor or stored in memory as a software program, with the processor executing the software program to implement the baseband processing function.

[0500] The memory is primarily used to store software programs and data. The memory 1012 can exist independently or be connected to the processor 1011. Optionally, the memory 1012 can be integrated with the processor 1011, for example, integrated within a single chip. The memory 1012 can store program code that executes the technical solutions of the embodiments of this application, and its execution is controlled by the processor 1011. The various types of computer program code being executed can also be considered as drivers for the processor 1011.

[0501] Figure 10 Only one memory and one processor are shown. In actual terminal devices, there may be multiple processors and multiple memories. Memory can also be called storage medium or storage device, etc. Memory can be a storage element on the same chip as the processor, i.e., an on-chip storage element, or it can be a separate storage element; this application does not limit this.

[0502] Transceiver 1013 can be used to support the reception or transmission of radio frequency (RF) signals between a communication device and a terminal. Transceiver 1013 can be connected to antenna 1015. Transceiver 1013 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1015 can receive RF signals. The receiver Rx of transceiver 1013 is used to receive the RF signals from the antennas, convert the RF signals into digital baseband signals or digital intermediate frequency (IF) signals, and provide the digital baseband signals or IF signals to processor 1011 so that processor 1011 can perform further processing on the digital baseband signals or IF signals, such as demodulation and decoding. In addition, the transmitter Tx in transceiver 1013 is also used to receive modulated digital baseband signals or IF signals from processor 1011, convert the modulated digital baseband signals or IF signals into RF signals, and transmit the RF signals through one or more antennas 1015. Specifically, the receiver Rx can selectively perform one or more stages of downmixing and analog-to-digital conversion on the radio frequency signal to obtain a digital baseband signal or a digital intermediate frequency (IF) signal. The order of these downmixing and IF conversion processes is adjustable. The transmitter Tx can selectively perform one or more stages of upmixing and digital-to-analog conversion on the modulated digital baseband signal or digital IF signal to obtain a radio frequency signal. The order of these upmixing and IF conversion processes is also adjustable. The digital baseband signal and the digital IF signal can be collectively referred to as digital signals.

[0503] The transceiver 1013 can also be called a transceiver unit, transceiver, transceiver device, etc. Optionally, the device in the transceiver unit that performs the receiving function can be regarded as the receiving unit, and the device in the transceiver unit that performs the transmitting function can be regarded as the transmitting unit. That is, the transceiver unit includes a receiving unit and a transmitting unit. The receiving unit can also be called a receiver, input port, receiving circuit, etc., and the transmitting unit can be called a transmitter, transmitter, or transmitting circuit, etc.

[0504] It should be noted that, Figure 10 The communication device 1000 shown can be used to implement the steps implemented by the network device in the aforementioned method embodiments, and to achieve the corresponding technical effects of the network device. Figure 10 The specific implementation of the communication device 1000 shown can be referred to the description in the foregoing method embodiments, and will not be repeated here.

[0505] This application also provides a computer-readable storage medium for storing one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in the possible implementations of the first network element, the second network element, or the third network element in the foregoing embodiments.

[0506] This application also provides a computer program product (or computer program) that, when executed by a processor, executes the method of implementing the first network element, the second network element, or the third network element as described above.

[0507] This application also provides a chip system including at least one processor for supporting a communication device in implementing the functions involved in the possible implementations of the communication device described above. Optionally, the chip system further includes an interface circuit that provides program instructions and / or data to the at least one processor. In one possible design, the chip system may also include a memory for storing the program instructions and data necessary for the communication device. The chip system may be composed of chips or may include chips and other discrete devices, wherein the communication device may specifically be the first network element, the second network element, or the third network element in the aforementioned method embodiments.

[0508] This application also provides a communication system, which includes a first network element and a second network element in any of the above embodiments.

[0509] Optionally, the communication system may also include a third network element.

[0510] Optionally, the communication system may also include NRF network elements.

[0511] Optionally, the communication system may also include a fourth network element.

[0512] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms. Whether a function is implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0513] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0514] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A communication method characterized by comprising: The method comprises: sending, by a first network element, a first message to a second network element, the first message comprising an identification of a first machine learning, ML, model and a first address; receiving, by the first network element, a first request via the first address, the first request comprising the identification of the first ML model, the first request being used to indicate that the second network element has a capability of using and / or monitoring the first ML model.

2. The method of claim 1, wherein, Before the first network element sends the first message to the second network element, the method further comprises: receiving, by the first network element, first indication information from a third network element, the first indication information being used to request the first address.

3. The method according to claim 1 or 2, characterized in that, Before the first network element sends the first message to the second network element, the method further comprises: receiving, by the first network element, a second request from a third network element, the second request comprising an identification of the second network element, the second request being used to request a first ML model.

4. The method according to any one of claims 1-3, characterized in that, The first request further comprises the identification of the second network element.

5. The method according to any one of claims 1-4, characterized in that, The method further comprises: sending, by the first network element, a second message to the second network element, the second message being used to monitor the first ML model.

6. A communication method characterized by comprising: The method comprises: sending, by a first network element, a first message to a second network element, the first message comprising an identification of a first machine learning, ML, model and second indication information, the second indication information being used to identify the first network element; receiving, by the first network element, a first request, the first request comprising the identification of the first ML model, the first request being used to indicate that the second network element has a capability of using and / or monitoring the first ML model.

7. The method of claim 6, wherein, The method comprises: receiving, by the first network element, a second request from a third network element, the second request comprising an identification of the second network element, the second request being used to request a first ML model.

8. The method of claim 7, wherein, The third network element is a network element that requests the first ML model from the first network element on behalf of the second network element.

9. The method of claim 6, wherein, The second indication information comprises one or more of: a network function instance identifier of the first network element; an internet protocol address of the first network element; a port number of the first network element; or a fully qualified domain name of the first network element.

10. A communication method characterized by comprising: The method comprises: receiving, by a first network element, a second request from a third network element, the second request comprising a notification target address of a second network element and a notification target address of the third network element, the second request being used to request a first machine learning, ML, model; sending, by the first network element, a first message via the notification target address of the second network element, the first message comprising an identification of the first ML model; sending, by the first network element, a second message via the notification target address of the third network element, the second message comprising the identification of the first ML model.

11. The method of claim 10, wherein, The method further comprises: receiving, by the first network element, a fifth request from a third network element, the fifth request comprising the identification of the first ML model and an identification of the second network element, the fifth request being used to indicate that the second network element has a capability of using and / or monitoring the first ML model.

12. A communication method characterized by comprising: The method comprises: receiving, by a second network element, a first message from a first network element, the first message comprising an identification of a first machine learning, ML, model and a first address; The second network element sends a first request through the first address, the first request comprising an identification of the first ML model, the first request being used to indicate that the second network element has the capability of using and / or monitoring the first ML model.

13. The method of claim 12, wherein, Before the second network element receives the first message, the method further comprises: The second network element sends first indication information to a third network element, the first indication information being used to request the first address.

14. The method according to claim 12 or 13, characterized in that, The first request further comprises an identification of the second network element.

15. The method according to any one of claims 12-14, characterized in that, The method further comprises: The second network element receives a second message from the first network element, the second message being used to monitor the first ML model.

16. A method of communication, comprising: Comprise: The second network element receives a first message from a first network element, the first message comprising an identification of a first machine learning (ML) model and second indication information; The second network element sends a first request to a network element identified by the second indication information, the first request comprising an identification of the first ML model, the first request being used to indicate that the second network element has the capability of using and / or monitoring the first ML model.

17. The method of claim 16, wherein, The second indication information comprises one or more of: A network function instance identifier of the first network element; An internet protocol address of the first network element; A port number of the first network element; or A fully qualified domain name of the first network element.

18. The method of claim 16 or 17, wherein, The second network element sends a first request to the first network element, comprising: The second network element sends a fourth request to a network storage function network element, the fourth request comprising the second indication information; The second network element receives a first configuration file from the network storage function network element, the first configuration file comprising one or more configuration information of the first network element; The second network element sends the first request to the first network element based on the first configuration file.

19. A method of communication, comprising: Comprise: The first network element receives a second request from a third network element, the second request comprising an identification of a second network element, the second request being used to request a first machine learning (ML) model, the third network element requesting the first ML model from the first network element on behalf of the second network element; The first network element sends a first message to the second network element, the first message comprising an identification of the first ML model and second indication information, the second indication information being used to identify the first network element; The first network element receives a first request, the first request comprising an identification of the first ML model, the first request being used to indicate that the second network element has the capability of using and / or monitoring the first ML model.

20. A method of communication, comprising: Comprise: The third network element receives a first message from a first network element, the first message comprising an identification of a first machine learning (ML) model; The third network element receives a first request from a second network element, the first request comprising an identification of the first ML model, the first request being used to indicate that the second network element has the capability of using and / or monitoring the first ML model; The third network element sends a fifth request to the first network element, the fifth request comprising an identification of the first ML model and an identification of the second network element, the fifth request being used to indicate that the second network element has the capability of using and / or monitoring the first ML model.

21. The method of claim 20, wherein, Before the third network element receives the first message from the first network element, the method further comprises: The third network element receives a third request from the second network element, the third request being used for requesting the first ML model; The third network element determines the first network element based on the third request, the first network element being a provider of the first ML model; The third network element sends a second request to the first network element, the second request comprising an identifier of the second network element, the second request being used for requesting the first ML model.

22. The method of claim 21, wherein, The second request comprises a notification target address of the second network element and a notification target address of the third network element.

23. A method of communication, comprising: Comprise: The first network element receives a first request from the third network element, the first request comprising an identifier of the second network element, an analysis identifier and a notification target address of the second network element, the first request being used for indicating that the third network element requests to provide a machine learning (ML) model corresponding to the analysis identifier on behalf of the second network element; The first network element sends a first message through the notification target address, the first message comprising an identifier of the ML model and a first interoperability identifier corresponding to the analysis identifier.

24. A method of communication, comprising: Comprise: The second network element sends a first request to the third network element, the first request comprising an analysis identifier, the first request being used for requesting to provide a machine learning (ML) model corresponding to the analysis identifier; The second network element receives a first message from the first network element, the first message comprising an identifier of the ML model and a first interoperability identifier, the first interoperability identifier comprising a first vendor identifier list, the first interoperability identifier corresponding to the analysis identifier; The second network element sends a second request to a network storage function network element, the second request comprising a second vendor identifier list, the second vendor identifier list being a subset of the first vendor identifier list; The second network element receives information of a fourth network element from the network storage function network element, the information of the fourth network element being used for determining the fourth network element; wherein a vendor identifier of the fourth network element is one of the second vendor identifier list; The second network element sends a third request to the fourth network element, the third request comprising analysis subscription information corresponding to the analysis identifier.

25. A communication system, characterized by Comprise: The first network element is configured to send a first message to a second network element, the first message comprising an identifier of a first machine learning (ML) model; The first network element is further configured to send a second message to a third network element, the second message comprising the identifier of the first ML model; The second network element is configured to send a first request to the third network element, the first request comprising the identifier of the first ML model, the first request being used for indicating that the second network element has the capability of using and / or monitoring the first ML model; The third network element sends a fifth request to the first network element, the fifth request comprising the identifier of the first ML model and an identifier of the second network element, the fifth request being used for indicating that the second network element has the capability of using and / or monitoring the first ML model; The first network element receives the fifth request.

26. A communications device, characterized by Comprise a transceiver unit and a processing unit; The transceiver unit is configured to perform the transmitting step or the receiving step in the method of any one of claims 1-24. The processing unit is configured to perform the steps in the method of any one of claims 1-24 other than the transmitting step and the receiving step.

27. A communications device, characterized by The apparatus comprises at least one processor coupled with a memory; the memory is configured to store a program or instructions; The at least one processor is configured to execute the program or instructions to cause the apparatus to implement the method of any one of claims 1-5, or to cause the apparatus to implement the method of claims 6-9, or to cause the apparatus to implement the method of claim 10 or 11, or to cause the apparatus to implement the method of any one of claims 12-15, or to cause the apparatus to implement the method of any one of claims 16-18, or to cause the apparatus to implement the method of claim 19, or to cause the apparatus to implement the method of any one of claims 20-22, or to cause the apparatus to implement the method of claim 23, or to cause the apparatus to implement the method of claim 24.

28. The communication apparatus according to claim 27, wherein The communication apparatus is a chip or a chip system.

29. A computer-readable storage medium, characterized in that, The computer readable storage medium has stored therein a computer program or instructions which, when executed by a communication apparatus, implement the method of any one of claims 1-5, or implement the method of claim 6 or 9, or implement the method of claim 10 or 11, or implement the method of any one of claims 12-15, or implement the method of any one of claims 16-18, or cause the apparatus to implement the method of claim 19, or implement the method of any one of claims 20-22, or implement the method of claim 23, or implement the method of claim 24.

30. A computer program product, characterised in that, The computer program or instructions, when executed by a computer, implement the method of any one of claims 1-5, or implement the method of claim 6 or 9, or implement the method of claim 10 or 11, or implement the method of any one of claims 12-15, or implement the method of any one of claims 16-18, or cause the apparatus to implement the method of claim 19, or implement the method of any one of claims 20-22, or implement the method of claim 23, or implement the method of claim 24.

Images