A communication method, a communication device, and a communication system

Abstract

The application provides a communication method, a communication device and a communication system, comprising: a network storage function network element receiving a first request message from a first network function, the first request message being used for requesting authorization of the first network function to obtain a model; the network storage function network element sending a second request message to a model production network element according to the first request message, the second request message being used for requesting confirmation of whether to authorize the first network function to obtain the model; the network storage network element receiving a second response message from the model production network element, and generating a first access token according to the second response message, the second response message being used for indicating authorization of the first network function to obtain the model, and the first access token being used for indicating authorization of the first network function to obtain the model; and the network storage function network element sending a first response message to the first network function, the first response message comprising the first access token, so as to ensure the security of model authorization and sharing.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication, and more particularly, to a communication method, a communication apparatus and a communication system. BACKGROUND

[0002] In the field of communication, Machine Learning (ML) model combined with NWDAF (Network Data Analytics Function) can make prediction services in different scenarios. Based on the specificity and sensitivity of AI / ML model, the NWDAF containing model analytics logical function as NF service consumer (NFc) needs to ensure that the ML model can be accessed only after the authorization of NFp by NFc when the NWDAF containing model training logical function (MTLF) as NF service producer (NFp) generates the ML model.

[0003] However, the current authorization mode according to the network repository function (NRF) in the service-based architecture (SBA) is not suitable for the demand of AI / ML model authorization. Therefore, it is urgent to ensure the security of model authorization and sharing through additional steps. SUMMARY

[0004] The present application provides a communication method, a communication apparatus and a communication system, which can ensure the security of model authorization and sharing.

[0005] In a first aspect, a communication method is provided, which includes: a network repository function network element receiving a first request message from a first network function, the first request message being used to request authorization of the first network function to obtain a model; the network repository function network element sending a second request message to a model production network element according to the first request message, the second request message being used to request confirmation of whether to authorize the first network function to obtain the model; the network repository network element receiving a second response message from the model production network element, and generating a first access token according to the second response message, the second response message being used to indicate that the first network function is authorized to obtain the model, and the first access token being used to indicate that the first network function is authorized to obtain the model; and the network repository function network element sending a first response message to the first network function, the first response message including the first access token.

[0006] It should be understood that the first network function obtaining model is requested to generate an access token for the first network function to obtain the model from a model storage network element, for example, an analytics data repository function (ADRF).

[0007] Based on the above scheme, after the network storage function network element receives the authorization request message of the first network function for obtaining the model, the network storage function network element requests authorization from the model production network element of the model, and determines whether to authorize according to the authorization response message of the model production network element. Further, the network storage function network element can issue a first access token for the first network function in the case that the model production network element agrees to authorize the first network function to obtain the model, thereby ensuring the security of model authorization and sharing.

[0008] In combination with the first aspect, in some implementations of the first aspect, the first request message includes an analytics identifier, the analytics identifier being used to indicate the type of the model; and before the network storage function network element sends a second request message to the model production network element according to the first request message, the method further includes: the network storage function network element determines the model production network element according to the analytics identifier and at least one model production network element corresponding analytics identifier stored in the network storage function network element.

[0009] Based on the above scheme, the network storage function network element determines and sends an authorization request to the model production network element that can provide the type of model requested by the first network function according to the analytics identifier carried in the request message and the analytics identifier corresponding to the model storage network element stored locally, thereby improving the flexibility of the scheme.

[0010] In combination with the first aspect, in some implementations of the first aspect, the first request message includes an analytics identifier, the analytics identifier being used to indicate the type of the model.

[0011] Based on the above scheme, the network storage function network element can obtain the type of model requested by the first network function, thereby improving the flexibility of the scheme.

[0012] In combination with the first aspect, in some implementations of the first aspect, the network storage function network element determines the model production network element according to the analytics identifier, at least one model production network element corresponding analytics identifier stored in the network storage function network element, the supplier identifier of the first network function, and the interoperability identifier of at least one model production network element stored in the network storage function network element, wherein the interoperability identifier of the at least one model production network element is used to indicate the supplier of the network function allowed to obtain the model from the at least one model production network element.

[0013] Based on the above scheme, the network storage function network element determines and sends an authorization request to the model production network element that can provide the model type requested by the first network function and is allowed to provide services to the first network function according to the analysis identifier carried in the request message, the analysis identifier corresponding to the model storage network element stored locally by the network storage function network element, the vendor identifier of the first network function, and the interoperability identifier of at least one model production network element stored locally, thereby improving the flexibility of the scheme.

[0014] In combination with the first aspect, in some implementations of the first aspect, the network storage function network element determines the model production network element according to the analysis identifier, the analysis identifier corresponding to at least one model production network element stored in the network storage function network element, the vendor identifier of the first network function, and the interoperability identifier of at least one model production network element stored in the network storage function network element, including: the network storage function network element determines at least two candidate model production network elements according to the analysis identifier in the first request message and the analysis identifier corresponding to the at least one network production network element; and the network storage function network element determines the model production network element from the at least two candidate model production network elements according to the vendor identifier of the first network function and the interoperability identifier of at least one model production network element stored in the network storage function network element.

[0015] Based on the above scheme, when the network storage function network element determines at least two candidate model storage network elements through the analysis identifier carried in the request message and the analysis identifier corresponding to the model storage network element stored locally, the network storage function network element can further determine and send an authorization request to the model production network element that can provide the model type requested by the first network function and is allowed to provide services to the first network function according to the vendor identifier of the first network function and the interoperability identifier of at least one model production network element stored locally, thereby improving the flexibility of the scheme.

[0016] In some implementations of the first aspect, the first request message further comprises the first identifier, the first identifier being used to indicate a vendor of a model production network element corresponding to a model that the first network function desires to obtain, or the first identifier being used to indicate a type of a model production network element corresponding to a model that the first network function desires to obtain; and the network storage function network element determines the model production network element according to the analysis identifier and the analysis identifiers of the at least one model production network element stored in the network storage function network element, comprising: the network storage function network element determines the model production network element according to the analysis identifier, the analysis identifiers of the at least one model production network element stored in the network storage function network element, a vendor identifier of the first network function, interoperability identifiers of the at least one model production network element stored in the network storage function network element, the first identifier, and the vendor identifiers of the at least one model production network element stored in the network storage function, wherein the interoperability identifiers of the at least one model production network element are used to indicate the vendors of the network functions that are allowed to obtain models from the at least one model production network element.

[0017] In some implementations of the first aspect, the first request message further comprises the first identifier, the first identifier being used to indicate a vendor of a model production network element corresponding to a model that the first network function desires to obtain, or the first identifier being used to indicate a type of a model production network element corresponding to a model that the first network function desires to obtain; and the network storage function network element determines the model production network element according to the analysis identifier and the analysis identifiers of the at least one model production network element stored in the network storage function network element, comprising: the network storage function network element determines the model production network element according to the analysis identifier, the analysis identifiers of the at least one model production network element stored in the network storage function network element, a vendor identifier of the first network function, interoperability identifiers of the at least one model production network element stored in the network storage function network element, the first identifier, and the vendor identifiers of the at least one model production network element stored in the network storage function, wherein the interoperability identifiers of the at least one model production network element are used to indicate the vendors of the network functions that are allowed to obtain models from the at least one model production network element.

[0018] For example, the first identifier comprises at least one vendor identifier, or the first identifier comprises at least one vendor type.

[0019] Based on the above scheme, the network storage function network element determines and sends an authorization request to a model production network element that can provide a model type requested by the first network function and is allowed to provide services to the first network function according to the analysis identifier carried in the request message, the analysis identifiers of the model storage network elements stored locally, the vendor identifier of the first network function, the interoperability identifiers of the at least one model production network element stored locally, the first identifier, and the vendor identifiers of the at least one model production network element stored in the network storage function, thereby improving the flexibility of the scheme.

[0020] With reference to the first aspect, in some implementations of the first aspect, the second request message comprises the analysis identifier.

[0021] Based on the above scheme, after determining to send the request information to the model production network element corresponding to the model, the network storage function network element carries the analysis identifier in the request information, so that the model production network element can determine whether to authorize the first network function to obtain the model according to the above request information, and ensure the security of model authorization and sharing.

[0022] With reference to the first aspect, in some implementations of the first aspect, the second request message comprises a supplier identifier of the first network function and / or an identifier of the first network function.

[0023] In other words, the second request message comprises the first identifier and / or the identifier of the first network function.

[0024] Based on the above scheme, after determining to send the request information to the model production network element corresponding to the model, the network storage function network element carries the supplier identifier of the first network function and / or the identifier of the first network function in the request information, so that the model production network element can determine whether to authorize the first network function to obtain the model according to the above request information, and ensure the security of model authorization and sharing.

[0025] With reference to the first aspect, in some implementations of the first aspect, the second response message further comprises identifier information of the model.

[0026] It should be understood that the identifier information of the model is one or more of an identifier of the model, an address of the model, and a hash value of the address of the model.

[0027] Based on the above scheme, the network storage function network element can authorize the first network function to obtain the model through the model granularity according to the identifier information of the model authorized by the model production network element to the first network function, and further enhance the security of model authorization and sharing.

[0028] With reference to the first aspect, in some implementations of the first aspect, the first access token comprises the identifier information of the model.

[0029] Based on the above scheme, the network storage function network element adds the identifier information of the model returned by the model production network element in the first access token, and enhances the security of model authorization and sharing.

[0030] In some implementations of the first aspect, the second response message further includes a second access token, the second access token being used to indicate that the first network function is authorized to obtain the model, the second access token including an identity of the first network function, an identity of the model producing network element, and the analysis identity and / or the model identification information.

[0031] Based on the above scheme, the network storage function network element can authorize the first network function to obtain the model according to the second access token generated by the model producing network element, and further enhance the security of model authorization and sharing.

[0032] In some implementations of the first aspect, the first response message further includes the second access token.

[0033] Based on the above scheme, the network storage function network element sends the second access token generated by the model producing network element to the first network function, explicitly authorizes the first network function to obtain the model, and enhances the security of model authorization and sharing.

[0034] In some implementations of the first aspect, the first access token includes the analysis identity.

[0035] Based on the above scheme, the network storage function network element adds the authorization information returned by the model producing network element in the first access token, and enhances the security of model authorization and sharing.

[0036] Based on the above scheme, the network storage function network element adds the identity of the model producing network element authorized by the first network function in the first access token, and enhances the security of model authorization and sharing.

[0037] In some implementations of the first aspect, the first access token includes a first identity, the first identity being used to indicate a vendor type of the model producing network element that the first network function is authorized to obtain.

[0038] Based on the above scheme, the network storage network element adds the first identity in the first access token, and enhances the security of model authorization and sharing.

[0039] In some implementations of the first aspect, the first access token includes an identity of the model producing network element.

[0040] Based on the above scheme, the network storage function network element adds the identity of the model producing network element in the first access token, and enhances the security of model authorization and sharing.

[0041] In a second aspect, a communication method is provided. The method comprises: receiving, by a model production network element, a request message from a network storage function network element, the request message being used to request confirmation of whether the first network function is authorized to obtain the model; determining, by the model production network element, that the first network function is authorized to obtain the model according to the request message; and sending, by the model production network element, a response message to the network storage function network element, the response message being used to indicate that the first network function is authorized to obtain the model.

[0042] Based on the above scheme, the model production network element can receive a request message from the model storage network element for the first network function to obtain the produced model, thereby determining whether the first network function is authorized to obtain the model, so as to ensure the security of model authorization and sharing.

[0043] In combination with the second aspect, in some implementations of the second aspect, the request message comprises the analysis identifier, the supplier identifier of the first network function, and the identifier of the first network function.

[0044] Based on the above scheme, the model production network element determines whether the first network function is authorized to obtain the model according to the analysis identifier, the supplier identifier of the first network function, and the identifier of the first network function carried in the request message, thereby ensuring the security of model authorization and sharing.

[0045] In combination with the second aspect, in some implementations of the second aspect, the model production network element determines that the first network function is authorized to obtain the model according to the request message, comprising: the model production network element determines the identification information of the model according to the analysis identifier; and the model production network element adds the identification information of the model in the response message.

[0046] Based on the above scheme, the model production network element further authorizes the identification information of the model of the first network function according to the analysis identifier, and authorizes the first network function to obtain the model through model granularity, thereby further enhancing the security of model authorization and sharing.

[0047] In combination with the second aspect, in some implementations of the second aspect, the model production network element determines that the first network function is authorized to obtain the model according to the request message, comprising: the model production network element generates a second access token, the second access token being used to indicate that the first network function is authorized to obtain the model, the second access token comprising the identifier of the first network function, the identifier of the model production network element, and the analysis identifier and / or the identification information of the model; and the model production network element adds the second access token in the response message.

[0048] Based on the above scheme, the model production network element issues a second access token for the first network function, and authorizes the first network function to obtain the model, thereby further enhancing the security of model authorization and sharing.

[0049] In a third aspect, a communication system is provided, and the method comprises: a first network function, a network storage function network element, and a model production network element; the network storage function network element is configured to receive a first request message from the first network function, the first request message being used to request authorization for the first network function to obtain a model; the network storage function network element is further configured to send a second request message to the model production network element according to the first request message, the second request message being used to request confirmation of whether to authorize the first network function to obtain the model; the model production network element is configured to receive the second request message from the network storage function network element; the model production network element is further configured to determine, according to the second request message, that the first network function is authorized to obtain the model; the model production network element is further configured to send a second response message to the network storage function network element, the second response message being used to indicate that the first network function is authorized to obtain the model; the network storage function network element is further configured to receive the second response message from the model production network element, and generate a first access token according to the second response message, the first access token being used to indicate that the first network function is authorized to obtain the model; and the network storage function network element is further configured to send a first response message to the first network function, the first response message comprising the first access token.

[0050] Based on the above scheme, after the network storage function network element receives the authorization request message of the first network function for obtaining the model, the network storage function network element sends an authorization confirmation message to the model production network element of the model. The model production network element can determine whether to authorize the first network function to obtain the model according to the authorization confirmation message and notify the network storage function, so that the network storage function can determine whether to authorize according to the authorization response message of the model production network element. Further, the network storage function network element can issue a first access token for the first network function in the case where the model production network element agrees to authorize the first network function to obtain the model, thereby ensuring the security of model authorization and sharing.

[0051] In combination with the third aspect, in some implementations of the third aspect, the communication system further comprises a model storage network element; the first network function is configured to send a third request message to the model storage network element, the third request message being used to request to obtain the model, and the third request message comprising the first access token; and the first network function is configured to receive a third response message from the model storage network element, the third response message comprising a storage address of the model.

[0052] Based on the above scheme, the first network function can carry the first access token generated by the network storage function based on the authorization of the model production network element, and request the model storage network element to obtain the authorized model, thereby ensuring the security of model authorization and sharing.

[0053] In a fourth aspect, a communication method is provided. The method comprises: sending, by a first network function, a first request message to a model producing network element, the first request message being used to request the model producing network element to authorize the first network function to obtain a first model, the first model being generated by the model producing network element; receiving, by the first network function, a first access token from the model producing network element, the first access token being used to represent that the first network function is authorized to obtain the first model; sending, by the first network function, a second request message to a model storage network element, the second request message being used to request to obtain the first model, the second request message comprising the first access token; and receiving, by the first network function, a second response message from the model storage network element, the second response message comprising a storage address of the first model.

[0054] Based on the above scheme, the first network function can carry the generated first access token of the model producing network element, and request the model storage network element to obtain the authorized model, thereby ensuring the security of model authorization and sharing.

[0055] In combination with the fourth aspect, in some implementations of the fourth aspect, the first request message comprises one or more of the following: a first analysis identifier, the first analysis identifier being used to indicate a type of the first model; an identifier of the model storage network element; a supplier of a model producing network element corresponding to a model that the first network function expects to obtain.

[0056] Based on the above scheme, the first network function includes the above information in the first request message, so that the model producing network element determines the specific authorization information of the first model authorized to be obtained by the first network function according to the information in the first request message, thereby ensuring the security of model authorization and sharing.

[0057] In combination with the fourth aspect, in some implementations of the fourth aspect, the first access token comprises one or more of the following: an identifier of the first network function; an identifier of the model producing network element; the first analysis identifier; and identifier information of the model.

[0058] It should be understood that the identifier information of the model is one or more of the following: an identifier of the model, an address of the model, and a hash value of the address of the model.

[0059] Based on the above scheme, the model storage network element determines the first model authorized to be obtained by the first network function according to the content of the first access token, thereby ensuring the security of model authorization and sharing.

[0060] In combination with the fourth aspect, in some implementations of the fourth aspect, the first access token comprises a first identifier, the first identifier being used to indicate an issuer of the first access token, the issuer of the first access token being the model producing network element or a network storage function, the network storage function being used to authenticate and authorize the first network function and the model producing network element.

[0061] Based on the above scheme, the first access token can be issued by the model production network element, or requested by the model production network element to be issued by the network storage function, thereby improving the flexibility of the scheme while ensuring the security of model authorization and sharing.

[0062] In combination with the fourth aspect, in some implementations of the fourth aspect, the first response message further includes a first ticket, the first ticket being used to bind an address of the first model and the first network function; and the method further includes: the first network function obtaining the first model according to the storage address of the first model and the first ticket.

[0063] Based on the above scheme, by limiting the first ticket to allow the first network function to obtain the first model from the storage address of the first model, the security of model authorization and sharing is further improved.

[0064] In combination with the fourth aspect, in some implementations of the fourth aspect, the second request message further includes a second access token, the second access token being used to represent that the first network function is authorized to access the model production network element, and the second token includes an identifier of a supplier of the model production network element corresponding to the first model that the first network function is authorized to obtain.

[0065] Based on the above scheme, the first network function needs to pass through the authorization of the network storage function when accessing the model production function, and the second access token further includes an identifier of a supplier of the model production network element corresponding to the first model that the first network function is authorized to obtain, so that the model production network element can determine whether it belongs to the authorized range of the second access token, thereby ensuring the security of model authorization and sharing.

[0066] In combination with the fourth aspect, in some implementations of the fourth aspect, the method further includes: the first network function sending a third request message to the network storage function, the third request message being used to request authorization to access the second network function; and the first network function receiving a third response message, the third response message including a third token, the third token being used to represent that the first network function is authorized to access the second network function.

[0067] Based on the above scheme, the first network function needs to pass through the authorization of the network storage function when accessing the model storage function, thereby ensuring the security of model authorization and sharing.

[0068] In a fifth aspect, a communication method is provided. The method includes: receiving, by a model storage network element, a second request message from a first network function, the second request message being used to request a first model, the second request message including a first access token, the first access token being used to indicate that the first network function is authorized to obtain the first model; determining, by the model storage network element, that the first network function is authorized to obtain the first model according to the first access token; and sending, by the model storage network element, a first response message, the first response message including a storage address of the first model.

[0069] According to the above scheme, the model storage network element provides the first network function with the storage address of the first model according to the first access token, thereby ensuring the security of model authorization and sharing.

[0070] In combination with the fifth aspect, in some implementations of the fifth aspect, the first access token includes one or more of: an identifier of the first network function; an identifier of the model production network element; the first analysis identifier; and identifier information of the model.

[0071] It should be understood that the identifier information of the model is one or more of: an identifier of the model, an address of the model, and a hash value of the address of the model.

[0072] According to the above scheme, the model storage network element determines the first model that the first network function is authorized to obtain according to the content of the first access token, thereby ensuring the security of model authorization and sharing.

[0073] In combination with the fifth aspect, in some implementations of the fifth aspect, the first response message further includes a first ticket, the first ticket being used to bind the address of the first model and the first network function; and the method further includes: obtaining, by the first network function, the first model according to the storage address of the first model and the first ticket.

[0074] According to the above scheme, the network storage function limits the first network function to obtain the first model from the storage address of the first model through the first ticket, thereby further improving the security of model authorization and sharing.

[0075] In a sixth aspect, a communication method is provided. The method includes: receiving, by a model production network element, a first request message, the first request message being used to request authorization of a first network function to obtain a first model; obtaining, by the model production network element, a first access token according to the first request message, the first access token being used to indicate that the first network function is authorized to obtain the first model; and sending, by the model production network element, a first response message, the first response message including the first access token.

[0076] Based on the above scheme, the model production network element determines whether to authorize the first network function to obtain the first model according to the request message sent by the first network function, and when determining to authorize, the model production network element generates and sends a first access token to the first network function, so that the first network function can obtain the first model through the first access token, thereby ensuring the security of model authorization and sharing.

[0077] In combination with the sixth aspect, in some implementations of the sixth aspect, the first request message includes one or more of the following: a first analysis identifier, the first analysis identifier being used to indicate the type of the first model; an identifier of the model storage network element; a supplier of a model production network element corresponding to a model that the first network function expects to obtain.

[0078] Based on the above scheme, the model production network element determines the specific authorization information of the first model authorized for the first network function to obtain according to the information in the first request message, thereby ensuring the security of model authorization and sharing.

[0079] In combination with the sixth aspect, in some implementations of the sixth aspect, the model production network element obtains the first access token according to the first request message, including: the model production network element generates the first access token according to the first request message; or the model production network element sends a fourth request message to a network storage function, the fourth request message being used to request the first access token; and the model production network element receives a fourth response message from the network storage function, the fourth response message including the first access token.

[0080] Based on the above scheme, the model production network element generates the first access token according to the first request message, or requests the network storage function to generate the first access token, thereby improving the flexibility of the scheme.

[0081] In combination with the sixth aspect, in some implementations of the sixth aspect, the first access token includes one or more of the following: an identifier of the first network function; an identifier of the model production network element; the first analysis identifier; and identifier information of the model.

[0082] It should be understood that the identifier information of the model is one or more of the following: an identifier of the model, an address of the model, and a hash value of the address of the model.

[0083] Based on the above scheme, the model production network element adds the above information in the first access token, so that the model storage network element determines the first model authorized for the first network function to obtain according to the content of the first access token, thereby ensuring the security of model authorization and sharing.

[0084] In a seventh aspect, an apparatus is provided for implementing the method of the second aspect. The apparatus includes a transceiver configured to receive a first request message from a first network function, the first request message requesting authorization for the first network function to obtain a model; a processor configured to generate a second request message to a model production network element based on the first request message, the second request message requesting confirmation of whether the first network function is authorized to obtain the model; the transceiver is further configured to receive a second response message from the model production network element, the second response message indicating that the first network function is authorized to obtain the model; the processor is further configured to generate a first access token based on the second response message, the first access token indicating that the first network function is authorized to obtain the model; and the transceiver is further configured to transmit a first response message to the first network function, the first response message including the first access token.

[0085] The apparatus can specifically perform each step in the first aspect, for example, the sending unit is configured to perform the sending process, and the processing unit is configured to perform other processes in addition to the transceiving process. Various specific implementations of the apparatus can refer to the foregoing first aspect, and will not be described again.

[0086] In an eighth aspect, an apparatus is provided, which includes a transceiver configured to receive a request message from a network storage function network element, the request message requesting confirmation of whether a first network function is authorized to obtain a model; a processor configured to determine that the first network function is authorized to obtain the model based on the request message; and the transceiver is further configured to transmit a response message to the network storage function network element, the response message indicating that the first network function is authorized to obtain the model.

[0087] The apparatus can specifically perform each step in the second aspect, for example, the sending unit is configured to perform the sending process, and the processing unit is configured to perform other processes in addition to the transceiving process. Various specific implementations of the apparatus can refer to the foregoing first aspect, and will not be described again.

[0088] In a ninth aspect, an apparatus is provided, which includes a transceiver configured to transmit a first request message to a model production network element, the first request message requesting the model production network element to authorize a first network function to obtain a first model, the first model being generated by the model production network element; the transceiver is further configured to receive a first access token from the model production network element, the first access token indicating that the first network function is authorized to obtain the first model; the transceiver is further configured to transmit a second request message to a model storage network element, the second request message requesting to obtain the first model, the second request message including the first access token; and a processor configured to receive a second response message from the model storage network element, the second response message including a storage address of the first model.

[0089] The apparatus can specifically perform the steps in the fourth aspect described above, for example, the sending unit is configured to perform the sending process, and the processing unit is configured to perform other processes in addition to the sending process. Various specific implementations of the apparatus can refer to the first aspect described above, and will not be described again.

[0090] In a ninth aspect, an apparatus is provided, which includes: a transceiver configured to receive a second request message from a first network function, the second request message being configured to request a first model, the second request message including a first access token, the first access token being configured to indicate that the first network function is authorized to obtain the first model; a processor configured to determine, according to the first access token, that the first network function is authorized to obtain the first model; and the transceiver configured to send a first response message, the first response message including a storage address of the first model.

[0091] The apparatus can specifically perform the steps in the fifth aspect described above, for example, the sending unit is configured to perform the sending process, and the processing unit is configured to perform other processes in addition to the sending process. Various specific implementations of the apparatus can refer to the first aspect described above, and will not be described again.

[0092] In a tenth aspect, an apparatus is provided, which includes: a transceiver configured to receive a first request message, the first request message being configured to request authorization for a first network function to obtain a first model; a processor configured to obtain a first access token according to the first request message, the first access token being configured to indicate that the first network function is authorized to obtain the first model; and the model production network element sending a first response message, the first response message including the first access token.

[0093] The apparatus can specifically perform the steps in the sixth aspect described above, for example, the sending unit is configured to perform the sending process, and the processing unit is configured to perform other processes in addition to the sending process. Various specific implementations of the apparatus can refer to the first aspect described above, and will not be described again.

[0094] In an eleventh aspect, a computer program product is provided, which includes: a computer program (also referred to as code or instructions), when the computer program is executed, causes a computer to execute the method in the first aspect to the twelfth aspect and any possible implementation manner of the first aspect to the twelfth aspect.

[0095] In a twelfth aspect, a computer readable medium is provided, which stores a computer program (also referred to as code or instructions), when the computer program is executed on a computer, causes the computer to execute the method in the first aspect to the tenth aspect and any possible implementation manner of the first aspect to the tenth aspect.

[0096] In a thirteenth aspect, a processing apparatus is provided, including a processor and a memory. The processor is configured to read instructions stored in the memory, and is configured to receive a signal via a receiver, transmit a signal via a transmitter, to perform the method in the first aspect to the twelfth aspect and any possible implementation of the first aspect to the twelfth aspect.

[0097] In a certain possible implementation, the processor is one or more, and the memory is one or more.

[0098] In a certain possible implementation, the memory can be integrated with the processor, or the memory is separately arranged from the processor.

[0099] In a specific implementation process, the memory can be a non-transitory memory, for example, a read only memory (ROM), which can be integrated on the same chip as the processor, or can be separately arranged on different chips. The embodiments of the present application do not limit the type of memory and the arrangement of the memory and the processor.

[0100] Optionally, the related data interaction process, for example, the process of sending the indication information, can be the process of outputting the indication information from the processor, and the process of receiving the capability information can be the process of receiving the input capability information by the processor. Specifically, the data processed for output can be output to the transmitter, and the input data received by the processor can come from the receiver. The transmitter and the receiver can be collectively referred to as a transceiver.

[0101] The processor in the thirteenth aspect described above can be a chip, which can be implemented by hardware or software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented by software, the processor can be a general-purpose processor, which is configured to read software codes stored in the memory to implement the processor. The memory can be integrated in the processor, or can exist independently of the processor. BRIEF DESCRIPTION OF DRAWINGS

[0102] Figure 1 FIG. 1 is a schematic diagram of a network architecture 100 to which the embodiments of the present application are applicable.

[0103] Figure 2 FIG. 2 is a flowchart of a method 200 for obtaining an access token and an NF service.

[0104] Figure 3 FIG. 3 is a flowchart of a model sharing method 300 provided by the embodiments of the present application.

[0105] Figure 4 FIG. 4 is a flowchart of another model sharing method 400 provided by the embodiments of the present application.

[0106] Figure 5 FIG. 5 is a flowchart of a communication method 500 according to an embodiment of the present application.

[0107] Figure 6 FIG. 6 is a flowchart of another communication method 600 according to an embodiment of the present application.

[0108] Figure 7 FIG. 10 is a schematic diagram of a communication apparatus 1000 according to an embodiment of the present application.

[0109] Figure 8 FIG. 20 is a schematic diagram of another communication apparatus 2000 according to an embodiment of the present application.

[0110] Figure 9 FIG. 30 is a schematic diagram of a chip system 3000 according to an embodiment of the present application. DETAILED DESCRIPTION

[0111] The technical solutions in the present application will be described below with reference to the drawings.

[0112] The technical solutions in the embodiments of the present application can be applied to various communication systems, for example, 5G system or new radio (NR), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), etc. The technical solutions provided in the present application can also be applied to future communication systems, such as the sixth generation mobile communication system. The technical solutions in the embodiments of the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and internet of things (IoT) communication system or other communication systems.

[0113] For the convenience of description, the 5G network will be taken as an example for description in the embodiments of the present application.

[0114] Figure 1 FIG. 10 is a schematic diagram of a communication apparatus 1000 according to an embodiment of the present application. Figure 1 As shown in FIG. 10, the network architecture can include three parts, which are terminal device part, data network (DN) and operator network PLMN part. The functions of the network elements in each part will be briefly described below.

[0115] The terminal device part can include a terminal device 110, which can also be referred to as a user equipment (UE). The terminal device 110 in this application is a device with wireless transceiver function, which can communicate with one or more core network (CN) devices through an access network device (or also referred to as an access device) in a radio access network (RAN) 140. The terminal device 110 can also be referred to as an access terminal, a terminal, a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a user agent, or a user device, etc. The terminal device 110 can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on water (such as ships, etc.); can also be deployed in the air (such as airplanes, balloons and satellites, etc.). The terminal device 110 can be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a smart phone, a mobile phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), etc. Alternatively, the terminal device 110 can also be a handheld device, a computing device or other device connected to a wireless modem with wireless communication function, a vehicle-mounted device, a wearable device, a unmanned aerial vehicle device, or a terminal in Internet of Things, Internet of Vehicles, 5G network and future network, any form of terminal in future network, relay user equipment or terminal in future evolved 6G network, etc. Among them, the relay user equipment can be a 5G residential gateway (RG), for example. For example, the terminal device 110 can be a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. The terminal device here refers to a 3GPP terminal. The embodiments of this application do not limit the type or category of terminal device. For ease of description, the following embodiments of this application take the UE as an example to illustrate the terminal device.

[0116] The operator network PLMN part can include, but is not limited to, a (radio) access network ((R)AN) 120 and a core network (CN) part.

[0117] The (R)AN 120 can be regarded as a sub-network of the operator network, and is an implementation system between a service node of the operator network and the terminal device 110. To access the operator network, the terminal device 110 first accesses the (R)AN 120, and then can be connected to the service node of the operator network through the (R)AN 120. The access network device (RAN device) in the embodiments of the present application is a device that provides wireless communication functions for the terminal device 110, and can also be referred to as a network device. The RAN device includes, but is not limited to, a next generation node base station (gNB) in a 5G system, an evolved node B (eNB) in a long term evolution (LTE), a radio network controller (RNC), a node B (NB), a base station controller (BSC), a base transceiver station (BTS), a home base station (for example, a home evolved node B or a home node B, HNB), a base band unit (BBU), a transmitting and receiving point (TRP), a transmitting point (TP), a pico, a mobile switching center, or a network device in a future network, etc. In systems using different wireless access technologies, the names of devices with access network device functions may be different. For convenience of description, all embodiments of the present application collectively refer to the above-mentioned devices that provide wireless communication functions for the terminal device 110 as access network devices or simply as RAN or AN. It should be understood that the specific types of access network devices are not limited herein.

[0118] The CN part can include, but is not limited to, the following network functions (NFs): user plane function (UPF) 130, network exposure function (NEF) 131, network function repository function (NRF) 132, policy control function (PCF) 133, unified data management (UDM) 134, unified data repository (UDR) 135, network data analytics function (NWDAF) 136, authentication server function (AUSF) 137, access and mobility management function (AMF) 138, session management function (SMF) 139.

[0119] The data network DN 140, which can also be referred to as a packet data network (PDN), is usually a network outside the operator network, for example, a third-party network. Of course, in some implementations, the DN can also be deployed by the operator, that is, the DN belongs to a part of the PLMN. The present application does not limit whether the DN belongs to the PLMN. The operator network PLMN can access multiple data networks DN 140, and multiple services can be deployed on the data network DN 140 to provide data and / or voice services for the terminal device 110. For example, the data network DN 140 can be a private network of a certain smart factory, and the sensors installed in the workshop of the smart factory can be terminal devices 110. A control server of the sensors is deployed in the data network DN 140, and the control server can provide services for the sensors. The sensors can communicate with the control server, obtain instructions from the control server, and transmit the collected sensor data to the control server according to the instructions, and the like. For another example, the data network DN 140 can be an internal office network of a certain company, and the mobile phones or computers of employees of the company can be terminal devices 110. The mobile phones or computers of the employees can access information and data resources on the internal office network of the company. The terminal device 110 can establish a connection with the operator network through an interface (for example, N1, etc.) provided by the operator network, and use data and / or voice services provided by the operator network. The terminal device 110 can also access the data network DN 140 through the operator network, use operator services deployed on the data network DN 140, and / or third-party services.

[0120] The CN includes NF functions, which are further briefly described below.

[0121] 1. The UPF 130 is a gateway provided by the operator, which is a gateway for communication between the operator network and the data network DN 140. The UPF network function 130 includes functions related to the user plane, such as data packet routing and transmission, data packet detection, service usage reporting, quality of service (QoS) processing, lawful monitoring, uplink data packet detection, and downlink data packet storage.

[0122] 2. The NEF 131 is a control plane function provided by the operator, which mainly enables third parties to use services provided by the network, supports network exposure of its capabilities, event and data analysis, provision of information to PLMN security from external applications, conversion of information between the inside and outside of the PLMN, and the like.

[0123] 3. NRF 132 is a control plane function provided by an operator, which can be used to maintain real-time information of network functions, services in the network. For example, support network service discovery, maintain NF profile supported services, support service discovery of service communication proxy (SCP), maintain SCP profile of SCP instance, send notifications about newly registered, deregistered, updated NF and SCP, maintain health status of NF and SCP running, etc.

[0124] 4. PCF 133 is a control plane function provided by an operator, which supports a unified policy framework to govern network behavior, provides policy rules, subscription information related to policy decision to other control functions, etc.

[0125] 5. UDM 134 is a control plane function provided by an operator, which is responsible for storing information such as subscriber permanent identifier (SUPI) of a subscribed user in an operator network, generic public subscription identifier (GPSI) of a subscribed user, credential, etc. The SUPI will be encrypted first in the transmission process, and the encrypted SUPI is called subscription concealed identifier (SUCI). The information stored by the UDM network function 134 can be used for authentication and authorization of the terminal device 110 accessing the operator network. Among them, the subscribed user of the operator network can be a user who uses the services provided by the operator network, for example, a user who uses a China Telecom mobile phone chip card (subscriber identity module, SIM) card, or a user who uses a China Mobile mobile phone chip card, etc. The credential of the subscribed user can be a long-term key stored in the mobile phone chip card or a small file stored in the mobile phone chip card related to the encryption of the mobile phone chip card, which is used for authentication and / or authorization. It should be noted that the permanent identifier, the credential, the security context, the authentication data (cookie), and the token are all information related to verification / authentication and authorization, which are not distinguished and limited in the embodiments of the present application for the sake of convenience.

[0126] 6. UDR 135 is a control plane function provided by an operator, which provides storage and retrieval of subscription data for UDM, storage and retrieval of policy data for PCF, storage and retrieval of user NF group ID (group ID) information, etc.

[0127] 7. NWDAF 136 is a control plane function provided by the operator, whose main function is to collect data from NFs, external application functions (AFs), and operations, administration and maintenance (OAM) systems, etc., and provide NWDAF services such as registration, data exposure, and analysis data for NFs and AFs. Specifically, the NWDAF can include the following logical functions:

[0128] Analyze Logical Function (AnLF): a logical function in the NWDAF, used to perform inference, derive analysis information (i.e., derive statistics and / or predictions according to analysis consumer requests), and expose analysis services.

[0129] Model Training Logical Function (MTLF): a logical function in the NWDAF that trains machine learning (ML) models and exposes new training services, e.g., provides trained ML models.

[0130] It should be understood that the NWDAF can contain the MTLF or the AnLF or both logical functions. Among them, the NWDAF containing the AnLF is locally configured with the NWDAF ID containing the MTLF and the analysis ID (s) supported by each NWDAF containing the MTLF to retrieve the trained ML model. If necessary, the NWDAF containing the AnLF uses NWDAF discovery for the NWDAF containing the MTLF in the configuration ID set of the NWDAF containing the MTLF.

[0131] It should be understood that in order to ensure the accuracy of the analysis output of the analysis ID, based on the UE abnormal behavior analysis from itself or other NWDAFs, including the abnormal UE list and the observed time window, the NWDAF is used to detect and can delete the input data from the abnormal UE, and then can generate a new ML model and / or analysis output for the analysis ID during the observed time window without input data related to the abnormal UE list, and then send / update the ML model information and / or analysis output to the subscribed NWDAF service consumer.

[0132] In order to support NF discovery and selection of NWDAF instances containing MTLF, AnLF or both, which can provide the required services (such as analysis exposure or ML model deployment) for the required type of analysis, each NWDAF instance should provide a list of supported analysis IDs (possibly per supported service) and other NRF registration elements of the NF configuration file when registering to the NRF. NFs that need to discover NWDAF instances that support certain specific services for a specific type of analysis can query the NRF for NWDAFs that support the required services and the required analysis IDs.

[0133] The NWDAF architecture allows arranging multiple NWDAF instances in a hierarchy / tree with a flexible number of layers / branches. The number and organization of the hierarchy layers and the functionality of each NWDAF instance remains a deployment choice.

[0134] In a layered deployment, when DCCF, MFAF are not present in the network, the NWDAF can provide data collection exposure capabilities for generating analytics based on data collected by other NWDAFs.

[0135] In order for the NWDAF to be discoverable in some network deployments, the NWDAF can be configured (e.g. for UE mobility analytics) to register in the UDM (Nudm_UECM_Registration service operation) the UEs it serves and the related analytics ID. The registration in the UDM should happen when the NWDAF starts to serve or collect data for a UE(s). The deregistration in the UDM happens when the NWDAF deletes the analytics context for a UE of the related analytics ID (see clause 6.1B.4).

[0136] In future communication systems, the network data analytics function network element can still be the NWDAF network element, or, there can be other names, which are not limited by the present application.

[0137] 8、AUSF 137 is a control plane function provided by an operator, which is usually used for primary authentication, i.e., authentication between the terminal device 110 (a subscription user) and the operator network. After receiving an authentication request initiated by the subscription user, the AUSF network function 137 can authenticate and / or authorize the subscription user through authentication information and / or authorization information stored in the UDM network function 134, or generate authentication and / or authorization information of the subscription user through the UDM network function 134. The AUSF network function 137 can feed back authentication information and / or authorization information to the subscription user.

[0138] 9、AMF 138 is a control plane network function provided by an operator network, which is responsible for access control and mobility management of the terminal device 110 accessing the operator network, including, for example, mobile state management, allocation of a user temporary identity, authentication and authorization of a user, and the like.

[0139] 10. The SMF 139 is a control plane network function provided by the operator network, responsible for managing the protocol data unit (PDU) session of the terminal device 110. The PDU session is a channel for transmitting PDU, and the terminal device needs to transmit PDU with the data network DN 140 through the PDU session. The PDU session is responsible for establishment, maintenance and deletion, etc. by the SMF network function 139. The SMF network function 139 includes session management (such as session establishment, modification and release, including tunnel maintenance between the user plane function UPF 130 and the (R)AN 120), selection and control of the UPF network function 130, service and session continuity (SSC) mode selection, roaming and other session-related functions.

[0140] Optionally, the network architecture can also include a data collection coordination function (DCCF) network element and an analytics data repository function (ADRF) network element. Among them, the ADRF provides storage and retrieval services for data and analysis for consumers. For example, the consumer sends the Nadrf_DataManagement_StorageRequest containing the data or analysis to be stored to the ADRF; or the consumer sends the Nadrf_DataManagement_StorageSubscriptionRequest to the ADRF, requesting the ADRF to subscribe to receive data or analysis for storage, and then the ADRF subscribes to the NWDAF or DCCF to obtain data or analysis, providing the ADRF notification address (or notification association ID). Analysis or data is then provided as a notification using DCCF, NWDAF or MFAF services (Ndccf_DataManagement Nnwdaf_DataManagement or Nmfaf_3caDataManagement services).

[0141] Exemplarily, the consumer sends a Nadrf_DataManagement_RetrievalRequest request to the ADRF to retrieve data or analytics for a specified data or analytics collection time window. The ADRF determines the availability of the data or analytics in its repository and sends the data or analytics, or a description of the data or analytics, to the consumer in a response; or the consumer sends a Nadrf_DataManagement_RetrievalSubscribe request to the ADRF to retrieve data or analytics for a specified data or analytics collection time window. If the time window includes the future, and the ADRF has subscribed to receive the data or analytics, then the subsequent notifications received by the ADRF will be sent by the ADRF to the notification endpoint. The ADRF determines the availability of the data or analytics and sends a success / failure indication to the consumer in a response. The ADRF then sends one or more notifications to the consumer specified notification address (or notification association ID) using Nadrf_DataManagement_RetrievalNotify. The notifications provide the data or analytics, or provide the endpoint with instructions to obtain the data or analytics using Nadrf_DataManagement_RetrievalRequest.

[0142] It can be understood that the above network elements or functions can be either physical entities in hardware devices, or software instances running on special hardware, or virtualized functions instantiated on a shared platform (for example, a cloud platform). In short, an NF can be implemented by hardware or software.

[0143] Figure 1 The Nnef, Nnrf, Npcf, Nudm, Nudr, Nnwdaf, Nausf, Namf, Nsmf, N1, N2, N3, N4, and N6 are interface sequence numbers. Exemplarily, the meanings of the above interface sequence numbers can refer to the meanings defined in the 3GPP standard protocol, and the meanings of the above interface sequence numbers are not limited in the present application. It should be noted that, Figure 1 The interface names between the various network functions in the above are only examples, and in specific implementations, the interface names of the system architecture can also be other names, which are not limited in the present application. In addition, the names of the messages (or signaling) transmitted between the above various network elements are also only examples, and do not constitute any limitation on the functions of the messages themselves.

[0144] It should be noted that the interfaces between the various control plane network elements can also be point-to-point interfaces, which are not described here.

[0145] It should be understood that the network architecture to which the above embodiments of the present application can be applied is only illustratively described, and the network architecture to which the embodiments of the present application are applicable is not limited thereto, and any network architecture including the functions of the above-mentioned network elements is applicable to the embodiments of the present application.

[0146] It should also be understood that Figure 1 The AMF, SMF, UPF, PCF, UDM, etc. shown can be understood as network elements for realizing different functions, for example, can be combined into network slices as needed. These network elements can be independent devices, can be integrated into the same device to realize different functions, or can be network elements in a hardware device, or can be software functions running on a dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform), and the specific form of the network elements is not limited by the present application.

[0147] It should also be understood that the above naming is only defined for the convenience of distinguishing different functions and should not constitute any limitation on the present application. The present application does not exclude the possibility of using other names in 5G networks and other future networks. For example, in a 6G network, some or all of the above-mentioned network elements can use the terms in 5G, or other names, etc.

[0148] It should also be understood that Figure 1 The interface names between the various network elements of the above-mentioned are only an example, and the names of the interfaces in the specific implementation can be other names, and the present application does not make specific limitations thereon. In addition, the names of the messages (or signaling) transmitted between the above-mentioned network elements are also only an example, and do not constitute any limitation on the functions of the messages themselves.

[0149] The network architecture and service scenarios described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0150] In the service-oriented system architecture of 5G, the two parties based on service-oriented interface communication are called service consumer (service consumer) and service producer (service producer). The party requesting the service is the service consumer, and the party providing the service is the service producer. The service consumer can also be called consumer, consumer network element, user, requestor, or service consumer network element, etc. The service producer can also be called provider network element, service provider network element, provider, producer, or responder, etc., and the present application does not make any limitation.

[0151] For service-based architecture, the standard defines two ways of authorization for inter-access between NFs, one is static authorization, and the other is Oauth authorization.

[0152] Specifically, the static authorization is a mechanism based on local authorization policy. For example, in the scenario of AMF accessing SMF, SMF judges whether to allow AMF to access its own service according to the parameters in the service request sent by AMF and the local policy. If it is judged that the AMF is allowed to access its own service according to the local authorization policy, the service is provided for the AMF. Here, the local policy can be whether to allow the AMF type network to access its own service, and the examples of the local policy are not limited in the present application.

[0153] The Oauth authorization refers to an open authorization mechanism based on authorization parameters such as tokens, which includes entities such as authorization center, service user, service provider or resource owner. The authorization center authorizes whether the service user is allowed to use the service of the service provider. If allowed, the token is distributed to the service user. The service user sends the token to the service provider, and the service provider provides the service for the service user when the token verification is successful. In the 5G network, an NRF network element is defined, which is responsible for the judgment of service authorization. For example, before accessing the service providing function network element (NF service producer, NFp), the service consumer function network element (NF service consumer, NFc) will first send a request message to the NRF, and the NRF will generate an authorization token after judging that the NFc is allowed to access the NFp, and send the token to the NFc. Then, the NFc sends a service request when accessing the NFp service, which carries the token. The NFp provides the corresponding service for the NFc after verifying the token successfully. The following will be described in detail in combination with the specific embodiments. Figure 2 Briefly introduce how the NF service consumer obtains the access token before accessing the service of the NF service producer of a specific NF type.

[0154] Figure 2 It is a flowchart of a method 200 for obtaining an access token and NF service. As shown in the figure, the method comprises the following steps: Figure 2

[0155] S210, the NFc (for example, NWDAF) sends an access token request message #1 to the authorization service function network element (for example, NRF);

[0156] Correspondingly, the NRF receives the access token request message #1 from the NFc.

[0157] ​The token request message #1 gets information for requesting the NRF to authorize the NF consumer and issue an access token.

[0158] Exemplarily, the NFc can request an access token to access the service of the NFp of a specific NF type, the token request message #1 including the NF instance ID(s) of the NF service consumer, the requested "scope", the NF type of the intended NF service producer instance, or the intended NF service name and the NF instance ID of the NF service consumer. Wherein, the requested "scope" includes the intended NF service name and optionally "additional scope" information including the requested resource and the requested resource operation (service operation).

[0159] Exemplarily, the NFc can request an access token to access the service of the NFp of a specific NF type, the token request message #1 including the NF instance ID(s) of the NF service consumer, the requested "scope", the NF type of the intended NF service producer instance, or the intended NF service name and the NF instance ID of the NF service consumer. Wherein, the requested "scope" includes the intended NF service name and optionally "additional scope" information including the requested resource and the requested resource operation (service operation).

[0160] Optionally, the NF service consumer includes a list of NSSAI or a list of NSI ID of the intended NF service producer instance.

[0161] Optionally, the token request gets information further including the NF Set ID of the intended NF service producer instance and a list of S-NSSAI of the NF service consumer.

[0162] Exemplarily, the request message #1 can be referred to as Nnrf_AccessToken_Get Request message. It should be understood that the name of the message (or information) in the present application is not limited in any way, as long as the corresponding function can be realized.

[0163] Optionally, before NFc sends access token request message #1 to NRF, both NFc and NFp complete registration with NRF. To ensure the security of information exchange between NF and NRF, the registration information exchange can follow the OAuth 2.0 standard authorization framework defined by the Internet Engineering Task Force (IETF). In OAuth 2.0, the client corresponds to NFc, the client ID corresponds to the NFc instance ID, and the authorization server corresponds to NRF. The specific NF registration process can be found in existing protocols and will not be elaborated here.

[0164] It should be noted that this implementation method applies to cases where NFc and NFp belong to the same operator, and also applies to cases where NFc and NFp belong to different operators; this application does not impose any specific limitations.

[0165] S220, NRF verifies whether NFC is authorized and generates an access token token#1 (e.g., access_token_nwdaf).

[0166] In a service-oriented system architecture, when NFc requests a service from NFp, NFp needs to perform an authorization check on the requested service. This check determines whether NFc is authorized to use the requested service. Only if the authorization check passes will NFp provide the corresponding service to NFc. For NFp's authorization verification of services requested by NFc, an access token-based authorization verification scheme can be used.

[0167] For example, in an OAuth-based authorization framework, the NRF verifies the authenticity and validity of the access token request message #1 to determine whether to accept the NFc's request. The OAuth authorization framework does not restrict the specific verification method used by the NRF. For instance, the NFc can obtain a digital certificate beforehand, issued by the NRF or other network elements, which describes the NFc's legitimate profile. The NRF uses the issuer's (NRF or other network element) public key to verify the authenticity of the digital certificate, thereby determining the authenticity of the content in the certificate. As another example, the NFc can also obtain an NFc profile signed by the NRF or other network elements beforehand. The NRF verifies the authenticity of the signature using the signer's public key to determine the authenticity of the NFc profile. Furthermore, the NFc and NRF can also use other pre-agreed credentials or methods (e.g., passwords, shared keys) to enable the NRF to verify the authenticity of the NFc profile; this application does not impose any limitations on this.

[0168] Additionally, if the NRF stores the Profile of the NFc, the NRF can check whether the input parameters in the access token request message #1 are consistent with the parameters in the stored NFc Profile of the NFc. Meanwhile, the NRF can also check whether the parameters (e.g., NF type of the NFc, NF type of the NFp) in the access token request message #1 are consistent with the authorized NF types stored or included in the certificate.

[0169] For example, the NRF can verify that the input parameters (e.g., NF type) in the access token request match the corresponding parameters in the NF service consumer's public key certificate or the corresponding parameters in the NF service consumer's NF profile, and check whether the NF service consumer is authorized to access the requested service.

[0170] It should be understood that if the verification is passed, i.e., the NFc is authorized, the NRF generates a token #1 containing claims. The claims include the NF instance ID of the authorizing network element, the NF instance ID of the NF service consumer, the NF type of the NF service provider, the expected service name, the expires_in, etc. Optionally, the claims can also include additional scope (allowing the requested resource and the requested operation on the resource), the list of S-NSSAI or the list of NSIID of the expected NF service provider instance, the NF SetID of the expected NF service provider instance, etc. For example, the access token includes the NF instance ID of the NRF, the NF instance ID of the NF service consumer, the NF type of the NF service producer, or the NF instance ID or multiple NF instance IDs of the requested NF service producer, the expected service name, the authorized scope, the expires_in, and the optional "additional scope" information.

[0171] Further, the NRF can perform security protection on the generated token #1, and the security protection can be integrity protection. For example, the NRF generates a message authentication code (MAC) for the token #1 using a shared key, and the NRF can send the MAC and the token #1 to the NFc, and the MAC is used to verify whether the information in the token #1 is tampered with; or the NRF signs the claims using a private key, and the NFp can verify whether the claims are tampered with through the signature. If the NFc is not authorized, the NRF shall not issue the token #1 to the NFc. It should be understood that integrity protection refers to ensuring that information is not tampered with or not modified by unauthorized parties during the generation, transmission, storage process, and thereafter through physical means or cryptographic methods.

[0172] Optionally, the claims can also include other parameters, such as allowed resources, network slice information, "additional scope" information (i.e., allowed resources and allowed resource operations (service operations)), a list of NSSAI or NSI IDs of the intended NFp instance, NF Set ID of the intended NFp instance, etc.

[0173] S230, the NRF sends an access token response message #1 to the NFc.

[0174] Correspondingly, the NFc receives the access token response message #1 from the NRF.

[0175] Optionally, the access token response message #1 can include the validity period of the token #1, which can be reused within the validity period.

[0176] Illustratively, if all the parameters in the access token request message #1 are verified and the NFc is authorized to access the requested service, the NRF sends the generated token #1 to the NFc through the access token response message #1 (e.g., Nnrf_AccessToken_Get Response). Optionally, the access token response message #1 can also include other parameters, such as the expiration time of the token #1, the scope allowed to use the token #1, etc. If the authorization verification in S202 fails, the NRF sends an error response or a rejection response to the NFc. The stored token can be reused within its validity period to access services from the NF producer of the requested NF type listed in the claim, or the NF instance ID or multiple NF instance IDs of the requested NF Service producer instance.

[0177] S240, the NF service consumer sends a service request message #1 to the NF service producer

[0178] It should be understood that the token #1 is included in the service request message #1.

[0179] Illustratively, the NFp verifies the integrity of the token by verifying the signature using the public key of the NRF or checking the MAC value using the shared key. If the integrity check is successful, the NF Service producer should verify the declared NF service producer in the token as follows:

[0180] Optionally, the NF service producer checks whether its own ID or the type of the NF service producer matches in the access token.

[0181] The NF service producer checks whether the access token is not expired according to the current data / time by verifying the expiration time in the access token.

[0182] Optionally, the access token includes a NSSAI list or NSI ID list, and the NF service producer checks whether it serves the corresponding slice.

[0183] Optionally, the access token includes a NF set ID, and the NF service producer checks whether the NF set ID in the claim matches its own NF set ID.

[0184] Optionally, the access token includes a scope, and the NF service producer checks whether the scope matches the requested service operation.

[0185] Optionally, the access token includes "additional scope" information (i.e. allowed resources and allowed operations (service operations) on the resources), and the NF service producer checks whether the additional scope matches the requested service operation.

[0186] S250, the NF service producer verifies the access token.

[0187] S260, the NF service producer sends a service response message #1

[0188] It should be understood that if the verification is successful, the NFp performs the requested service and returns the NFc.

[0189] It should be understood that if the above verification is not successful, the NF service producer replies to the NFc through an error response or a rejection response.

[0190] In the field of communication, machine learning (ML) models combined with NWDAF (Network Data Analytics Function) can predict services in different scenarios. AI / ML models are shared between NWDAF and / or NFs, such as NWDAF to NWDAF, ADRF to NWDAF, etc. In different scenarios, the NF producer of the AI / ML model can store the model in the ADRF, NWDAF or other entities. With the enhancement of ADRF functions, AI / ML models are stored to facilitate the distribution and sharing of these models between NFs.

[0191] However, since the AI / ML model and its algorithm are usually proprietary and protected by intellectual property rights, the act of requesting to obtain the AI / ML model by others needs to be authorized by the owner, which has considerable commercial value. Meanwhile, since the ADRF itself cannot be regarded as a fully trusted entity for storing sensitive AI / ML data models, when the 3GPP defines an authorization scheme for the service-based architecture (SBA) shown in method 200 to apply to the AI / ML model sharing scenario, this way of authorization only through the NRF and with the authorization granularity at the service level or resource / operation level range cannot guarantee the security of model authorization and sharing. The reason is that the ADRF or NWDAF (or any other network function that may store AI / ML models) cannot verify whether the NF consumer is authorized by the owner of the AI / ML model and its algorithm to retrieve and obtain the AI / ML model.

[0192] Therefore, it is necessary to ensure that only the NF that generates the AI / ML model, and the NF that obtains the AI / ML model access authorization from the NF that produces the AI / ML model, can read and use these models. Based on this, the embodiments of the present application provide a model authorization and sharing method for NF to obtain AI / ML model, to protect the commercial value of the AI / ML model and its algorithm.

[0193] Figure 3 is a flow diagram of a model sharing method 300 provided by the embodiments of the present application, that is, a NFc requests to obtain a model trained by a NFp from a data analysis storage function network element ADRF.

[0194] S301, the NF service consumer NFc (for example, NWDAF AnLF) registers in the NRF using the analytic ID and the vendor ID.

[0195] It should be understood that the analytic ID is the type of ML model that the NFc expects to access.

[0196] It should be understood that the vendor ID is used to represent the vendor of the NF, which can be the ID of the vendor or the internal implementation of the vendor. Specifically, the NWDAF containing the AnLF registers its NF profile in the NRF, which is supported by the NWDAF containing the AnLF and its vendor ID.

[0197] S302, the NF service producer NFp (for example, NWDAF MTLF) trains the ML model.

[0198] Optionally, the NWDAF containing the MTLF encrypts the ML model according to the implementation of its vendor.

[0199] S303, NFp selects and stores the ADRF ID for storing the ML model.

[0200] Wherein, the NFp determines that the ML model can be stored in ADRF, and discovers and selects the ADRF through NRF, and stores the selected ADRF instance ID of the model.

[0201] S304, NFp triggers the ADRF storage service to the ADRF.

[0202] Wherein, the message includes the model association ID and the model address (URL1) in MTLF.

[0203] S305, ADRF obtains the ML model from NFp

[0204] Specifically, the ADRF securely obtains the model from the NFp through URL1.

[0205] It should be understood that the NFp verifies that the ADRF is the selected ADRF instance in step S303, and checks whether the model association ID is correct. It is assumed that the vendor ID of the ADRF does not need to be verified.

[0206] S306, ADRF sends the location (URL2) of the ML model to NFp.

[0207] S307, NFc performs discovery and selection procedure on NFp through NRF.

[0208] S308, NFc requests NFp to obtain the model.

[0209] Wherein, the NWDAF containing AnLF performs Nnwdaf_MLModelProvision service operation on the NWDAF containing MTLF, and the message contains analysis ID and vendor ID to retrieve the ML model of the analysis ID.

[0210] It should be understood that the analysis ID corresponds to the analysis ID corresponding to the model that the NFc expects to obtain, and the vendor ID is the vendor ID of the NFc.

[0211] S309, NFp retrieves the NF profile of NFc from NRF

[0212] Specifically, the NWDAF containing MTLF retrieves the NF profile of the NWDAF containing AnLF from NRF, and obtains the NWDAF containing AnLF from the NF profile. The vendor ID of AnLF.

[0213] Optionally, if the determined ML model is stored in the ADRF, the NWDAF containing the MTLF triggers the ADRF storage update service to the ADRF, the message containing the model association ID and the list of allowed NF instances. The ADRF stores the list of allowed NF instances for the ML model referenced by the model association ID.

[0214] S310, NFp verifies NFc and saves the NFc ID

[0215] Specifically, the NWDAF containing the MTLF verifies whether the vendor ID of the NWDAF containing the AnLF in the request message is the same as the vendor ID in its NF profile, and is contained in its interoperability identification.

[0216] It should be understood that if the verification is successful, the NWDAF containing the MTLF will determine the ML model to be shared for the requested analysis ID, and store the NF instance ID of the NWDAF containing the AnLF as part of the list of allowed NF instances for the ML model.

[0217] S311, optionally, NFp updates the ML model to the ADRF

[0218] Specifically, if the authorized ML model is stored in the ADRF, the NWDAF containing the MTLF triggers the ADRF storage update service to the ADRF, the message containing the model association ID and the list of allowed NF instances. The ADRF stores the list of allowed NF instances for the ML model referenced by the model association ID.

[0219] S312, the ADRF sends a response message to the NFp.

[0220] S313, the NFp sends a request model notification message to the NFc.

[0221] Specifically, the NWDAF containing the MTLF sends a request response message (Nnwdaf_MLModelProvision notification) to the NWDAF containing the AnLF, the request response message including the address of the determined ML model, which can be the address stored in the NWDAF containing the MTLF, or the address in the ADRF. S314, the NFc obtains the ML model from the address

[0222] Specifically, the NWDAF containing the AnLF obtains the target ML model by the URL received from S313.

[0223] Exemplarily, when the ML model is stored in the NWDAF containing the MTLF, the NWDAF containing the MTLF verifies that the NWDAF containing the AnLF is the NF consumer instance stored in S310.

[0224] Exemplarily, when the ML model is stored in the ADRF, the ADRF verifies whether the NWDAF containing the AnLF is part of the allowed NF instance list received by the S311.

[0225] It should be understood that if the verification is successful, the NWDAF containing the AnLF is entitled to obtain the ML model.

[0226] S315, the NFc decrypts the ML model.

[0227] Wherein, the NWDAF containing the AnLF decrypts the received ML model according to the implementation of the supplier, and the decryption manner of the ML model is not within the scope of 3GPP.

[0228] Figure 4 is another flowchart of a model sharing method 400 provided by the embodiment of the application. As shown in the figure, the method comprises the following steps, and the parts not described in detail can refer to the existing protocol. Figure 4

[0229] S401, the NF service producer NFp (for example, NWDAF MTLF) registers using the interoperability identifier.

[0230] It should be understood that the interoperability identifier is a list of supplier IDs of the NWDAF allowed to obtain the ML model from the NFp.

[0231] S402, the NF service consumer NFc (for example, NWDAF AnLF) registers using the supplier ID.

[0232] S403, optionally, the NFp performs operations specific to the interoperability identifier.

[0233] Exemplarily, the NFp performs operations such as encryption and integrity protection for the security of the ML model, and the encryption manner of the ML model is not within the scope of 3GPP.

[0234] S404, the NFp triggers storage of the ML model.

[0235] Exemplarily, the NFp sends a request message to the ADRF for requesting storage of the ML model. Wherein, the request message comprises a storage address of the ML model in the NFp, for example, URL1. The request message also comprises a model association identifier (for example, model correction ID). Correspondingly, the ADRF obtains the protected ML model according to the address URL1 of the ML model in the NFp, and stores the ML model.

[0236] S405, the ADRF obtains the ML model.

[0237] ​The ADRF securely acquires the protected model, and the specific acquisition method and its security are beyond the scope.

[0238] S406. The ADRF sends the storage location of the ML model to the NFp.

[0239] For example, the storage location of the ML model in the ADRF is URL2, which is used for subsequent updating or accessing the ML model by the NFp.

[0240] S407. The MTLF discovery procedure is performed between the NFc and the NRF.

[0241] S408. The NFc sends an access token request message to the NRF.

[0242] Correspondingly, the NRF receives the access token request message from the NFc.

[0243] The access token request message includes an analysis ID.

[0244] For example, the access token request message can be an Nnrf_AccessToken_Get Request message.

[0245] S409. The NRF sends an access token response message to the NFc.

[0246] Correspondingly, the NFc receives the access token response message from the NRF.

[0247] The access token response message includes a token, which includes a vendor ID to which the NFc belongs.

[0248] For example, the access token response message can be an Nnrf_AccessToken_Get Response message.

[0249] Specifically, before performing step S409, the NRF needs to check whether the vendor ID of the NFc stored in the configuration file of the NFc in the NRF is one of the vendor IDs in the interoperation identification in the NFp configuration file.

[0250] S410. The NFc sends a model request message to the NFp.

[0251] Correspondingly, the NFp receives the model request message from the NFc.

[0252] The model request message includes an analysis ID and a token, which carries a specified vendor ID.

[0253] S411. The NFp verifies the token and performs authorization.

[0254] For example, the NFp needs to verify whether the specified vendor ID carried in the token corresponds to the analytics ID carried in the model request message. It should be understood that the NFp can perform further authorization using the specified vendor ID in the token if the token is verified to be valid.

[0255] It should be understood that if the ML model requested by the NFc is stored in the ADRF, steps S411 to S413 are continued to be performed.

[0256] S412, the NFp sends a message requesting a URL to the ADRF;

[0257] Correspondingly, the ADRF receives the message requesting a URL from the NFp.

[0258] The message requesting a URL includes a model correlation identifier (e.g., model correction ID) or URL2.

[0259] For example, after receiving the URL request from the NFp, the ADRF checks whether the owner of the ML model stored therein is the NFp. If the check is successful, the ADRF provides a new storage address, e.g., URL3, for the stored ML model, and step S413 is continued to be performed. The URL3 can be a one-time use URL.

[0260] S413, the ADRF sends the URL3 to the NFp;

[0261] Correspondingly, the NFp receives the URL3 from the ADRF.

[0262] S414, the NFp sends the URL3 to the NFc;

[0263] Correspondingly, the NFc receives the URL3 from the NFp.

[0264] It should be understood that if the ML model requested by the NFc is stored in the NFp, after step 410, the NFp provides a new storage address, e.g., URL4, for the stored ML model, and returns the URL4 to the NFc, i.e., steps S412 to S414 do not need to be performed. The URL4 can be a one-time use URL. Therefore, the NFc can obtain the protected ML model from the NFp or the ADRF according to the URL4 or the URL3.

[0265] S415, optionally, the NFc performs operations specific to the interoperability identifier.

[0266] For example, the NFc can perform operations such as decryption and integrity check, etc. considering the interoperability identifier on the protected ML model.

[0267] In order to facilitate the understanding of the embodiments of the present application, the following points are explained:

[0268] First, in the present application, the terms and / or descriptions between different embodiments are consistent and can be referred to each other without special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0269] Second, in the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship between the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can represent the following cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In the literal description of the present application, the character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single item or multiple items. For example, at least one of a, b and c can represent: a, or b, or c, or a and b, or a and c, or b and c, or a, b and c. Where a, b and c can be single or multiple.

[0270] Third, in the present application, "first", "second" and various number designations (for example, #1, #2, etc.) indicate the differentiation for the convenience of description, and are not used to limit the scope of the embodiments of the present application. For example, to distinguish different messages, etc., rather than to describe a specific order or sequence. It should be understood that the objects thus described can be interchanged under appropriate circumstances, so as to be able to describe schemes other than the embodiments of the present application.

[0271] It should be noted that in the following, the meanings represented by information #1 and resource indication information #1 and resource request information #1 are different from each other. It should be understood that the names of each information are only illustrative, and the present application does not limit this, and should not constitute any limitation on the technical solutions of the present application;

[0272] Fourth, in the present application, "when", "in the case of" and "if" and other descriptions all mean that the device will make corresponding processing under certain objective circumstances, not limited to time, and also does not require the device to have a judgment action when implemented, nor does it mean that there are other limitations.

[0273] Fifthly, in the present application, the terms "comprising" and "having" and any variations thereof are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device that includes a list of steps or units need not be limited to those steps or units that are clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0274] Sixthly, in the present application, "for indicating" can include "for directly indicating" and "for indirectly indicating". When describing that certain indication information is used to indicate A, it can include that the indication information directly indicates A or indirectly indicates A, and it does not mean that A must be carried in the indication information.

[0275] The indication mode involved in the embodiments of the present application should be understood as covering various methods that can enable the to-be-indicated party to know the to-be-indicated information. The to-be-indicated information can be sent as a whole, or can be sent separately in multiple sub-information, and the sending period and / or sending occasion of these sub-information can be the same or different, and the present application does not limit the specific sending method.

[0276] The "indication information" in the embodiments of the present application can be explicit indication, that is, directly indicated through signaling, or obtained according to the parameters indicated by the signaling, combined with other rules or combined with other parameters or through derivation. It can also be implicit indication, that is, obtained according to rules or relationships, or according to other parameters, or through derivation. The present application does not make specific limitations.

[0277] Seventhly, in the present application, "protocol" can refer to a standard protocol in the communication field, which can include 5G protocol, NR protocol and related protocols applied in future communication systems, and the present application does not limit this. "Predefined" can include predefinition. For example, protocol definition. "Preconfigured" can be implemented by pre-storing corresponding codes, tables or other ways that can be used to indicate related information in the device, and the present application does not limit the specific implementation manner.

[0278] Eighthly, in the present application, "storage" can refer to saving in one or more memories. The one or more memories can be separately arranged, or integrated in the encoder or decoder, processor or communication device. The one or more memories can be partially separately arranged and partially integrated in the decoder, processor or communication device. The type of memory can be any form of storage medium, and the present application does not limit this.

[0279] Ninthly, in the present application, "communication" can also be described as "data transmission", "information transmission", "data processing" and the like. "Transmission" includes "sending" and "receiving".

[0280] The communication method provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings. The communication method provided by the embodiments of the present application can be applied to the communication system shown in the above Figure 1

[0281] Figure 5 FIG. 5 is a flow diagram of a communication method 500 provided by the embodiments of the present application.

[0282] S501, each network element initially registers connection establishment.

[0283] For example, in step S501, the NWDAF containing the MTLF registers its NFp profile in the NRF, and the profile contains the interoperability identifier supported by the NWDAF containing the MTLF; the NWDAF containing the AnLF registers its NFc profile in the NRF, and the profile contains the vendor ID of the NWDAF containing the AnLF.

[0284] S502, the NFp and the ADRF complete model storage.

[0285] For example, the NFp (such as the NWDAF_MTLF) needs to send a model storage request to the ADRF, including MTLF model identifier information (ML Model Identifier), used to identify the model.

[0286] After the ADRF determines the model requested by the NFp, the NFp and the ADRF complete the model transmission process, and then the ADRF sends a model storage response message including the address of the model storage to the NFp, where the storage address of the model is a URL or a Fully Qualified Domain Name (FQDN).

[0287] Optionally, the NFp also stores model-related information in the ADRF, such as Analytics ID, application ID of the model, interoperability identifier, and other information.

[0288] S503, the NFp updates the NF profile to the NRF and registers the model-related information.

[0289] For example, the NFp and the ADRF register the saved model to the NRF. For example, the NFp and the ADRF register the corresponding manufacturer NFp ID, interoperability identifier of the NFp (Interoperability indicator), and Analytics ID (indicating that the model of the application is saved) of the saved model.

[0290] S504, the NFc discovers and selects the NF for requesting the model through the NRF.

[0291] ​Exemplarily, the NFc (e.g., the NWDAF comprising the AnLF) performs a NF discovery request operation using the requested analytics ID to select a suitable NFp (e.g., the NWDAF comprising the MTLF, the ADRF).

[0292] S505, the NFc sends an access token request message #1 to the NRF.

[0293] Correspondingly, the NRF receives the access token request message #1 from the NFc.

[0294] The access token request message #1 is used to request to obtain an access token.

[0295] Exemplarily, the access token request message #1 comprises the NF type of the target NF (e.g., the NFp (the NWDAF comprising the MTLF, the ADRF), the NFc (e.g., the NWDAF comprising the AnLF)) and / or the NFc ID.

[0296] Optionally, the access token request message #1 comprises the analytics ID that the NFc expects to access.

[0297] Optionally, the access token request message #1 comprises indication information #1, which is used to indicate the vendor information of the NFp corresponding to the model that the NFc expects to obtain, or the vendor information of the NWDAF supporting the interoperable ML model of the NFc (e.g., the interoperability indicator of the NFc). Exemplarily, the vendor information can be a vendor ID. It should be understood that the vendor information of the model that the NFc expects to obtain is equivalent to the vendor information of the corresponding model production network element NWDAF of the model that the NFc expects to obtain. It should be noted that the NFc expects to obtain the model produced by the vendor indicated by the above vendor information.

[0298] It should be understood that the name of the indication information #1 is not limited in the embodiments of the present application, as long as the above-mentioned function can be realized.

[0299] Optionally, the access token request message #1 comprises the interoperability indicator of the NFc.

[0300] Optionally, the access token request message #1 comprises the vendor ID of the NFc.

[0301] Optionally, the access token request message #1 comprises model filtering information (ML Model Filter information), which exemplarily comprises: S-NSSAI (s) slice information and Area (s) of Interest interested area, etc.

[0302] Exemplarily, the access token request message #1 can be an Nnrf_AccessToken_Get Request message.

[0303] S506, the NRF sends an access token response message #1 to the NFc.

[0304] Correspondingly, the NFc receives the access token response message #1 from the NRF.

[0305] The access token response message #1 includes a token #1.

[0306] Exemplarily, the access token response message #1 can be an Nnrf_AccessToken_Get Response message.

[0307] Optionally, the token #1 includes an analytics identity that the NFc is authorized to access, which can be the same as or different from the analytics identity that the NFc desires to access, and the embodiments of the present application do not limit this.

[0308] Optionally, the token #1 includes an interoperability identity of the model that the NFc is authorized to access, which can be the same as or different from the indication information #1, and the embodiments of the present application do not limit this.

[0309] Optionally, the token #1 includes the vendor information of the model that the NFc is authorized to access, which can be the same as or different from the indication information #1, and the embodiments of the present application do not limit this.

[0310] Optionally, the token #1 includes the vendor ID of the NFc.

[0311] Optionally, the token #1 includes the NF type and / or the NF instance ID of the model that the NFc is authorized to access.

[0312] It should be understood that the NRF generates the token #1 based on the NF profile information of the NWADF containing the MTLF only when the verification is passed, and then step S506 is performed.

[0313] Exemplarily, before step S506 is performed, the NRF needs to verify whether the vendor ID of the NWDAF containing the AnLF is included in the interoperability identity of the NWDAF of the MTLF.

[0314] Exemplarily, before performing step S506, the NRF needs to verify that the supplier ID of the MTLF is included in the indication information #1 of the NWDAF containing the AnLF.

[0315] S507, the NFc sends a model authorization token request message #1 to the NFp.

[0316] Correspondingly, the NFp receives the model authorization token request message #1 from the NFc.

[0317] The model authorization token request message #1 is used to request an authorization token for a target model, and exemplarily, the second request message carries an analysis ID expected to be accessed and a token #1.

[0318] Optionally, the model authorization token request message #1 includes an ADRF ID where the target model is located. It should be understood that the NFc can determine the ADRF ID of the target MTLF through S504 before requesting the target MTLF.

[0319] Optionally, the model authorization token request message #1 includes the indication information #1.

[0320] Method one

[0321] S508, the NFp verifies and authorizes the model.

[0322] It should be understood that the NFp needs to check the token #1 before deciding whether to authorize the model.

[0323] Exemplarily, the NFp verifies whether the analysis ID requested in the model authorization token response message #1 is within the analysis ID authorized by the token #1.

[0324] Optionally, if the indication information #1 of the NFc is included in the token #1, the NFp judges whether its own supplier ID is within the indication information #1 of the NFc.

[0325] Optionally, if the supplier ID of the NFc is included in the token #1, the NFp judges whether the NFc is within its own interoperability identifier according to the supplier ID.

[0326] It should be understood that if the NFp chooses to return the third-party address (URL or FQDN) of the model to the NFc after the token #1 verification is passed, the NFp directly returns the model address to the NFc and no longer performs subsequent steps.

[0327] It should be understood that the NFp generates the model authorization token #1 only if the verification is passed. Exemplarily, the model authorization token can be a client credentials assertion (CCA), and the embodiments of the present application are not limited thereto as long as the corresponding functions can be implemented.

[0328] In a possible implementation, the model authorization token #1 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #1, and the analytics ID of the model authorized to be acquired by the NFc.

[0329] In another possible implementation, the model authorization token #1 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #1, and the model indication information of the model authorized to be acquired by the NFc. Exemplarily but not limitatively, the model indication information includes one or more of a model identifier (ML Model Identifier) or an address (Address of Model file) of the model or a hash value (Hash of Address of Model file) of the address of the model, where the address of the model can be a URL or a FQDN, and correspondingly, the hash value of the address of the model can be a hash value of the URL or the FQDN.

[0330] In yet another possible implementation, the model authorization token #1 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #1, the analytics ID of the model authorized to be acquired by the NFc, and the ADRF ID where the ML model is located.

[0331] In yet another possible implementation, the model authorization token #1 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #1, the analytics ID of the model authorized to be acquired by the NFc, and the model indication information of the ML model.

[0332] In yet another possible implementation, the model authorization token #1 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #1, the model indication information of the model authorized to be acquired by the NFc, and the ADRF ID where the ML model is located.

[0333] In yet another possible implementation, the model authorization token #1 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #1, the analytics ID of the model authorized to be acquired by the NFc, the model indication information of the ML model, and the ADRF ID where the model is located.

[0334] In yet another possible implementation, the NFp-generated model authorization token #1 includes the NFp ID, the NFc ID, the expiration time of the CCA #1, and the model indication information of the model authorized for the NFc to obtain. Optionally, when the NFc includes the ADRF type or the ADRF ID in the model authorization request information #1, the NFp can add the ADRF ID IE in the authorization token, indicating that the model authorization is only applicable to the model corresponding to the analysis ID in the ADRF ID.

[0335] S509, the NFp sends the model authorization token response message #1 to the NFc.

[0336] Correspondingly, the NFc receives the model authorization token response message #1 from the NFp.

[0337] The model authorization token response message #1 includes the model authorization token #1.

[0338] Method two

[0339] S510, the NFp decides whether to authorize the model.

[0340] It should be understood that the NFp needs to verify the token #1 before deciding whether to authorize the model. Only when the verification of the token #1 is passed, the NFp sends the model authorization token request message #2 to the NRF to request the NRF to generate a model authorization token #2 according to the information.

[0341] Exemplarily, the NFp verifies whether the analysis ID requested in the model authorization token response message #1 is within the analysis ID authorized by the token #1.

[0342] Optionally, if the token #1 includes the indication information #1 of the NFc, the NFp judges whether its own vendor ID is within the indication information #1 authorized for the NFc.

[0343] Optionally, if the token #1 contains the vendor ID of the NFc, the NFp judges whether the NFc is within its own interoperability identification according to the vendor ID.

[0344] It should be understood that after the verification is passed, if the NFp chooses to return the third-party address (URL or FQDN) of the model to the NFc, the NFp directly returns the model address to the NFc and no longer performs the subsequent steps.

[0345] S511, the NFp sends the model authorization token request message #2 to the NRF.

[0346] Correspondingly, the NRF receives the model authorization token request message #2 from the NFp.

[0347] It should be understood that the NRF generates the token#2 accordingly based on the content of the Model Authorization Token Request message #2.

[0348] In one possible implementation, the Model Authorization Token Request message #2 includes the NFp ID, the NFc ID, the expiration time of the token#2, and the analytics ID of the model that the NFc is authorized to obtain.

[0349] In another possible implementation, the Model Authorization Token Request message #2 includes the NFp ID, the NFc ID, the expiration time of the token#2, and the model indication information of the model that the NFc is authorized to obtain. As an example but not limitation, the model indication information includes one or more of a model identifier (ML Model Identifier) or an address of the model (Address of Model file) or a hash of the address of the model file (Hash of Address of Model file), where the address of the model can be a URL or a FQDN, and correspondingly, the hash of the address of the model can be a hash of the URL or the FQDN.

[0350] In yet another possible implementation, the Model Authorization Token Request message #2 includes the NFp ID, the NFc ID, the expiration time of the token#2, and the analytics ID of the model that the NFc is authorized to obtain and the ADRF ID where the ML model is located.

[0351] In yet another possible implementation, the Model Authorization Token Request message #2 includes the NFp ID, the NFc ID, the expiration time of the token#2, and the ML analytics ID of the model that the NFc is authorized to obtain and the model indication information of the ML model.

[0352] In yet another possible implementation, the Model Authorization Token Request message #2 includes the NFp ID, the NFc ID, the expiration time of the token#2, and the model indication information of the model that the NFc is authorized to obtain and the ADRF ID where the ML model is located.

[0353] In yet another possible implementation, the Model Authorization Token Request message #2 includes the NFp ID, the NFc ID, the expiration time of the token#2, and the analytics ID of the model that the NFc is authorized to obtain, the model indication information of the ML model, and the ADRF ID where the ML model is located.

[0354] It should be understood that the NRF ID is also included in the token#2 generated by the NRF.

[0355] It should be understood that if the NFp chooses to return the third party address (URL or FQDN) of the model to the NFc, the NFp directly returns the model address to the NFc and no subsequent steps are performed.

[0356] S512, the NRF sends a model authorization token response message #2 to the NFp;

[0357] Correspondingly, the NFp receives the model authorization token response message #2 from the NRF.

[0358] The model authorization token response message #1 includes token #2.

[0359] It should be understood that the NRF correspondingly generates token #2 according to the content of the model authorization token request message #2 in S508.

[0360] S513, the NFp sends a model authorization token response message #2 to the NFc;

[0361] Correspondingly, the NFc receives the model authorization token response message #2 from the NFp.

[0362] The model authorization token response message #2 includes token #2.

[0363] S514, the NFp sends a model authorization token response message #1 to the NFc;

[0364] Correspondingly, the NFc receives the model authorization token response message #1 from the NFp.

[0365] The model authorization token response message #1 includes token #2.

[0366] The NFc obtains the authorization token of the target model, model authorization token #1 or token #2, through the model authorization token response message #1 by the above-mentioned method one or method two, and the subsequent steps are described below taking token #2 as an example.

[0367] S515, optionally, the NFc sends an access authorization token request message #2 to the NRF.

[0368] Correspondingly, the NFc receives the access authorization token request message #2 from the NRF.

[0369] The access authorization token request message #2 is used to request access to the ADRF where the target model is located.

[0370] It should be understood that the NFc can determine the ADRF where the target model is located through the NRF or through the NFp.

[0371] S516, optionally, the NRF sends an access authorization token response message #2 to the NFc.

[0372] Correspondingly, the NRF receives the access authorization token response message #2 from the NFc.

[0373] The access authorization token response message #2 includes token #3.

[0374] The specific implementation of the above steps S515 and S516 can refer to steps S408 and S409 of the above method 400. For example, before performing step S516, the NRF needs to check whether the NWDAF containing the AnLF is authorized to access the ADRF. Only in the case of verification, the NRF generates token #3, and then performs step S516, which is not described in detail here.

[0375] S517, the NFc sends a model obtaining request message #1 to the ADRF.

[0376] Correspondingly, the ADRF receives the model obtaining request message #1 from the NFc.

[0377] The model obtaining request message #1 includes analysis ID and token #2.

[0378] Optionally, the model obtaining request message #1 further includes indication information #2, which is used to indicate the vendor information of the model expected to be obtained by the NFc.

[0379] Optionally, the model obtaining request message #1 further includes the NFc ID.

[0380] Optionally, the model obtaining request message #1 further includes a random number generated by the NFc, so that the ADRF can generate a ticket based on the random number in the subsequent step, thereby binding the NFc ID and the model address information #1, and ensuring that only a specific NFc can obtain the model based on the model address information #1.

[0381] S518, the ADRF determines whether to authorize the NFc to obtain the model

[0382] It should be understood that the ADRF needs to check the parameter information contained in the model obtaining request #1 and the information type in the token #2 before deciding whether to authorize the NFc to obtain the model, and further, the ADRF checks whether the above two kinds of information are consistent, or whether the parameter information is within the authorization range of the authorization information indicated by the token #2.

[0383] For example, the ADRF verifies whether the token #2 is within the valid period according to the expiration time of the token #2, and the ADRF verifies whether the NFc ID sending the model obtaining request message #1 is consistent with the NFc ID in the token #2.

[0384] Optionally, when token#2 contains ADRFID, ADRF verifies that the ADRFID in token#2 matches its own NF ID.

[0385] Optionally, when token#2 contains NFp ID and ML model indication information, ADRF verifies the relationship between the NFp ID and the ML model indication information indicating the model, and determines that the NFp does indeed have the authorization permissions for the model.

[0386] It should be understood that after the verification is successful using the example above, ADRF returns model address information #1 (e.g., address of model file2) to NFC based on token #2 and local configuration information, so that NFC can obtain the model.

[0387] In one possible implementation, ADRF can use a ticket as a model retrieval credential, binding the NFc ID and model address information #1 to ensure that only a specific NFc can retrieve the model based on model address information #1.

[0388] Furthermore, ADRF notifies the third-party storage address of the ticket content.

[0389] As an example and not a limitation, the content of the ticket can be [token#2, message authentication code (MAC) of token#2, random number provided by NFC, random number generated by ADRF].

[0390] Optionally, the note may also include the note’s expiry date.

[0391] S519, ADRF sends Model Acquisition Response Message #1 to NFC.

[0392] Correspondingly, NFc receives model acquisition response message #1 from ADRF.

[0393] The model acquisition response message #1 includes the address where the target model is stored.

[0394] Optionally, the model retrieves response message #1, which also includes the ticket from S519.

[0395] Optionally, the ticket is included in the model address information #1.

[0396] S520, NFC and ADRF are used for model transfer.

[0397] NFc obtains the target model based on model address information #1.

[0398] Figure 6 is a flowchart of another communication method 600 provided by an embodiment of the application.

[0399] S601, each network element initially registers connection establishment.

[0400] For example, in step S601, the NWDAF containing the MTLF registers its NFp profile in the NRF, which contains the interoperability identifier supported by the NWDAF containing the MTLF.

[0401] S602, the NFp and the ADRF complete model storage.

[0402] Among them, the NFp (such as: NWDAF_MTLF) needs to send a model storage request to the ADRF first, including MTLF model identifier (ML Model Identifier), used to identify the model.

[0403] After the ADRF determines the model requested by the NFp, the NFp and the ADRF complete the model transmission process, and then the ADRF sends a model storage response message including the address of the model storage to the NFp, wherein the storage address of the model is URL or FQDN.

[0404] Optionally, the NFp also stores model related information in the ADRF, such as: Analytics ID, model application ID, interoperability identifier, and other information.

[0405] S603, the NFp updates the NF profile to the NRF, and registers the related information of the model.

[0406] For example, the NFp and the ADRF register the saved model to the NRF. For example, the NFp and the ADRF register the corresponding manufacturer NFp ID of the saved model, the interoperability identifier of the NFp, and the Analytics ID, wherein the Analytics ID indicates that the model of the application indicated by the Analytics ID is saved.

[0407] S604, the NFc discovers and selects the NF for requesting the model through the NRF.

[0408] For example, the NFc (such as: the NWDAF containing the AnLF) performs NF discovery request operation using the requested Analytics ID to select a suitable NFp (such as: the NWDAF containing the MTLF, the ADRF).

[0409] S605, the NFc sends an access token request message #1 to the NRF.

[0410] Correspondingly, the NRF receives the access token request message #1 from the NFc.

[0411] The access token request message #1 is used to request an access token. The access token request message #1 includes, for example, a target NF ID (such as a NWDAF ID containing MTLF, an ADRF ID) and / or an NF type (for example, NFp (NWDAF containing MTLF, ADRF), an analytics ID that the NFc expects to access.

[0412] Optionally, the access token request message #1 includes an NFc ID.

[0413] Optionally, the access token request message #1 includes indication information #1 indicating a vendor of an NFp corresponding to a model that the NFc expects to obtain, or vendor information (for example, an interoperability identifier of the NFc) of a NWDAF supporting an interoperable ML model of the NFc. For example, the vendor information can be a vendor ID. It should be understood that the vendor information of the model that the NFc expects to obtain is equivalent to the vendor information of the corresponding model production network element NWDAF of the model that the NFc expects to obtain. It should be noted that the NFc expects to obtain the model produced by the vendor indicated by the above vendor information.

[0414] It should be understood that the name of the indication information #1 is not limited in the embodiments of the present application, as long as the above-mentioned functions can be realized.

[0415] Optionally, the access token request message #1 includes a vendor ID of the NFc.

[0416] Optionally, the access token request message #1 includes an interoperability ID of the NFc, wherein the interoperability ID of the NFc is pre-assigned by the vendor of the NFc. The interoperability ID is consistent with the identification information of the vendor indicated in the interoperability identifier of the NFp produced by the vendor. For example, the interoperability ID of the NFc #1 produced by the vendor #1 is ID #1, the interoperability identifier of the NFp #1 produced by the vendor #1 is ID #1 and ID #2, the interoperability identifier of the NFp #2 produced by the vendor #2 is ID #2, and then the NFc #1 can only obtain the model produced by the NFp #1, but cannot obtain the model produced by the NFp #2.

[0417] Optionally, the access token request message #1 includes model filtering information (ML Model Filter information), which includes, for example, S-NSSAI (s) slice information and Area (s) of Interest region of interest.

[0418] For example, the access token request message #1 can be an Nnrf_AccessToken_Get Request message.

[0419] S606, the NRF sends a model authorization request message #1 to the NFp.

[0420] Correspondingly, the NFp receives the model authorization request message #1 from the NRF.

[0421] It should be understood that before the NRF performs step S606, the NRF needs to determine whether the parameters of the access token request message #1 are consistent with the information stored in the NF profile and the public key certificate stored by the NRF.

[0422] Further, the NRF needs to determine whether the analytics ID that the NFc expects to access is consistent with the NFp profile stored in the local configuration to determine the target NFp that the NRF sends the model authorization request message #1 to.

[0423] Specifically, the NRF determines one or more NFps corresponding to the analytics ID that the NFc expects to access according to the analytics ID supported by each NFp in the NFp profile.

[0424] Optionally, the NRF determines the vendor ID of the NFc and the interoperability identifier of the NFp in the NFp profile, and further determines the NFp that the NFc can access from the plurality of NFps determined according to the analytics ID by determining whether the vendor ID of the NWDAF containing the AnLF is in the interoperability identifier of the NWDAF containing the MTLF.

[0425] Optionally, the NRF determines the interoperability ID of the NFc and the interoperability identifier of the NFp in the NFp profile, and further determines the NFp that the NFc can access from the plurality of NFps determined according to the analytics ID by determining whether the interoperability ID of the NWDAF containing the AnLF is in the interoperability identifier of the NWDAF containing the MTLF.

[0426] Optionally, the NRF determines one or more NFps corresponding to the analytics ID that the NFc expects to access according to the analytics ID supported by each ADRF in the ADRF profile.

[0427] Optionally, the NRF determines the indication information #1 of the NFc and the vendor ID of the NFp in the NFp profile, and further determines the NFp that the NFc can access from the plurality of NFps determined according to the analytics ID by determining whether the indication information #1 of the NWDAF containing the AnLF contains the vendor ID of the NWDAF containing the MTLF.

[0428] As an example but not limitation, the NRF determines the NFs contained in the indication information #1 according to the vendor information indicated in the indication information #1 and the vendor ID of the NFp in the NF profile saved in the local configuration. For example, the indication information #1 contains vendor #1, vendor #2, vendor #3, the NF profile of the NFp saved in the NRF includes NFp #1 with vendor #1 and NFp #2 with vendor #2, and the NRF selects NFp #1 and NFp #2 as the candidate NFp.

[0429] As an example but not limitation, the NRF determines NFp #1, NFp #2 and NFp #3 corresponding to the analysis ID #1 in the NFp profile saved in the local configuration according to the analysis ID #1, and further selects NFp #1 from NFp #1, NFp #2 and NFp #3 according to the vendor ID and the interoperability identifier of the NFc #1, in combination with the interoperability identifier and the vendor ID of NFp #1, NFp #2 and NFp #3, which can provide the model corresponding to the analysis ID #1 for the NFc #1.

[0430] It should be understood that the NRF will send the model authorization request message #1 to the selected NFp only if the verification is passed, and the model authorization request message #1 includes the analysis ID.

[0431] Optionally, the model authorization request message #1 includes the NFc ID and / or the vendor ID of the NFc.

[0432] Optionally, the model authorization request message #1 includes the interoperability ID of the NFc. The interoperability ID is consistent with the identification information of the vendor indicated in the interoperability identifier of the NFp produced by the vendor. For example, the interoperability ID of the NFc #1 produced by the vendor #1 is ID #1, the interoperability identifier of the NFp #1 produced by the vendor #1 is ID #1 and ID #2, the interoperability identifier of the NFp #2 produced by the vendor #2 is ID #2, and then the NFc #1 can only obtain the model produced by the NFp #1, but cannot obtain the model produced by the NFp #2.

[0433] Optionally, the model authorization request message #1 includes the indication information #1.

[0434] Optionally, the model authorization request message #1 further includes the ADRF ID. It should be understood that the ADRF ID included in the model authorization request message #1 can be the same as or different from the ADRF ID included in the access token request message #1.

[0435] Optionally, the model authorization request message #1 further includes the model filtering information included in the access token request message #1.

[0436] Case 1

[0437] In the case 1, the NRF sends a model authorization request message #1 to the NFp to request the NFp to agree to authorize the NFc to acquire the model.

[0438] S607, the NFp decides to authorize the model.

[0439] It should be understood that the NFp needs to determine whether to agree to authorize the NFc to acquire the model according to the NFc information carried in the model authorization request message #1 by the NRF, in combination with a local policy.

[0440] Exemplarily, the NFp verifies that the analytics ID included in the model authorization request message #1 belongs to the service capability range of the NFp.

[0441] Exemplarily, the NFp verifies that the vendor ID of the NFc included in the model authorization request message #1 is within the interoperability identification of the NFp.

[0442] Exemplarily, the NFp verifies that the interoperability ID of the NFc included in the model authorization request message #1 is within the interoperability identification of the NFp.

[0443] S608, the NFp sends a model authorization response message #1 to the NRF.

[0444] Correspondingly, the NRF receives the model authorization response message #1 from the NFp.

[0445] In a possible implementation, the model authorization response message #1 includes an identifier indicating that the NRF agrees to authorize the NFc to acquire the target model.

[0446] In another possible implementation, the model authorization response message #1 includes the analytics ID that the NFc is authorized to acquire, exemplarily, the NFc is authorized to access the model corresponding to the analytics ID.

[0447] In another possible implementation, the model authorization response message #1 includes the identifier indicating that the NRF agrees to authorize the NFc to acquire the target model and the analytics ID that the NFc is authorized to access.

[0448] Optionally, the model authorization response message #1 further includes the validity period of the authorization described above.

[0449] Optionally, the model authorization response message #1 further includes the NFp ID.

[0450] S609, the NRF sends an access token response message #1 to the NFc.

[0451] Correspondingly, the NFc receives the access token response message #1 from the NRF.

[0452] Wherein, the access token response message #1 includes token #4. It should be understood that the NRF will generate token #4 according to the content of the local configuration.

[0453] In a possible implementation, token #4 includes the expiration time of token #4 and the analysis ID of the model authorized for NFc to obtain.

[0454] In another possible implementation, token #4 includes the expiration time of token #4, the analysis ID of the model authorized for NFc to obtain, and the interoperability identification of the model authorized for NFc to access.

[0455] In another possible implementation, token #4 includes the expiration time of token #4, the analysis ID of the model authorized for NFc to obtain, and the supplier ID(s) of the model authorized for NFc to access.

[0456] In another possible implementation, token #4 includes the expiration time of token #4, the analysis ID of the model authorized for NFc to obtain, the interoperability identification of the model authorized for NFc to access, and the NFp ID(s).

[0457] Case 2

[0458] Wherein, the NRF requests detailed authorization information from the NFp through the model authorization request message #1, as an example but not limited to, the NRF requests the specific case of model authorization from the NFp through the model authorization request message #1, including the specific authorized model indication information, the authorization time, etc.

[0459] Mode 1

[0460] S607, the NFp decides to authorize the model.

[0461] It should be understood that the NFp needs to determine whether to agree to authorize the NFc to obtain the model according to the NFc information carried by the NRF in the model authorization request message #1, in combination with the local policy.

[0462] Illustratively, the NFp verifies that the analysis ID included in the model authorization request message #1 belongs to the service capability range of the NFp.

[0463] Illustratively, the NFp verifies that the supplier ID of the NFc included in the model authorization request message #1 is within the interoperability identification of the NFp.

[0464] Illustratively, the NFp verifies that the interoperability ID of the NFc included in the model authorization request message #1 is within the interoperability identification of the NFp.

[0465] Further, the NFp decides to authorize the specific model to the NFc in combination with the local policy, thereby returning the detailed authorization information to the NRF.

[0466] Exemplarily, the NFp determines the specific model to be authorized to the NFc according to the analysis ID included in the Model Authorization Request message #1.

[0467] Optionally, when the model filter information is included in the Model Authorization Request message #1, the NFp further selects the suitable model according to the model filter information.

[0468] In a possible implementation, the NFp requests the ADRF for the address of the model authorized to the NFc to obtain a new model address and add in the detailed authorization information.

[0469] S608, the NFp sends the Model Authorization Response message #1 to the NRF.

[0470] Correspondingly, the NRF receives the Model Authorization Response message #1 from the NFp.

[0471] It should be understood that the NFp generates the Model Authorization Response message #1 based on the detailed authorization information determined in S607.

[0472] In a possible implementation, the Model Authorization Response message #1 includes an indication of agreeing to the NRF authorizing the NFc to obtain the analysis ID.

[0473] In another possible implementation, the Model Authorization Response message #1 includes an indication of agreeing to the NRF authorizing the NFc to obtain the target model.

[0474] In another possible implementation, the Model Authorization Response message #1 includes an indication of agreeing to the NRF authorizing the NFc to obtain the target model and the NFp ID.

[0475] In yet another possible implementation, the Model Authorization Response message #1 includes an indication of agreeing to the NRF authorizing the NFc to obtain the target model and the ADRF ID corresponding to the target model.

[0476] In yet another possible implementation, the Model Authorization Response message #1 includes an indication of agreeing to the NRF authorizing the NFc to obtain the target model and the model indication information of the target model. As an example but not limitation, the model indication information includes one or more of the model identifier (ML Model Identifier) or the address of the model (Address of Model file) or the hash of the address of the model file (Hash of Address of Model file), wherein the address of the model can be a URL or a FQDN, and correspondingly, the hash of the address of the model can be a hash of the URL or the FQDN.

[0477] In yet another possible implementation, the model authorization information response message #1 includes an identifier indicating the consent of the NRF to authorize the NFc to obtain the target model, an authorization expiration time, model indication information of the target model, and an ADRF ID corresponding to the target model.

[0478] In each of the above implementation, optionally, the model authorization response message #1 further includes an authorization expiration time of the NFp authorizing the NFc to obtain the model.

[0479] In each of the above implementation, optionally, the model authorization response message #1 further includes an analysis ID that the NFc is authorized to access. The analysis ID indicates the model corresponding to the analysis ID(s) generated by the NFp.

[0480] It should be noted that the address of the model included in the model authorization response message #1 can be the address of the model stored by the NFp in step S602, or the address of the model requested to obtain from the ADRF in S611, and the embodiments of the present application do not limit this.

[0481] S609, the NRF sends an access token response message #1 to the NFc.

[0482] Correspondingly, the NFc receives the access token response message #1 from the NRF.

[0483] The access token response message #1 includes token #4.

[0484] It should be understood that the NRF will generate token #4 according to the local configuration and the content of the model authorization response message #1.

[0485] In one possible implementation, token #4 includes an expiration time of token #4 and an analysis ID of the model that the NFc is authorized to obtain.

[0486] In another possible implementation, token #4 includes an expiration time of token #4, an analysis ID of the model that the NFc is authorized to obtain, and an interoperability identifier of the model that the NFc is authorized to access.

[0487] In another possible implementation, token #4 includes an expiration time of token #4, an analysis ID of the model that the NFc is authorized to obtain, and a supplier ID of the model that the NFc is authorized to access.

[0488] In another possible implementation, token #4 includes an expiration time of token #4, an analysis ID of the model that the NFc is authorized to obtain, an interoperability identifier of the model that the NFc is authorized to access, and NFp ID(s).

[0489] In another possible implementation, the token #4 includes an expiration time of the token #4, an analytics ID of the model authorized for the NFc to acquire, and an NFp ID(s) of the model authorized for the NFc to access.

[0490] In another possible implementation, the token #4 includes an expiration time of the token #4, an analytics ID of the model authorized for the NFc to acquire, an interoperation identification of the model authorized for the NFc to access, an NFp ID(s), and model indication information of the model authorized for the NFc to acquire. Optionally, a vendor ID of the NFc is also included in the token #4.

[0491] Mode 2

[0492] S607, the NFp decides to authorize the model.

[0493] It should be understood that the NFp needs to determine whether to agree to authorize the NFc to acquire the model according to the NFc information carried in the model authorization request message #1 by the NRF, in combination with a local policy.

[0494] For example, the NFp verifies that the analytics ID included in the model authorization request message #1 belongs to the service capability range of the NFp.

[0495] For example, the NFp verifies that the vendor ID of the NFc included in the model authorization request message #1 is within the interoperation identification of the NFp.

[0496] For example, the NFp verifies that the interoperation ID of the NFc included in the model authorization request message #1 is within the interoperation identification of the NFp.

[0497] Further, the NFp decides to authorize the specific model to the NFc in combination with the model authorization request message #1 and the local policy, and further generates a model authorization token #2. For example, the model authorization token can be a CCA, and the embodiments of the present application do not limit this, and any function that can be implemented can be used.

[0498] In a possible implementation, the model authorization token #2 generated by the NFp includes an NFp ID, an NFc ID, an expiration time of the model authorization token #2, and an analytics ID of the model authorized for the NFc to acquire.

[0499] In another possible implementation, the model authorization token #2 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #2, and the model indication information of the model authorized for the NFc to obtain. As an example but not limitation, the model indication information includes one or more of a model identifier (ML Model Identifier) or an address of the model (Address of Model file) or a hash of the address of the model file (Hash of Address of Model file), where the address of the model can be a URL or a FQDN, and correspondingly, the hash of the address of the model can be a hash of the URL or the FQDN.

[0500] In yet another possible implementation, the model authorization token #2 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #2, and an analytics ID of the model authorized for the NFc to obtain and an ADRF ID or an ADRF type where the model is located.

[0501] In yet another possible implementation, the model authorization token #2 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #2, and an analytics ID of the model authorized for the NFc to obtain and model indication information of the model.

[0502] In yet another possible implementation, the model authorization token #2 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #2, and model indication information of the model authorized for the NFc to obtain and an ADRF ID or an ADRF type where the model is located.

[0503] In yet another possible implementation, the model authorization token #2 generated by the NFp includes the NFp ID, the NFc ID, the expiration time of the model authorization token #2, and an analytics ID of the model authorized for the NFc to obtain, model indication information of the model, and an ADRF ID or an ADRF type where the model is located.

[0504] S608, the NFp sends the model authorization response message #1 to the NRF.

[0505] Correspondingly, the NRF receives the model authorization response message #1 from the NFp.

[0506] In the model authorization response message #1, the NFp generates the model authorization token #2.

[0507] Optionally, the model authorization response message #1 further includes the authorization information in the model authorization token #2.

[0508] Optionally, the model authorization response message #1 further includes an identifier indicating that the NFp authorizes the NFc to obtain the model.

[0509] Optionally, the model authorization response message #1 further includes the NFp ID.

[0510] S609, the NRF sends an access token response message #1 to the NFc.

[0511] Correspondingly, the NRF receives the access token response message #1 from the NFc.

[0512] In a possible implementation, the access token response message #1 includes a token #4.

[0513] It should be understood that the NRF will generate the token #4 according to the local configuration and the content of the model authorization token #2.

[0514] Exemplarily, the token #4 includes its own expiration time and the analytics ID of the model that the NFc is authorized to obtain.

[0515] Exemplarily, the token #4 includes its own expiration time, the analytics ID of the model that the NFc is authorized to obtain, and the interoperability identifier of the model that the NFc is authorized to access.

[0516] Exemplarily, the token #4 includes its own expiration time, the analytics ID of the model that the NFc is authorized to obtain, the interoperability identifier of the model that the NFc is authorized to access, and the NFp ID(s).

[0517] Exemplarily, the token #4 includes its own expiration time, the analytics ID of the model that the NFc is authorized to obtain, the interoperability identifier of the model that the NFc is authorized to access, the NFp ID(s), and the model indication information of the model that the NFc is authorized to obtain.

[0518] Exemplarily, the token #4 includes its own expiration time and the model indication information of the model that the NFc is authorized to obtain.

[0519] Optionally, the token #4 further includes the vendor ID of the NFc.

[0520] Optionally, the token #4 further includes the interoperability ID of the NFc.

[0521] In another possible implementation, the access token response message #1 includes the token #4 and the model authorization token #2.

[0522] It should be understood that the NRF will generate the token #4 according to the local configuration.

[0523] Exemplarily, the token#4 includes its own expiry time and the analytics ID of the model authorized for the NFc to retrieve.

[0524] Exemplarily, the token#4 includes its own expiry time, the analytics ID of the model authorized for the NFc to retrieve and the interoperability identification of the model authorized for the NFc to access.

[0525] Exemplarily, the token#4 includes its own expiry time, the analytics ID of the model authorized for the NFc to retrieve, the interoperability identification of the model authorized for the NFc to access and the NFp ID(s).

[0526] Optionally, the token#4 further includes the vendor ID of the NFc.

[0527] Optionally, the token#4 further includes the interoperability ID of the NFc.

[0528] In yet another possible implementation, the access token response message#1 includes the token#4, the model authorization token#2 and the information in the model authorization token.

[0529] In this implementation, the NRF reads the authorization information in the model authorization token#2 before performing the step S609, or the NRF includes the authorization information in the model authorization token#2 in the model authorization response message#1 according to the authorization information carried in the model authorization response message#1.

[0530] It should be understood that the NRF will generate the token#4 according to the local configuration.

[0531] Exemplarily, the token#4 includes its own expiry time and the analytics ID of the model authorized for the NFc to retrieve.

[0532] Exemplarily, the token#4 includes its own expiry time, the analytics ID of the model authorized for the NFc to retrieve and the interoperability identification of the model authorized for the NFc to access.

[0533] Exemplarily, the token#4 includes its own expiry time, the analytics ID of the model authorized for the NFc to retrieve, the interoperability identification of the model authorized for the NFc to access and the NFp ID(s).

[0534] Optionally, the token#4 further includes the vendor ID of the NFc.

[0535] Optionally, the token#4 further includes the interoperability ID of the NFc.

[0536] It should be understood that the NFc obtains the token#4 through the above steps S607 to S609.

[0537] S610. Optionally, the NFc sends an access authorization token request message #2 to the NRF.

[0538] Correspondingly, the NFc receives an access authorization token response message #2 from the NRF.

[0539] The access authorization token response message #2 is used to request the ADRF where the target model is located.

[0540] It should be understood that the NFc can determine the ADRF where the target model is located through the NRF or through the NFp.

[0541] S611. Optionally, the NRF sends an access authorization token response message #2 to the NFc.

[0542] Correspondingly, the NRF receives an access authorization token response message #2 from the NFc.

[0543] The access authorization token response message #3 includes the token #5.

[0544] The specific implementation of steps S610 and S611 can refer to steps S407 and S408 of the above method 400. For example, before performing step S611, the NRF needs to check whether the NWDAF containing the AnLF is authorized to access the ADRF. Only in the case of verification, the NRF generates the token #5, and then performs step S611, which will not be described in detail here.

[0545] S612. The NFc sends a model obtaining request message #1 to the ADRF.

[0546] The model obtaining request message #1 includes the analysis ID.

[0547] Optionally, the model obtaining request message #1 further includes the model ID that the NFc requests to access.

[0548] Optionally, the model obtaining request message #1 further includes the indication information #1 of the NFc.

[0549] Correspondingly, the ADRF receives the model obtaining request message #1 from the NFc.

[0550] In one possible implementation, the model obtaining request message #1 includes the analysis ID of the model that the NFc requests to obtain and the token #4.

[0551] In another possible implementation, the model obtaining request message #1 includes the analysis ID of the model that the NFc requests to obtain, the token #4, and the model authorization token #2.

[0552] Optionally, the model retrieval request message #1 may also include the model ID of the model requested by the NFC request.

[0553] Optionally, the model retrieval request message #1 may also include token #5.

[0554] Optionally, the model acquisition request message #1 also includes a random number generated by the NFc, which enables ADRF to generate a ticket based on the random number in subsequent steps, thereby binding the NFc ID and the model address information #1 to ensure that only a specific NFc can acquire the model based on the model address information #1.

[0555] S613, ADRF verification to determine whether NFC is authorized to obtain the model.

[0556] For example, ADRF verifies whether token #4 is valid based on its expiration time, and ADRF verifies that the NFc ID identity of the sending model retrieval request message #1 is consistent with the NFc ID in token #4.

[0557] Optionally, when token#4 contains ADRFID, ADRF verifies that the ADRFID in token#4 matches its own NF ID.

[0558] Optionally, when token#4 contains NFp ID and ML model indication information, ADRF verifies the relationship between the NFp ID in token#4 and the model indication information indicating the model, and determines that NFp does indeed have the authorization permissions for the model.

[0559] It should be understood that after the verification is successful using the example above, ADRF returns model address information #1 (e.g., address of model file2) to NFC based on token #4 and local configuration information, so that NFC can obtain the model.

[0560] In one possible implementation, ADRF can use a ticket as a model retrieval credential, binding the NFc ID and model address information #2 to ensure that only a specific NFc can retrieve the model based on model address information #2.

[0561] Furthermore, ADRF notifies the third-party storage address of the ticket content.

[0562] As an example and not a limitation, the content of the ticket can be [token#4, the MAC of token#4, a random number provided by NFc (which NFc carries when sending the model request), and a random number generated by NFp].

[0563] Correspondingly, in this implementation, the model also includes a ticket when obtaining response message #1.

[0564] Optionally, the ticket includes the model address information #2.

[0565] S614, the ADRF sends a model obtaining response message #1 to the NFc.

[0566] Correspondingly, the NFc receives the model obtaining response message #1 from the ADRF.

[0567] The model obtaining response message #1 includes the model address information #2.

[0568] S615, the NFc and the ADRF perform model transmission.

[0569] The NFc obtains the target model according to the model address information #2.

[0570] Figure 7 is a schematic diagram of a communication apparatus 1000 provided by an embodiment of the present application. As shown in the figure, the apparatus 1000 can include a transceiver unit 1010 and a processing unit 1020. The transceiver unit 1010 can communicate with the outside, and the processing unit 1020 is configured to perform data processing. The transceiver unit 1010 can also be referred to as a communication interface or a transceiver unit. Figure 7 In a possible design, the apparatus 1000 can implement steps or procedures corresponding to those performed by the NFc in the above method embodiments, where the processing unit 1020 is configured to perform processing-related operations of the NFc in the above method embodiments, and the transceiver unit 1010 is configured to perform transceiving-related operations of the NFc in the above method embodiments.

[0571] In another possible design, the apparatus 1000 can implement steps or procedures corresponding to those performed by the NFp in the above method embodiments, where the transceiver unit 1010 is configured to perform transceiving-related operations of the NFp in the above method embodiments, and the processing unit 1020 is configured to perform processing-related operations of the NFp in the above method embodiments.

[0572] In yet another possible design, the apparatus 1000 can implement steps or procedures corresponding to those performed by the NRF in the above method embodiments, where the transceiver unit 1010 is configured to perform transceiving-related operations of the NRF in the above method embodiments, and the processing unit 1020 is configured to perform processing-related operations of the NRF in the above method embodiments.

[0573] In yet another possible design, the apparatus 1000 can implement steps or procedures corresponding to those performed by the NRF in the above method embodiments, where the transceiver unit 1010 is configured to perform transceiving-related operations of the NRF in the above method embodiments, and the processing unit 1020 is configured to perform processing-related operations of the NRF in the above method embodiments.

[0574] In another possible design, the device 1000 can implement the steps or processes corresponding to the ADRF execution in the above method embodiments, wherein the transceiver unit 1010 is used to perform the transceiver-related operations of the ADRF in the above method embodiments, and the processing unit 1020 is used to perform the processing-related operations of the ADRF in the above method embodiments.

[0575] It should be understood that the device 1000 here is embodied in the form of a functional unit. The term "unit" here can refer to an application-specific integrated circuit (ASIC), electronic circuitry, a processor (e.g., a shared processor, a proprietary processor, or a group processor, etc.) and memory for executing one or more software or firmware programs, integrated logic circuitry, and / or other suitable components supporting the described functions. In an alternative example, those skilled in the art will understand that the device 1000 may specifically be the transmitting end in the above embodiments, used to execute the various processes and / or steps corresponding to the transmitting end in the above method embodiments; or, the device 1000 may specifically be the receiving end in the above embodiments, used to execute the various processes and / or steps corresponding to the receiving end in the above method embodiments. To avoid repetition, further details are omitted here.

[0576] The device 1000 in each of the above-described schemes has the function of implementing the corresponding steps performed by the transmitting end in the above-described method, or the device 1000 in each of the above-described schemes has the function of implementing the corresponding steps performed by the receiving end in the above-described method. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions; for example, the transceiver unit can be replaced by a transceiver (e.g., the transmitting unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as processing units, can be replaced by processors, respectively executing the transceiver operations and related processing operations in each method embodiment.

[0577] Furthermore, the aforementioned transceiver unit can also be a transceiver circuit (e.g., it may include a receiving circuit and a transmitting circuit), and the processing unit can be a processing circuit. In embodiments of this application, Figure 9 The device mentioned can be the receiving end or transmitting end in the foregoing embodiments, or it can be a chip or a chip system, such as a system on a chip (SoC). The transceiver unit can be an input / output circuit or a communication interface. The processing unit is a processor, microprocessor, or integrated circuit integrated on the chip. No limitations are imposed here.

[0578] Figure 8 This is a schematic diagram of another communication device 2000 provided in an embodiment of this application. For example...Figure 8 As shown in FIG. 20, the device 2000 includes a processor 2010 and a transceiver 2020. The processor 2010 and the transceiver 2020 communicate with each other through an internal connection path. The processor 2010 is configured to execute instructions to control the transceiver 2020 to transmit and / or receive signals.

[0579] Optionally, the device 2000 can further include a memory 2030, which communicates with the processor 2010 and the transceiver 2020 through an internal connection path. The memory 2030 is configured to store instructions, and the processor 2010 is configured to execute the instructions stored in the memory 2030.

[0580] In a possible implementation, the device 2000 is configured to implement the procedures and steps corresponding to the NFc in the method embodiments described above.

[0581] In another possible implementation, the device 2000 is configured to implement the procedures and steps corresponding to the NFp in the method embodiments described above.

[0582] In yet another possible implementation, the device 2000 is configured to implement the procedures and steps corresponding to the NRF in the method embodiments described above.

[0583] In yet another possible implementation, the device 2000 is configured to implement the procedures and steps corresponding to the ADRF in the method embodiments described above.

[0584] It should be understood that the device 2000 can be a transmitter or a receiver in the above-described embodiments, and can also be a chip or a chip system. Correspondingly, the transceiver 2020 can be a transceiver circuit of the chip, which is not limited herein. Specifically, the device 2000 can be configured to perform the procedures and steps corresponding to the transmitter or the receiver in the above-described method embodiments.

[0585] Optionally, the memory 2030 can include a read-only memory and a random access memory, and provide instructions and data to the processor. A part of the memory can also include a non-volatile random access memory. For example, the memory can also store device type information. The processor 2010 can be configured to execute the instructions stored in the memory, and when the processor 2010 executes the instructions stored in the memory, the processor 2010 is configured to perform the procedures and steps corresponding to the transmitter or the receiver in the above-described method embodiments.

[0586] In the implementation process, the steps of the above method can be completed by the integrated logic circuit of hardware in the processor or the instruction in the form of software. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as hardware processor execution completion, or executed by the combination of hardware and software modules in the processor. The software module can be located in the mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, register, etc. The storage medium is located in the memory, and the processor reads the information in the memory, and combines the hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0587] It should be noted that the processor in the embodiments of the present application can be an integrated circuit chip with signal processing capability. In the implementation process, the steps of the above method embodiments can be completed by the integrated logic circuit of hardware in the processor or the instruction in the form of software. The above processor can be a general processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The processor in the embodiments of the present application can realize or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as hardware decoding processor execution completion, or executed by the combination of hardware and software modules in the decoding processor. The software module can be located in the mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, register, etc. The storage medium is located in the memory, and the processor reads the information in the memory, and combines the hardware to complete the steps of the above method.

[0588] It is to be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronous link dynamic random access memory and direct memory bus random access memory. It should be noted that the memory of the system and method described herein is intended to include but not limited to these and any other suitable types of memory.

[0589] Figure 9 is a schematic diagram of a chip system 3000 provided by an embodiment of the present application. The chip system 3000 (or also referred to as a processing system) includes a logic circuit 3010 and an input / output interface 3020.

[0590] Among them, the logic circuit 3010 can be a processing circuit in the chip system 3000. The logic circuit 3010 can be coupled to a storage unit, call instructions in the storage unit, so that the chip system 3000 can implement the methods and functions of the embodiments of the present application. The input / output interface 3020 can be an input / output circuit in the chip system 3000, which outputs the processed information of the chip system 3000 or inputs the data or signaling information to be processed into the chip system 3000 for processing.

[0591] As a solution, the chip system 3000 is used to implement the operations performed by the NFc in the above various method embodiments. For example, the logic circuit 3010 is used to implement the processing-related operations performed by the NFc in the above method embodiments; the input / output interface 3020 is used to implement the sending and / or receiving-related operations performed by the NFc in the above method embodiments.

[0592] As another option, the chip system 3000 is configured to implement operations performed by the NFp in the various method embodiments described above. For example, the logic circuit 3010 is configured to implement processing-related operations performed by the NFp in the method embodiments described above; the input / output interface 3020 is configured to implement sending and / or receiving-related operations performed by the NFp in the method embodiments described above.

[0593] As another option, the chip system 3000 is configured to implement operations performed by the ADRF in the various method embodiments described above. For example, the logic circuit 3010 is configured to implement processing-related operations performed by the ADRF in the method embodiments described above; the input / output interface 3020 is configured to implement sending and / or receiving-related operations performed by the ADRF in the method embodiments described above.

[0594] As another option, the chip system 3000 is configured to implement operations performed by the NRF in the various method embodiments described above. For example, the logic circuit 3010 is configured to implement processing-related operations performed by the NRF in the method embodiments described above; the input / output interface 3020 is configured to implement sending and / or receiving-related operations performed by the NRF in the method embodiments described above.

[0595] Embodiments of the present application also provide a computer readable storage medium having stored thereon computer instructions for implementing the method performed by the device (e.g., the NFc, or the NFp, or the ADRF, or the NRF) in the various method embodiments described above.

[0596] Embodiments of the present application also provide a computer program product containing instructions, which, when executed by a computer, implement the method performed by the device (e.g., the NFc, or the NFp, or the ADRF, or the NRF) in the various method embodiments described above.

[0597] Embodiments of the present application also provide a communication system, which includes one or more of the aforementioned NFc, or the NFp, or the ADRF, or the NRF.

[0598] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0599] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0600] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0601] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments.

[0602] In addition, each functional unit in the embodiments of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0603] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and various media that can store program codes.

[0604] The above describes only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method, characterized in that, include: The network storage function network element receives a first request message from the first network function. The first request message is used to request authorization for the first network function to obtain the model. The first request message includes a first interoperability identifier, which is used to indicate the supplier information of the model production network element that the first network function supports for interoperability. The network storage function network element determines the model production network element based on the first interoperability identifier; The network storage function network element sends a second request message to the model production network element according to the first request message. The second request message is used to request confirmation of whether to authorize the first network function to obtain the model. The network storage element receives a second response message from the model production element and generates a first access token based on the second response message. The second response message is used to indicate authorization for the first network function to obtain the model, and the first access token is used to indicate authorization for the first network function to obtain the model. The network storage function element sends a first response message to the first network function, the first response message including the first access token.

2. The method according to claim 1, characterized in that, The first request message includes an analysis identifier, which indicates the type of the model.

3. The method according to claim 2, characterized in that, Before the network storage function element sends a second request message to the model production network element based on the first request message, the method further includes: The network storage function network element determines the model production network element based on the analysis identifier and the analysis identifier corresponding to at least one model production network element stored in the network storage function network element.

4. The method according to claim 3, characterized in that, The network storage function element determines the model production network element based on the analysis identifier and the analysis identifier corresponding to at least one model production network element stored in the network storage function element, including: The network storage function network element determines the model production network element based on the analysis identifier, the analysis identifier corresponding to at least one model production network element stored in the network storage function network element, the supplier identifier of the first network function, and the interoperability identifier of at least one model production network element stored in the network storage function network element, wherein the interoperability identifier of the at least one model production network element is used to indicate the supplier of the network function that allows the model to be obtained from the at least one model production network element.

5. The method according to claim 4, characterized in that, The network storage function element determines the model production network element based on the analysis identifier, the analysis identifier corresponding to at least one model production network element stored in the network storage function element, the supplier identifier of the first network function, and the interoperability identifier of at least one model production network element stored in the network storage function element, including: The network storage function element determines at least two candidate model production elements based on the analysis identifier in the first request message and the analysis identifier corresponding to the at least one network production element; and The network storage function network element determines the model production network element from the at least two candidate model production network elements based on the supplier identifier of the first network function and the interoperability identifier of at least one model production network element stored in the network storage function network element.

6. The method according to claim 3, characterized in that, The first request message further includes a first identifier, which indicates the supplier of the model production network element corresponding to the model that the first network function expects to obtain; and The network storage function element determines the model production network element based on the analysis identifier and the analysis identifier corresponding to at least one model production network element stored in the network storage function element, including: The network storage function network element determines the model production network element based on the analysis identifier, the analysis identifier corresponding to at least one model production network element stored in the network storage function network element, the vendor identifier of the first network function, the interoperability identifier of at least one model production network element stored in the network storage function network element, the first identifier, and the vendor identifier of at least one model production network element stored in the network storage function network element, wherein the interoperability identifier of the at least one model production network element is used to indicate the vendor of the network function that allows the model to be obtained from the at least one model production network element.

7. The method according to any one of claims 2 to 6, characterized in that, The second request message includes the analysis identifier.

8. The method according to any one of claims 2 to 6, characterized in that, The second request message also includes the vendor identifier of the first network function and / or the identifier of the first network function.

9. The method according to any one of claims 2 to 6, characterized in that, The second response message includes the identification information of the model.

10. The method according to claim 9, characterized in that, The first access token includes the identification information of the model.

11. The method according to any one of claims 2 to 6, characterized in that, The second response message also includes a second access token, which is used to indicate authorization for the first network function to obtain the model. The second access token includes the identifier of the first network function, the identifier of the model producing network element, and the analysis identifier and / or the identification information of the model.

12. The method according to claim 11, characterized in that, The first response message also includes the second access token.

13. The method according to any one of claims 2 to 6, characterized in that, The first access token includes the analytics identifier.

14. The method according to any one of claims 2 to 6, characterized in that, The first access token includes a first identifier, which indicates the vendor type of the model production network element to which the first network function is authorized to access.

15. A communication method, characterized in that, include: The model production network element receives a request message from the network storage function network element. The request message is used to request confirmation of whether the first network function is authorized to obtain the model. The request message includes a first interoperability identifier, which is used to indicate the supplier information of the model production network element that the first network function supports interoperability with. The model-producing network element determines, based on the request message, that it is authorized by the first network function to obtain the model; The model production network element sends a response message to the network storage function network element, and the response message is used to instruct the first network function to obtain the model.

16. The method according to claim 15, characterized in that, The model-producing network element determines, based on the request message, that it is authorized by the first network function to obtain the model, including: The model-producing network element determines the authorization of the first network function to obtain the model based on the first interoperability identifier.

17. The method according to claim 16, characterized in that, The request message includes an analysis identifier, a vendor identifier for the first network function, and an identifier for the first network function, wherein the analysis identifier is used to indicate the type of the model.

18. The method according to claim 17, characterized in that, The model-producing network element determines, based on the request message, that it is authorized by the first network function to obtain the model, including: The model-producing network element determines the identification information of the model based on the analysis identifier; The model-producing network element adds the model's identification information to the response message.

19. The method according to claim 17 or 18, characterized in that, The model-producing network element determines, based on the request message, that it is authorized by the first network function to obtain the model, including: The model production network element generates a second access token, which is used to indicate authorization for the first network function to obtain the model. The second access token includes the identifier of the first network function, the identifier of the model production network element, and the analysis identifier and / or the identifier information of the model. The model production network element adds the second access token to the response message.

20. A communication system, characterized in that, This includes network storage function network elements and model production network elements: The network storage function element is used to receive a first request message from a first network function. The first request message is used to request authorization for the first network function to obtain a model. The first request message includes a first interoperability identifier, which is used to indicate the supplier information of the model production network element that the first network function supports for interoperability. The network storage function network element determines the model production network element based on the first interoperability identifier; The network storage function network element is also used to send a second request message to the model production network element according to the first request message. The second request message is used to request confirmation of whether to authorize the first network function to obtain the model. The model production network element is used to receive the second request message from the network storage function network element; The model production network element is also used to determine, based on the second request message, to authorize the first network function to obtain the model; The model production network element is also used to send a second response message to the network storage function network element, the second response message being used to instruct the first network function to obtain the model; The network storage function element is also used to receive the second response message from the model production element, and generate a first access token based on the second response message. The first access token is used to indicate authorization for the first network function to obtain the model. The network storage function element is also used to send a first response message to the first network function, the first response message including the first access token.

21. The communication system according to claim 20, characterized in that, The communication system further includes a first functional network element and a model storage network element: The first network function is used to send a third request message to the model storage network element, the third request message being used to request to obtain the model, the third request message including the first access token; The first network function is used to receive a third response message from the model storage network element, the third response message including the storage address of the model.

22. A communication device, characterized in that, The apparatus includes: a module for performing the method as described in any one of claims 1 to 14, or a module for performing the method as described in any one of claims 15 to 19.

23. A communication device, characterized in that, include: A processor for executing a computer program stored in memory to cause the apparatus to perform the method as claimed in any one of claims 1 to 14, or to cause the apparatus to perform the method as claimed in any one of claims 15 to 19.

24. A computer program product, characterized in that, The computer program product includes instructions for performing the method as described in any one of claims 1 to 14, or the computer program product includes instructions for performing the method as described in any one of claims 15 to 19.

25. A computer-readable storage medium, characterized in that, include: The computer-readable storage medium stores a computer program; when the computer program is run on a computer, it causes the computer to perform the method as described in any one of claims 1 to 14, or causes the computer to perform the method as described in any one of claims 15 to 19.

Images