Model licensing method, apparatus and readable storage medium

Abstract

The application relates to the technical field of communication, in particular to a model authorization method and device and a readable storage medium, the method comprising the following steps: an MTLF1 receives a first model acquisition request of an AnLF, the first model acquisition request comprising an analysis ID; the MTLF1 sends a token acquisition request to an NRF, the token acquisition request comprising the analysis ID, an AnLF ID and an MTLF2 ID, the MTLF2 being used for providing a model corresponding to the analysis ID; after the NRF verifies that the AnLF has the permission to acquire the model from the MTLF2, the NRF returns a first token to the MTLF1; the MTLF1 sends a second model acquisition request to the MTLF2, the second model acquisition request comprising the analysis ID, the AnLF ID and the first token; after the MTLF2 verifies that the first token is correct, the MTLF2 sends information of the model to the AnLF. By adopting the application, the model authorization and model acquisition in the model delegation acquisition scene can be realized, and the security of the model is improved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a model licensing method, apparatus and readable storage medium. Background Technology

[0002] Network data analytics function (NWDAF) network elements have functions such as data collection, model training, data analysis, and model inference. NWDAF network elements containing analytics logical function (AnLF) can be used to infer and derive analytical information and expose analytical services. NWDAF network elements containing model training logical function (MTLF) can be used to train machine learning (ML) models or artificial intelligence (AI) models and expose new training services; for example, providing trained AI or ML models. Analytics data repository functional (ADRF) network elements can provide services for storing, deleting, and retrieving AI / ML models.

[0003] AI / ML models can be stored in ADRF network elements in the following way: A consumer (e.g., an NWDAF network element containing MTLF) sends a Nadrf_MLModelManagement_Storage Request to the ADRF network element, which contains the model to be stored or the address of the model; the ADRF network element returns a response, providing a result indication. AI / ML models can be retrieved from ADRF network elements as follows: A consumer (e.g., an NWDAF network element containing AnLF) sends a Nadrf_MLModelManagement_Retrieval Request to the ADRF network element, which includes an Analytics Identifier (ID) and a token. The ADRF network element authenticates the consumer (e.g., an NWDAF network element containing MTLF) and verifies whether the token and the consumer's (e.g., an NWDAF network element containing MTLF) network function (NF) instance identifier (NF ID) are included in the allowed NF consumer (NFclist) of the ML model. If both verifications are successful, the ADRF network element returns a response providing a result indication.

[0004] Currently, authorization is required during the model acquisition / retrieval process, but security issues still exist in model authorization in some scenarios. Summary of the Invention

[0005] This application provides a model authorization method, apparatus, and readable storage medium, which helps to realize model authorization and model acquisition in model delegation acquisition scenarios and improves the security of models in model delegation acquisition scenarios.

[0006] The present application is described below from different aspects. It should be understood that the different implementation methods and beneficial effects described below can be referenced from each other.

[0007] In a first aspect, this application provides a model authorization method, the method comprising: a first model training logic function network element receiving a first model acquisition request from an analysis logic function network element, the first model acquisition request including an analysis identifier, the first model acquisition request being usable to request information of a model corresponding to the analysis identifier; the first model training logic function network element sending a token acquisition request to a network repository function (NRF) network element, the token acquisition request including the analysis identifier, an identifier of the analysis logic function network element, and an identifier of a second model training logic function network element, the second model training logic function network element being usable to provide information of a model corresponding to the analysis identifier; the first model training logic function network element receiving a first token from an NRF network element, the first token including the identifier of the analysis logic function network element and the identifier of the second model training logic function network element; the first model training logic function network element sending a second model acquisition request to the second model training logic function network element, the second model acquisition request including the analysis identifier, the identifier of the analysis logic function network element, and the first token, the second model acquisition request being used to obtain information of a model corresponding to the analysis identifier for the analysis logic function network element.

[0008] In this application, the identifiers of various network elements can be Network Function Instance IDs (NF instance IDs), which will not be elaborated further below. For example, the identifier of an analysis logic function network element refers to its NF instance ID, and the identifier of a second model training logic function network element refers to its NF instance ID. The NF instance ID can be used to uniquely identify a network function instance (NF Instance ID: Unique identity of the NF Instance).

[0009] For example, the first token in the second model acquisition request can be used to verify the second model acquisition request. Alternatively, the first token in the second model acquisition request can be used to verify various identifiers in the second model acquisition request. Alternatively, the first token in the second model acquisition request can be used to verify the permission of the analysis logic function network element to acquire a model (which can be the model corresponding to the aforementioned analysis ID) from the second model training logic function network element. Alternatively, the first token in the second model acquisition request can be used to verify the permission of the first model training logic function network element (or representing behalf) for the analysis logic function network element to acquire a model (which can be the model corresponding to the aforementioned analysis ID) from the second model training logic function network element.

[0010] For example, the first model training logic function network element can be a first network element with model training logic function, such as a first NWDAF network element containing MTLF (NWDAF1 containing MTLF), which can be simply referred to as MTLF1. The second model training logic function network element can be a second network element with model training logic function, such as a second NWDAF network element containing MTLF (NWDAF2 containing MTLF), which can be simply referred to as MTLF2. The analysis logic function network element can be a network element with analysis logic function, such as an NWDAF network element containing AnLF (NWDAF containing AnLF), which can be simply referred to as AnLF.

[0011] For example, the token acquisition request described above can be used to request a first token. Alternatively, the token acquisition request can be used to request (NRF network element) authorization for the analysis logic function network element to obtain the model corresponding to the analysis ID from the second model training logic function network element. Or, the token acquisition request can be used by the first model training logic function network element to request a first token for (or on behalf of) the analysis logic function network element to obtain the model corresponding to the analysis ID. The first token can be used to indicate authorization for the analysis logic function network element to obtain information about the model corresponding to the analysis ID from the second model training logic function network element. Alternatively, the first token can be used to indicate authorization for the first model training logic function network element to (or on behalf of) the analysis logic function network element to obtain information about the model corresponding to the analysis ID from the second model training logic function network element.

[0012] Existing technologies only consider the case where NF service consumers directly obtain / retrieve models from model providers (such as NWDAF containing MTLF). However, for model delegation acquisition scenarios, model providers or model producers cannot verify whether the model consumer has the right to obtain the requested model, which poses a security problem.

[0013] After receiving a model acquisition request from an analysis logic function network element, the first model training logic function network element of this application requests an authorization token (i.e., the aforementioned first token) from the NRF for (or on behalf of) the analysis logic function network element. After obtaining the authorization token, the first model training logic function network element requests information about a model that meets the requirements from the second model training logic function network element for (or on behalf of) the analysis logic function network element. This request includes the identifier of the analysis logic function network element and the authorization token. This facilitates model authorization and model acquisition in a delegated acquisition scenario, and authorizes the actual model consumer (i.e., the analysis logic function network element) in the delegated acquisition scenario, thereby improving model security.

[0014] In conjunction with the first aspect, in one possible implementation, the aforementioned token acquisition request further includes one or more of the following: an identifier of the first model training logic function network element, a vendor identifier of the analysis logic function network element, or first indication information. The vendor identifier of the analysis logic function network element can be used by the NRF network element to verify whether it can be authorized to obtain the model corresponding to the analysis ID from the second model training logic function network element. The first indication information can be used to instruct the first model training logic function network element to request the first token for (or on behalf of) the analysis logic function network element. Alternatively, the first indication information can be used to indicate a request for the NRF network element to authorize the analysis logic function network element to obtain the model in the second model training logic function network element. Furthermore, the first indication information can be used to indicate that the token acquisition request is an access token acquisition request (Nnrf_AccessToken_Get request) for a model delegation acquisition scenario.

[0015] This application includes the vendor identifier of the analysis logic function network element in the token acquisition request, which helps the NRF network element verify whether the analysis logic function network element has the authority to obtain the model from the second model training logic function network element. This application also includes first indication information in the token acquisition request, which makes the meaning of the token acquisition request clearer and allows the NRF network element to understand its own behavior.

[0016] In conjunction with the first aspect, in one possible implementation, after receiving a token acquisition request from the first model training logic function network element, the NRF network element can verify whether the vendor identifier of the analysis logic function network element is included in the interoperability indicator corresponding to the aforementioned analysis ID of the second model training logic function network element. In other words, after receiving the aforementioned token acquisition request, the NRF network element can verify whether the analysis logic function network element has the authority to obtain the model from the second model training logic function network element. The specific verification method is described in the following method embodiment, and will not be detailed here. If the vendor identifier of the analysis logic function network element is included in the interoperability indicator corresponding to the aforementioned analysis ID of the second model training logic function network element, it indicates that the analysis logic function network element has the authority to obtain the model from the second model training logic function network element, and the NRF network element sends a first token to the first model training logic function network element.

[0017] In conjunction with the first aspect, in one possible implementation, the aforementioned first token further includes one or more of the following: the aforementioned analysis identifier, the identifier of the first model training logic function network element, the supplier identifier of the analysis logic function network element, or second instruction information. The second instruction information can be used to instruct the authorized analysis logic function network element to obtain the model information corresponding to the aforementioned analysis ID from the second model training logic function network element. Alternatively, the second instruction information can be used to indicate that the authorized first model training logic function network element is (or represents behalf) to obtain the model information corresponding to the analysis ID from the second model training logic function network element. Furthermore, the second instruction information can be used to indicate that the first token is an authorization token for a model delegation acquisition scenario.

[0018] This application includes second instruction information in the first token, which can make the meaning of the first token clearer and help the first model training logic function network elements to understand the role of the first token.

[0019] In conjunction with the first aspect, in one possible implementation, the aforementioned second model acquisition request further includes one or more of the following: the identifier of the first model training logic function network element, the address of the analysis logic function network element, the vendor identifier of the analysis logic function network element, or third indication information. The address of the analysis logic function network element can be carried by a subscription endpoint address. This subscription endpoint address can be used to represent the address for receiving model notification messages. The third indication information can be used to instruct the first model training logic function network element to acquire (or on behalf of) the analysis logic function network element information of the model corresponding to the aforementioned analysis ID. Alternatively, the third indication information can be used to indicate that the second model acquisition request is an ML model provision request (Nnwdaf_MLModelProvision request) for a model delegation acquisition scenario.

[0020] This application includes the address of the analysis logic function network element in the second model acquisition request, which helps the second model training logic function network element determine the recipient of the model notification message. This application also includes the vendor identifier of the analysis logic function network element in the second model acquisition request, which helps the second model training logic function network element verify whether it has the authority to acquire the model from itself. Finally, this application includes third instruction information in the second model acquisition request, which clarifies the meaning of the second model acquisition request and enables the second model training logic function network element to understand its own behavior.

[0021] In conjunction with the first aspect, in one possible implementation, after receiving the second model acquisition request, the second model training logic function network element can verify the first token in the request. The specific verification method is described in the following method embodiment and will not be detailed here. If the first token is successfully verified, the second model training logic function network element can send a model notification message to the analysis logic function network element. This model notification message may include information about the model corresponding to the analysis ID, such as: model identifier, the model's address in the second model training logic function network element, or the model file, etc. For example, the model notification message may also include the identifier of the ADRF network element storing the model.

[0022] In conjunction with the first aspect, in one possible implementation, before the first model training logic function network element sends a token acquisition request to the NRF network element, the method further includes: the first model training logic function network element sending a network element discovery request to the NRF network element, the network element discovery request including the analysis identifier, and the identifier of the analysis logic function network element and / or the vendor identifier of the analysis logic function network element; the first model training logic function network element receiving a network element discovery response from the NRF network element, the network element discovery response including a list of candidate network elements, the network element list including a second model training logic function network element, and the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element including the vendor identifier of the analysis logic function network element.

[0023] It is understandable that during the network element registration process, the first and second model training logic function network elements can register their respective analytics IDs and interoperability indicators with the NRF network element. The analytics logic function network element can register its own analytics ID and vendor ID with the NRF network element. The interoperability indicator can be used to represent a list of NWDAF providers (or vendors) that are allowed to retrieve ML models from the NWDAF containing MTLF.

[0024] In conjunction with the first aspect, in one possible implementation, after receiving a network element discovery request, the NRF network element can obtain the vendor identifier of the analysis logic function network element based on the network element discovery request; then, it can determine a candidate network element list based on the locally stored NF configuration files of each network element; and then send a network element discovery response to the first model training logic function network element, which includes the candidate network element list. The method by which the NRF network element determines the candidate network element list can be found in the description of the method embodiments below, and will not be detailed here. The interoperability indicator corresponding to the aforementioned analysis ID of each model training logic function network element in the candidate network element list includes the vendor identifier of the analysis logic function network element. The second model training logic function network element can be any network element in the candidate network element list.

[0025] Secondly, this application provides a model authorization method, which includes: an NRF network element receiving a token acquisition request from a first model training logic function network element, the token acquisition request including an analysis identifier, an identifier of the analysis logic function network element, and an identifier of a second model training logic function network element, the second model training logic function network element being able to provide information about the model corresponding to the analysis identifier; the NRF network element verifying whether the vendor identifier of the analysis logic function network element is included in the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element; if the vendor identifier is included in the interoperability indicator, indicating that the analysis logic function network element has the authority to obtain the model from the second model training logic function network element, then the NRF network element sending a first token to the first model training logic function network element, the first token including the identifier of the analysis logic function network element and the identifier of the second model training logic function network element.

[0026] For example, the token acquisition request described above can be used to request a first token. Alternatively, the token acquisition request can be used to request (NRF network element) authorization for the analysis logic function network element to obtain the model corresponding to the analysis ID from the second model training logic function network element. Or, the token acquisition request can be used by the first model training logic function network element to request a first token for (or on behalf of) the analysis logic function network element to obtain the model corresponding to the analysis ID. The first token can be used to indicate authorization for the analysis logic function network element to obtain information about the model corresponding to the analysis ID from the second model training logic function network element. Alternatively, the first token can be used to indicate authorization for the first model training logic function network element to (or on behalf of) the analysis logic function network element to obtain information about the model corresponding to the analysis ID from the second model training logic function network element.

[0027] The first model training logic function network element of this application requests an authorization token (i.e., the aforementioned first token) from the NRF as an analysis logic function network element (or representing the behalf of the analysis logic function network element). This request includes at least the identifier of the analysis logic function network element and the identifier of the second model training logic function network element. After verifying that the analysis logic function network element has the authority to obtain the model from the second model training logic function network element, the NRF returns the authorization token (i.e., the aforementioned first token) to the first model training logic function network element. This facilitates the first model training logic function network element (or representing the behalf of the analysis logic function network element) to obtain the model from the second model training logic function network element, thereby improving the security of the model.

[0028] In conjunction with the second aspect, in one possible implementation, before the NRF network element verifies whether the vendor identifier of the analysis logic function network element is included in the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element, the method further includes: the NRF network element obtaining the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element from the NF configuration file corresponding to the identifier of the second model training logic function network element. The interoperability indicator can be used to represent a list of NWDAF providers (or vendors) that allow retrieval of ML models from NWDAF containing MTLF.

[0029] In conjunction with the second aspect, in one possible implementation, before the NRF network element verifies whether the vendor identifier of the analysis logic function network element is included in the interoperability indicator of the second model training logic function network element, the method further includes: the NRF network element obtaining the vendor identifier of the analysis logic function network element from the NF configuration file corresponding to the identifier of the analysis logic function network element.

[0030] In conjunction with the second aspect, in one possible implementation, the aforementioned token acquisition request further includes one or more of the following: an identifier of the first model training logic function network element, a vendor identifier of the analysis logic function network element, or first indication information. The analysis ID can be the identifier of the analysis service corresponding to the requested authorized model. The vendor identifier of the analysis logic function network element can be used by the NRF network element to verify whether it can be authorized to obtain the model corresponding to the analysis ID from the second model training logic function network element. The first indication information can be used to instruct the first model training logic function network element to request the first token for (or on behalf of) the analysis logic function network element. Alternatively, the first indication information can be used to indicate that the request is for the NRF network element to authorize the analysis logic function network element to obtain the model in the second model training logic function network element. Furthermore, the first indication information can be used to indicate that the token acquisition request is an access token acquisition request (Nnrf_AccessToken_Get request) for a model delegation acquisition scenario.

[0031] In conjunction with the second aspect, in one possible implementation, the aforementioned first token further includes one or more of the following: the aforementioned analysis identifier, the identifier of the first model training logic function network element, the supplier identifier of the analysis logic function network element, or second instruction information. The second instruction information can be used to instruct the authorized analysis logic function network element to obtain the model information corresponding to the aforementioned analysis ID from the second model training logic function network element. Alternatively, the second instruction information can be used to indicate that the authorized first model training logic function network element is (or represents "behalf") authorized to obtain the model information corresponding to the analysis ID from the second model training logic function network element. Furthermore, the second instruction information can be used to indicate that the first token is an authorization token for a model delegation acquisition scenario.

[0032] In conjunction with the second aspect, in one possible implementation, before the NRF network element receives the token acquisition request from the first model training logic function network element, the method further includes: the NRF network element receiving a network element discovery request from the first model training logic function network element, the network element discovery request including the analysis identifier, and the identifier of the analysis logic function network element and / or the vendor identifier of the analysis logic function network element; the NRF network element obtaining the vendor identifier of the analysis logic function network element based on the network element discovery request; the NRF network element determining a candidate network element list based on the stored NF configuration files of each network element; and the NRF network element sending a network element discovery response to the first model training logic function network element, the network element discovery response including the candidate network element list. Wherein, the interoperability indicator corresponding to the aforementioned analysis ID of each model training logic function network element in the candidate network element list includes the vendor identifier of the analysis logic function network element. The second model training logic function network element can be any network element in the candidate network element list, therefore, the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element includes the vendor identifier of the analysis logic function network element.

[0033] For example, the above-mentioned network element discovery request includes the identifier of the analysis logic function network element. The NRF network element obtains the vendor identifier of the analysis logic function network element based on the network element discovery request, including: the NRF network element obtains the vendor identifier of the analysis logic function network element from the NF configuration file corresponding to the identifier of the analysis logic function network element.

[0034] Thirdly, this application provides a model authorization method, which includes: a second model training logic function network element receiving a second model acquisition request from a first model training logic function network element, the second model acquisition request including an analysis identifier, an identifier of the analysis logic function network element, and a first token, the second model acquisition request being used to acquire information about the model corresponding to the analysis identifier for the analysis logic function network element; the second model training logic function network element verifying the first token; and, if the first token is successfully verified, the second model training logic function network element sending a model notification message to the analysis logic function network element, the model notification message including information about the model corresponding to the analysis identifier. The specific verification method of the first token is described in the following method embodiment, and will not be detailed here.

[0035] After receiving a request from the first model training logic function network element (or on behalf of the analysis logic function network element) to acquire a model, the second model training logic function network element verifies the validity of the token. If the token verification is successful, it sends information about the model that meets the requirements to the analysis logic function network element. This improves model acquisition in the model delegation acquisition scenario and verifies the actual model consumer (i.e., the analysis logic function network element) in the model delegation acquisition scenario, thereby enhancing model security.

[0036] In conjunction with the third aspect, in one possible implementation, the aforementioned second model acquisition request further includes one or more of the following: the identifier of the first model training logic function network element, the address of the analysis logic function network element, the vendor identifier of the analysis logic function network element, or third indication information. The address of the analysis logic function network element can be carried by a subscription endpoint address. This subscription endpoint address can be used to represent the address for receiving model notification messages. The third indication information can be used to instruct the first model training logic function network element to acquire (or on behalf of) the analysis logic function network element information corresponding to the aforementioned analysis ID. Alternatively, the third indication information can be used to indicate that the second model acquisition request is an ML model provision request (Nnwdaf_MLModelProvision request) for a model delegation acquisition scenario.

[0037] In conjunction with the third aspect, in one possible implementation, the aforementioned model notification message also includes the identifier of the ADRF network element storing the model.

[0038] In conjunction with the third aspect, in one possible implementation, if the first token verification passes, the second model training logic function network element can add the identifier of the analysis logic function network element to the allowed NF consumer list (allowed NFc list). This allowed NFc list is associated with the model corresponding to the aforementioned analysis ID. Alternatively, this allowed NFc list is a list of network function instance identifiers that are allowed to retrieve / obtain the model corresponding to the aforementioned analysis ID.

[0039] After the first token verification is successful, this application adds the identifier of the analysis logic function network element to the list of allowed NF consumers, which is beneficial for the analysis logic function network element to obtain the model again in the future.

[0040] Fourthly, this application provides a model authorization method, the method comprising: a source analysis logic function network element receiving an analysis context transfer request from a target analysis logic function network element, the analysis context transfer request including an identifier of the analysis context, the analysis context transfer request being used to request the transfer of information of a first model in the analysis context; the source analysis logic function network element sending a token acquisition request to an NRF network element, the token acquisition request including an analysis identifier corresponding to the first model, an identifier of the target analysis logic function network element, and an identifier of a model training logic function network element, the model training logic function network element being used to provide information of the first model; the source analysis logic function network element receiving a first token from the NRF network element, the first token including the identifier of the target analysis logic function network element and the identifier of the model training logic function network element; and the source analysis logic function network element sending a model acquisition request to the model training logic function network element, the model acquisition request including the analysis identifier, the identifier of the target analysis logic function network element, and the first token, the model acquisition request being used to acquire information of the first model for the target analysis logic function network element.

[0041] It is understood that the identifier of the aforementioned analysis context can be a subscription correlation ID. The subscription correlation ID can be used to identify the analysis subscription requesting the relevant analysis context. This analysis context can include model-related information, such as: the identifier of the model producer / provider / trainer (e.g., NWDAF containing MTLF), the model identifier, the model's file address, the model's analysis identifier, etc. It is understood that this analysis context can include the identifiers of multiple model producers / providers / trainers (e.g., NWDAF containing MTLF). For simplicity, this application uses a single model producer / provider / trainer as an example. The aforementioned analysis context transfer request can be used to request the transfer of information about one or more models within the analysis context. For simplicity, this embodiment uses the example of the analysis context transfer request requesting the transfer of information about the first model within the aforementioned analysis context for illustration.

[0042] For example, the first token in the model acquisition request can be used to verify the model acquisition request. Alternatively, the first token in the model acquisition request can be used to verify various identifiers in the model acquisition request. Alternatively, the first token in the model acquisition request can be used to verify the permission of the target analysis logic function network element to acquire the first model from the model training logic function network element. Alternatively, the first token in the model acquisition request can be used to verify the permission of the source analysis logic function network element (or representing "behalf") for the target analysis logic function network element to acquire the first model from the model training logic function network element.

[0043] For example, the source analysis logic function network element can be a network element that has analysis logic function network elements, such as a source NWDAF network element containing AnLF, which can be simply referred to as source AnLF. The target analysis logic function network element can be another network element that has analysis logic function network elements, such as a target NWDAF network element containing AnLF, which can be simply referred to as target AnLF. The model training logic function network element can be a network element that has model training logic function, such as an NWDAF network element containing MTLF, which can be simply referred to as MTLF.

[0044] For example, the token acquisition request described above can be used to request a first token. Alternatively, the token acquisition request can be used to request (NRF network element) authorization for the target analysis logic function network element to obtain the first model from the model training logic function network element. Furthermore, the token acquisition request can be used by the source analysis logic function network element to request a first token for (or on behalf of) the target analysis logic function network element to obtain the first model. The first token can be used to indicate authorization for the target analysis logic function network element to obtain information about the first model from the model training logic function network element. Alternatively, the first token can be used to indicate authorization for the source analysis logic function network element to (or on behalf of) the target analysis logic function network element to obtain information about the first model from the model training logic function network element.

[0045] Upon receiving an analysis context transfer request from a target analysis logic function network element, the source analysis logic function network element of this application requests an authorization token (i.e., the aforementioned first token) from the NRF for (or on behalf of) the target analysis logic function network element. This request includes the identifier of the target analysis logic function network element and the identifier of the model training logic function network element. After obtaining the authorization token, the source analysis logic function network element requests information about the first model from the model training logic function network element for (or on behalf of) the target analysis logic function network element. This request includes the identifier of the target analysis logic function network element and the authorization token. This facilitates model authorization and model acquisition in model delegation acquisition scenarios, and authorizes the actual model consumer (i.e., the target analysis logic function network element) in model delegation acquisition scenarios, thereby improving model security.

[0046] In conjunction with the fourth aspect, in one possible implementation, after receiving the aforementioned analysis context transfer request, the source analysis logic function network element can return analysis context information to the target analysis logic function network element. This analysis context information may include other information besides model-related information from the analysis context transfer request, such as the active data source identifier (ID) and subscription association identifier.

[0047] For example, model-related information includes, but is not limited to: the identifier of the model producer / provider / trainer (such as NWDAF containing MTLF), the model identifier, the model file address, or the analysis identifier corresponding to the model.

[0048] In conjunction with the fourth aspect, in one possible implementation, the aforementioned analysis context transfer request further includes one or more of the following: a second operation indicator for the target analysis logic function network element, or a vendor identifier for the target analysis logic function network element. The second operation indicator can be used to represent the models that the target analysis logic function network element can use and the providers / producers of these models.

[0049] For example, if an operation indicator corresponds to an AnLF, that is, one AnLF corresponds to one operation indicator. The operation indicator may include a list of vendor identifiers (or a vendor list), or be described as a list of NWDAF providers (or vendors). AnLF allows retrieving or using models provided by vendors in the vendor list. The operation indicator also indicates that AnLF supports using models provided by vendors for network elements (e.g., NWDAFs) of vendors in that vendor list. In other words, the operation indicator applies to each analysis identifier.

[0050] For example, if an operation indicator corresponds to an analysis identifier, that is, one AnLF can correspond to one or more operation indicators. Different operation indicators can correspond to different analysis identifiers. Specifically, an operation indicator corresponding to an analysis identifier includes a list of vendor identifiers (or a vendor list), or is described as a list of NWDAF providers (or vendors). AnLF allows retrieving or using models provided by vendors in the vendor list. The operation indicator also indicates that AnLF supports using models provided by vendors for network elements (e.g., NWDAFs) of vendors in the vendor list, and that these models correspond to a specific analysis identifier.

[0051] This application provides a new operation indicator to indicate which vendors' models are supported by the analysis logic function network element, which is beneficial for subsequent verification of whether the actual consumers of the model have the ability or permission to use the specified model.

[0052] In conjunction with the fourth aspect, in one possible implementation, before the source analysis logic function network element sends a token acquisition request to the NRF network element, the method further includes: the source analysis logic function network element determining that the provider of the aforementioned first model is located in the second operation instruction of the target analysis logic function network element. In other words, the source analysis logic function network element can confirm that the target analysis logic function network element has the ability or permission to use the model in the aforementioned analysis context.

[0053] In conjunction with the fourth aspect, in one possible implementation, before the source analysis logic function (NRF) element sends a token acquisition request to the NRF element, the method further includes: the source NRF element determining that the vendor identifier of the target NRF element is included in the interoperability indicator of the information provider (or producer of the first model, such as MTLF) of the first model. In other words, the source NRF element can determine whether the target NRF element can retrieve / acquire the first model.

[0054] In conjunction with the fourth aspect, in one possible implementation, before the source analysis logic function network element receives the analysis context transfer request from the target analysis logic function network element, the method further includes: the source analysis logic function network element sending a network element registration request to the NRF network element, the network element registration request including a first operation indicator of the source analysis logic function network element. The first operation indicator can be used to represent the models that the source analysis logic function network element can use and the providers / producers of these models.

[0055] In this application, the source analysis logic function network element registers its own operation indicator with the NRF network element during the network element registration process, which is beneficial for the subsequent verification of the NRF network element.

[0056] In conjunction with the fourth aspect, in one possible implementation, the aforementioned token acquisition request further includes one or more of the following: the identifier of the source analysis logic function network element, the vendor identifier of the target analysis logic function network element, the identifier of the aforementioned first model, or first indication information. The vendor identifier of the target analysis logic function network element can be used by the NRF network element to verify whether it can be authorized to obtain the aforementioned first model from the model training logic function network element. The first indication information can be used to instruct the source analysis logic function network element to request the first token for (or on behalf of) the target analysis logic function network element. Alternatively, the first indication information can be used to indicate a request for the NRF network element to authorize the target analysis logic function network element to obtain the first model from the model training logic function network element. Furthermore, the first indication information can be used to indicate that the token acquisition request is an access token acquisition request (Nnrf_AccessToken_Get request) for a model delegation acquisition scenario.

[0057] This application includes the vendor identifier of the target analysis logic function network element in the token acquisition request, which helps the NRF network element verify whether the target analysis logic function network element has the authority to obtain the first model from the model training logic function network element. This application also includes first indication information in the token acquisition request, which makes the meaning of the token acquisition request clearer and allows the NRF network element to understand its own behavior.

[0058] In conjunction with the fourth aspect, in one possible implementation, after receiving a token acquisition request from the source analysis logic function network element, the NRF network element can verify whether the vendor identifier of the target analysis logic function network element is included in the interoperability indicator corresponding to the aforementioned analysis identifier of the model training logic function network element. Alternatively, after receiving the token acquisition request, the NRF network element can verify whether the target analysis logic function network element has the authority to obtain the aforementioned first model from the model training logic function network element. If the vendor identifier is included in the interoperability indicator, it indicates that the target analysis logic function network element has the authority to obtain the first model from the model training logic function network element. The NRF network element then sends a first token to the source analysis logic function network element, the first token including the identifier of the target analysis logic function network element and the identifier of the model training logic function network element.

[0059] In conjunction with the fourth aspect, in one possible implementation, the aforementioned first token further includes one or more of the following: the aforementioned analysis identifier, the identifier of the source analysis logic function network element, the supplier identifier of the target analysis logic function network element, the identifier of the aforementioned first model, or second indication information. The second indication information can be used to instruct the authorized target analysis logic function network element to obtain the aforementioned first model information from the model training logic function network element. Alternatively, the second indication information can be used to indicate that the authorized source analysis logic function network element is (or represents behalf) the target analysis logic function network element to obtain the first model information from the model training logic function network element. Furthermore, the second indication information can be used to indicate that the first token is an authorization token for a model delegation acquisition scenario.

[0060] This application includes second instruction information in the first token, which can make the meaning of the first token clearer and help the network elements of the model training logic function to understand the role of the first token.

[0061] In conjunction with the fourth aspect, in one possible implementation, the aforementioned model acquisition request further includes one or more of the following: the identifier of the source analysis logic function network element, the address of the target analysis logic function network element, the identifier of the aforementioned first model, the vendor identifier of the target analysis logic function network element, or third indication information. The address of the target analysis logic function network element can be carried by a subscription endpoint address. This subscription endpoint address can be used to represent the address for receiving model notification messages. The third indication information can be used to instruct the source analysis logic function network element to acquire the aforementioned first model information for (or on behalf of) the target analysis logic function network element. Alternatively, the third indication information can be used to indicate that the model acquisition request is an ML model provision request (Nnwdaf_MLModelProvision request) for a model delegation acquisition scenario.

[0062] This application includes the address of the target analysis logic function network element in the model acquisition request, which helps the model training logic function network element determine the recipient of the model notification message. This application also includes the vendor identifier of the target analysis logic function network element in the model acquisition request, which helps the model training logic function network element verify whether the target analysis logic function network element has the authority to acquire the model from itself. Furthermore, this application includes third-party instruction information in the model acquisition request, which clarifies the meaning of the model acquisition request and enables the model training logic function network element to understand its own behavior.

[0063] In conjunction with the fourth aspect, in one possible implementation, after receiving a model acquisition request, the model training logic function network element can verify the first token in the request. The specific verification method is described in the following method embodiment and will not be detailed here. If the first token is successfully verified, the model training logic function network element can send a model notification message to the target analysis logic function network element. This model notification message may include information about the first model, such as the identifier of the first model, the address of the first model in the model training logic function network element, or the model file of the first model. For example, the model notification message may also include the identifier of the ADRF network element storing the first model.

[0064] Fifthly, this application provides a model licensing method, comprising: an NRF network element receiving a token acquisition request from a source analysis logic function network element, the token acquisition request including an analysis identifier, an identifier of a target analysis logic function network element, and an identifier of a model training logic function network element, the model training logic function network element providing information about a first model corresponding to the analysis identifier; the NRF network element verifying whether the vendor identifier of the target analysis logic function network element is included in an interoperability indicator corresponding to the analysis identifier of the model training logic function network element; if the vendor identifier is included in the interoperability indicator, the NRF network element sending a first token to the source analysis logic function network element, the first token including the identifier of the target analysis logic function network element and the identifier of the model training logic function network element.

[0065] For example, the token acquisition request described above can be used to request a first token. Alternatively, the token acquisition request can be used to request (NRF network element) authorization for the target analysis logic function network element to obtain the first model from the model training logic function network element. Furthermore, the token acquisition request can be used by the source analysis logic function network element to request a first token for (or on behalf of) the target analysis logic function network element to obtain the first model. The first token can be used to indicate authorization for the target analysis logic function network element to obtain information about the first model from the model training logic function network element. Alternatively, the first token can be used to indicate authorization for the source analysis logic function network element to (or on behalf of) the target analysis logic function network element to obtain information about the first model from the model training logic function network element.

[0066] When the NRF element of this application receives a token acquisition request from the source analysis logic function element, which includes the identifier of the target analysis logic function element and the identifier of the model training logic function element, the NRF verifies that the target analysis logic function element has the authority to obtain the first model from the model training logic function element, and then returns the authorization token (i.e. the aforementioned first token) to the source analysis logic function element. This is beneficial for the source analysis logic function element to obtain the model from the model training logic function element for (or on behalf of) the target analysis logic function element, thereby improving the security of the model.

[0067] In conjunction with the fifth aspect, in one possible implementation, before the NRF network element verifies whether the vendor identifier of the target analysis logic function network element is included in the interoperability indicator of the model training logic function network element, the method further includes: the NRF network element obtaining the interoperability indicator corresponding to the analysis identifier of the model training logic function network element from the NF configuration file corresponding to the identifier of the model training logic function network element.

[0068] In conjunction with the fifth aspect, in one possible implementation, before the NRF network element verifies whether the vendor identifier of the target analysis logic function network element is included in the interoperability indicator of the model training logic function network element, the method further includes: the NRF network element obtaining the vendor identifier of the target analysis logic function network element from the NF configuration file corresponding to the identifier of the target analysis logic function network element.

[0069] In conjunction with the fifth aspect, in one possible implementation, the aforementioned token acquisition request further includes one or more of the following: the identifier of the source analysis logic function network element, the vendor identifier of the target analysis logic function network element, the identifier of the aforementioned first model, or first indication information. The vendor identifier of the target analysis logic function network element can be used by the NRF network element to verify whether it can be authorized to obtain the aforementioned first model from the model training logic function network element. The first indication information can be used to instruct the source analysis logic function network element to request the first token for (or on behalf of) the target analysis logic function network element. Alternatively, the first indication information can be used to indicate a request for the NRF network element to authorize the target analysis logic function network element to obtain the first model from the model training logic function network element. Furthermore, the first indication information can be used to indicate that the token acquisition request is an access token acquisition request (Nnrf_AccessToken_Get request) for a model delegation acquisition scenario.

[0070] In conjunction with the fifth aspect, in one possible implementation, the aforementioned first token further includes one or more of the following: the aforementioned analysis identifier, the identifier of the source analysis logic function network element, the supplier identifier of the target analysis logic function network element, the identifier of the aforementioned first model, or second indication information. The second indication information can be used to instruct the authorized target analysis logic function network element to obtain the aforementioned first model information from the model training logic function network element. Alternatively, the second indication information can be used to indicate that the authorized source analysis logic function network element is (or represents behalf) the target analysis logic function network element to obtain the first model information from the model training logic function network element. Furthermore, the second indication information can be used to indicate that the first token is an authorization token for a model delegation acquisition scenario.

[0071] In conjunction with the fifth aspect, in one possible implementation, before the NRF network element receives a token acquisition request from the source analysis logic function network element, the method further includes: the NRF network element receiving a first network element registration request from the source analysis logic function network element, the first network element registration request including a first operation indicator of the source analysis logic function network element. The first operation indicator is used to indicate the models that the source analysis logic function network element can use and the providers / producers of these models.

[0072] In conjunction with the fifth aspect, in one possible implementation, before the NRF network element receives a token acquisition request from the source analysis logic function network element, the method further includes: the NRF network element receiving a second network element registration request from the target analysis logic function network element, the second network element registration request including a second operation indicator of the target analysis logic function network element. The second operation indicator is used to indicate the providers of models that the target analysis logic function network element can use and the providers / producers of these models.

[0073] Sixthly, this application provides a model authorization method, which includes: a model training logic function network element receiving a model acquisition request from a source analysis logic function network element, the model acquisition request including an analysis identifier, an identifier of a target analysis logic function network element, and a first token, the model acquisition request being used to acquire information of a first model corresponding to the analysis identifier for the target analysis logic function network element; the model training logic function network element verifying the first token; and, if the first token is successfully verified, the model training logic function network element sending a model notification message to the target analysis logic function network element, the model notification message including the aforementioned information of the first model. The verification method of the first token is described in the following method embodiment and will not be detailed here.

[0074] After receiving a request from the source analysis logic function network element (or on behalf of the target analysis logic function network element) to obtain the first model, the model training logic function network element in this application verifies the validity of the token. Upon successful token verification, it sends the information of the first model to the target analysis logic function network element. This improves model acquisition in the model delegation acquisition scenario and verifies the actual model consumer (i.e., the target analysis logic function network element) in this scenario, thereby enhancing model security.

[0075] In conjunction with the sixth aspect, in one possible implementation, the aforementioned model acquisition request further includes one or more of the following: the identifier of the source analysis logic function network element, the address of the target analysis logic function network element, the identifier of the aforementioned first model, the vendor identifier of the target analysis logic function network element, or third indication information. The address of the target analysis logic function network element can be carried by a subscription endpoint address. This subscription endpoint address can be used to represent the address for receiving model notification messages. The third indication information can be used to instruct the source analysis logic function network element to acquire the aforementioned first model information for (or on behalf of) the target analysis logic function network element. Alternatively, the third indication information can be used to indicate that the model acquisition request is an ML model provision request (Nnwdaf_MLModelProvision request) for a model delegation acquisition scenario.

[0076] In conjunction with the sixth aspect, in one possible implementation, the aforementioned model notification message also includes the identifier of the ADRF network element storing the first model.

[0077] In conjunction with the sixth aspect, in one possible implementation, upon successful verification of the first token, the model training logic function network element can add the identifier of the target analysis logic function network element to the allowed NF consumer list (allowed NFc list). This allowed NFc list is associated with the first model. Alternatively, the allowed NFc list is a list of network function instance identifiers that are allowed to acquire / retrieve the first model.

[0078] After the first token verification is successful, this application adds the identifier of the target analysis logic function network element to the list of allowed NF consumers, which is beneficial for the target analysis logic function network element to obtain the first model again in the future.

[0079] Seventhly, this application provides a communication device, which may be a first model training logic function network element, a second model training logic function network element, an NRF network element, or a chip therein. The communication device includes units and / or modules for performing the methods provided by any one of the first to third aspects, or any possible implementation thereof, such as transceiver units and / or processing units. The transceiver units are used to transmit and receive various information or signaling, thus also achieving the beneficial effects (or advantages) of the methods provided by any one of the first to third aspects.

[0080] Eighthly, this application provides a communication device, which may be a source analysis logic function network element, a target analysis logic function network element, an NRF network element, or a chip therein. The communication device includes units and / or modules for performing the methods provided by any of the fourth to sixth aspects above, or any possible implementation thereof, such as transceiver units and / or processing units. The transceiver units are used to transmit and receive various information or signaling, thus also achieving the beneficial effects (or advantages) of the methods provided by any of the fourth to sixth aspects above.

[0081] Ninthly, this application provides a communication device including a processor for executing the method shown in any one of the first to third aspects, or any possible implementation thereof. Alternatively, the processor is configured to execute a program stored in a memory, wherein when the program is executed, the method shown in any one of the first to third aspects, or any possible implementation thereof, is executed.

[0082] In conjunction with the ninth aspect, in one possible implementation, the memory is located outside the aforementioned communication device.

[0083] In conjunction with the ninth aspect, in one possible implementation, the memory is located within the aforementioned communication device.

[0084] In this application, the processor and memory can also be integrated into a single device, that is, the processor and memory can be integrated together.

[0085] In conjunction with the ninth aspect, in one possible implementation, the communication device further includes a transceiver for sending or receiving various types of information, such as receiving a first model acquisition request, sending and receiving a token acquisition request, sending and receiving a second model acquisition request, sending and receiving a first token, etc.

[0086] Tenthly, this application provides a communication device including a processor for executing the method shown in any one of the fourth to sixth aspects, or any possible implementation thereof. Alternatively, the processor is configured to execute a program stored in a memory, wherein when the program is executed, the method shown in any one of the first to sixth aspects, or any possible implementation thereof, is executed.

[0087] In conjunction with the tenth aspect, in one possible implementation, the memory is located outside the aforementioned communication device.

[0088] In conjunction with the tenth aspect, in one possible implementation, the memory is located within the aforementioned communication device.

[0089] In this application, the processor and memory can also be integrated into a single device, that is, the processor and memory can be integrated together.

[0090] In conjunction with the tenth aspect, in one possible implementation, the communication device further includes a transceiver for sending or receiving various types of information, such as receiving a context transfer request, a token acquisition request, a model acquisition request, a first token, etc.

[0091] Eleventhly, this application provides a communication device, which may include a processor and an interface circuit connected together. The interface circuit is used for exchanging (or sending / receiving or inputting / outputting) information or data, and the processor is used to execute program instructions, causing the communication device to perform the methods described in any one of the first to sixth aspects above, or any possible implementation thereof. The interface circuit may be a communication interface or a transceiver. The transceiver may be a radio frequency module in the communication device, or a combination of a radio frequency module and an antenna, or an input / output interface of a chip or circuit.

[0092] In a twelfth aspect, this application provides a readable storage medium storing program instructions that, when executed on a communication device, cause the communication device to perform the model licensing method described in any one of the first to sixth aspects above, or any possible implementation thereof.

[0093] In a thirteenth aspect, this application provides a program product containing instructions that, when executed, cause the model licensing method described in any possible implementation of any of the first to sixth aspects above to be executed.

[0094] In a fourteenth aspect, this application provides a communication device, which can be implemented as a chip or as a device, including a processor. The processor is used to read and execute a program stored in a memory to perform one or more of the first to sixth aspects described above, or one or more of the model-licensed methods provided in any possible implementation of any of these aspects. Optionally, the device further includes a memory connected to the processor via a circuit. Further optionally, the device includes a communication interface to which the processor is connected. The communication interface is used to receive information and / or signaling to be processed, the processor obtains the information and / or signaling from the communication interface, processes the information and / or signaling, and outputs the processing result through the communication interface. The communication interface can be an input / output interface.

[0095] Optionally, the processor and memory mentioned above can be physically independent units, or the memory can be integrated with the processor.

[0096] In a fifteenth aspect, this application provides a communication system comprising the aforementioned first model training logic function network element and NRF network element, and optionally including a second model training logic function network element and / or analysis logic function network element.

[0097] In a sixteenth aspect, this application provides a communication system comprising the aforementioned source analysis logic function network element and NRF network element, optionally including a model training logic function network element and / or a target analysis logic function network element.

[0098] The technical effects achieved in the above aspects can be referred to each other or to the beneficial effects in the method embodiments shown below, which will not be repeated here. Attached Figure Description

[0099] Figure 1 This is a schematic diagram of the system architecture provided in the embodiments of this application;

[0100] Figure 2This is a schematic diagram of a secure and authorized AI / ML model sharing process provided in an embodiment of this application;

[0101] Figure 3 This is a flowchart illustrating a model licensing method provided in an embodiment of this application;

[0102] Figure 4 This is another flowchart illustrating the model licensing method provided in this application embodiment;

[0103] Figure 5 This is a schematic diagram of the structure of the communication device provided in an embodiment of this application;

[0104] Figure 6 This is another structural schematic diagram of the communication device provided in the embodiments of this application;

[0105] Figure 7 This is another structural schematic diagram of the communication device provided in the embodiments of this application. Detailed Implementation

[0106] In the description of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or "one or more of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c; a and b; a and c; b and c; or a and b and c. Where a, b, and c can be single or multiple.

[0107] In the description of this application, the terms "first," "second," etc., are used only to distinguish different objects and do not limit the quantity or order of execution, nor do they imply that they are necessarily different. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0108] In this application, the words "exemplary" or "for example" are used to indicate that something is an example, illustration, or illustration. Any embodiment or design described as "exemplary," "for example," or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of the words "exemplary," "for example," or "for example" is intended to present the relevant concepts in a specific manner.

[0109] It should be understood that in this application, "when," "if," and "if" all refer to the device making a corresponding action under certain objective circumstances, and are not time-limited, nor do they require the device to make a judgment when it is implemented, nor do they imply any other limitations.

[0110] In this application, the use of singular designations for elements is intended to represent "one or more" rather than "one and only one," unless otherwise specified.

[0111] In addition, the terms “system” and “network” are often used interchangeably in this article.

[0112] It is understood that in the various embodiments of this application, expressions such as "A corresponds to B" or "A corresponds to / is associated with B" all indicate that there is a correspondence between A and B, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0113] The following is a brief description of the network elements and system architecture involved in this application.

[0114] The network data analytics function (NWDAF) network element supports collecting data from other network functions and application functions (AF) network elements, collecting data from operation administration and maintenance (OAM) network elements, and providing analytical information to other network functions and AF network elements, etc.

[0115] The NWDAF network element has functions such as data collection, model training, data analysis, and model inference. It can collect relevant data from network function elements, third-party service servers, terminal devices, or network management systems, perform data analysis based on this data to obtain analysis results, and provide these results to these network function elements, third-party service servers, terminal devices, or network management systems. These analysis results can assist the network in selecting service quality parameters, performing traffic routing, or selecting background data transmission strategies. Furthermore, the NWDAF network element can also collect relevant data from network function elements, third-party service servers, terminal devices, or network management systems, and perform model training based on this data to obtain artificial intelligence (AI) or machine learning (ML) models. It can then provide these AI / ML models to other NWDAF network elements. These AI / ML models can assist the NWDAF network element in generating data analysis results based on relevant data.

[0116] An NWDAF containing AnLF can be used to perform inference and derive analytics information (i.e., derive statistics and / or predictions based on analytics consumer requests) and expose analytics services. An NWDAF containing MTLF can be used to train machine learning (ML) models and expose new training services; for example, providing trained ML models.

[0117] For ease of description, "NWDAF containing AnLF" can be simply referred to as "AnLF", and in some cases, the two can be used interchangeably; "NWDAF containing MTLF" can be simply referred to as "MTLF", and in some cases, the two can be used interchangeably.

[0118] The analytics data repository functional (ADRF) network element can provide services for storing, deleting, and retrieving AI / ML models. The ADRF network element can also provide data storage and retrieval services, as well as analytics storage and retrieval services. For example, a consumer sends a Nadrf DataManagement Storage Request to the ADRF network element, containing the data or analytics to be stored; or, the consumer sends a Nadrf Data Management Storage Subscription Request to the ADRF network element, requesting the ADRF network element to subscribe to the data or analytics for storage. The ADRF network element then subscribes to an NWDAF network element or a data collection control function (DCCF) network element to obtain the data or analytics. These analyses or data can be provided as notifications using the DCCF Data Management (Ndccf_DataManagement) service, the NWDAF Data Management (Nnwdaf_DataManagement) service, or the messaging framework adapter function (MFAF) Data Management (Nmfaf_3caDataManagement) service.

[0119] Network repository function (NRF) elements can provide registration and discovery functions, enabling network functions (NFs) to discover each other and communicate through application programming interfaces (APIs).

[0120] The technical solutions provided in this application can be applied to various communication systems that deploy virtual network functions. Examples include: 5th generation (5G) communication systems or new radio (NR), Long Term Evolution (LTE) networks equipped with network functions virtualization infrastructure (NFVI) or other virtual network functions, MulteFire networks (creating new wireless networks by independently operating LTE technology on unlicensed spectrum (e.g., global 5GHz unlicensed spectrum), or home base station networks, mobile networks with wireless fidelity (Wi-Fi) access, wideband code division multiple access (WCDMA) networks, fixed-mobile converged networks (fixed access network accessing mobile network), and other future communication systems such as 6th generation mobile communication systems.

[0121] For example, the technical solution provided in this application can be applied to the 5G system architecture defined in 3GPP TS 23.288.

[0122] See Figure 1 , Figure 1 This is a schematic diagram of the system architecture provided in an embodiment of this application. For example... Figure 1As shown, the system architecture 100 includes, but is not limited to: an access network, a core network, a data network (DN) 140, and an application function (AF) 141. The access network can be used to implement functions related to radio access, and it may include a radio access network (RAN) 120 and user equipment (UE) 110. The core network may include, but is not limited to, the following logical functions: User plane function (UPF) 130, Network exposure function (NEF) 131, Network repository function (NRF) 132, Policy control function (PCF) 133, Unified data management (UDM) function 134, Unified data repository (UDR) function 135, Network data analytics function (NWDAF) 136, Authentication server function (AUSF) 137, Access and mobility management function (AMF) 138, or Session management function (SMF) 139, etc. This is understandable. Figure 1 In this context, “Nnef”, “Nnrf”, “Npcf”, “Nudm”, “Nudr”, “Nnwdaf”, “Naf”, “Nausf”, “Namf”, and “Nsmf” represent the names of service interfaces. For details, please refer to the relevant descriptions in the 3GPP standard protocols, which will not be elaborated here.

[0123] Optionally, the UE can access the data network by establishing a session between the UE and the RAN, then to the UPF, and finally to the data network (DN), namely a protocol data unit (PDU) session.

[0124] In this architecture, the UE can be a terminal device, such as a mobile phone, IoT terminal device, smart terminal, vehicle terminal, vehicle equipment, wearable device, multimedia device, streaming media device, etc. The RAN provides wireless access for terminal devices, including but not limited to: 5G base stations (Next-Generation node B, gNB), LTE network radio base stations (evolved Node B, eNodeB or eNB), wireless fidelity access points (Wi-Fi AP), worldwide interoperability for microwave access base stations (WiMAX BS), relay stations, etc. In the 5G RAN architecture, the gNB can include centralized units (CU) and distributed units (DU). The gNB can also include radio units (RU). CU and DU can be understood as a logical functional division of the base station; CU and DU can be physically separated or deployed together. For example, multiple DUs can share a CU, or a DU can connect to multiple CUs. CUs and DUs can be connected via the F1 interface.

[0125] The AMF (Agency Management Function) is primarily responsible for mobility management in mobile networks, such as user location updates, network registration, and user handover. The SMF (Service Management Function) is primarily responsible for session management in mobile networks, such as session establishment, modification, and release. Specific functions include assigning Internet Protocol (IP) addresses to users and selecting the UPF (User Provider Function) to provide packet forwarding. The PCF (Process Management Function) is responsible for providing policies to the AMF and SMF, such as Quality of Service (QoS) policies and slice selection policies. The UDM (User Data Management Function) can be used to store user data, such as subscription information, authentication, or authorization information. The UPF (User Provider Function) is primarily responsible for processing user packets, such as forwarding and accounting.

[0126] Understandable. Figure 1 The various network functions shown can be referenced in relevant protocols or standards, and will not be elaborated upon in this application. It should also be understood that... Figure 1 N1, N2, N3, N4, N6, etc., shown are all interface sequence numbers. For example, the meaning of the above interface sequence numbers can be found in the definitions in the 3GPP standard protocol, and this application does not limit the meaning of the above interface sequence numbers.

[0127] To better understand the technical solutions of the embodiments of this application, the following is a brief introduction to the secure and authorized AI / ML model sharing process between different vendors.

[0128] See Figure 2 , Figure 2 This is a schematic diagram of a secure and authorized AI / ML model sharing process provided in an embodiment of this application. For example... Figure 2 As shown, the secure and authorized AI / ML model sharing process between different vendors includes, but is not limited to:

[0129] Step 0a involves registering the NWDAF containing the MTLF, which means registering the NWDAF containing the MTLF with the NRF. Specifically, the NWDAF containing the MTLF sends an Analytics ID and an Interoperability Indicator to the NRF. The Interoperability Indicator is specifically a Model Interoperability Indicator (e.g., ML Model Interoperability Indicator). The NF Service Producer (NFp), i.e., the NWDAF containing the MTLF, registers its Network Function (NF) profile in the NRF network element using the Interoperability Indicator based on the Analytics ID. The Interoperability Indicator can be used to indicate a list of NWDAF providers (or vendors) that are allowed to retrieve ML models from the NWDAF containing the MTLF.

[0130] Step 0b involves registering the NWDAF containing AnLF, which means registering the NWDAF containing AnLF with the NRF. Specifically, the NWDAF containing AnLF sends its analysis ID and the vendor ID of the AnLF to the NRF.

[0131] Step 0c: Conditionally encrypt the ML model. Unless the AI / ML model generator (NWDAF containing AnLF) and the storage platform (ADRF) are part of the same system and belong to the same vendor and operator's security domain, the model will be stored in an encrypted format.

[0132] Step 1: The NWDAF containing the MTLF sends a model storage request (e.g., Nadrf_MLModelManagement_StorageRequest) to the ADRF. The model storage request includes one or more of the following: the NWDAF containing the MTLF ID, the model ID, the model address in the NWDAF containing the MTLF (e.g., Uniform Resource Locator 1, URL1), and the allowed NFc list. The allowed NFc list indicates the list of Network Function Instance IDs (NF instanceIDs) that are allowed to retrieve / access / query the model.

[0133] Step 2: ADRF sends a response to NWDAF containing MTLF. This response contains the model ID and the model address in ADRF (e.g., URL2).

[0134] Step 3, NWDAF containing MTLF discovery. NF service consumers (NFc), such as NWDAF containing AnLF, send a network element discovery request (e.g., Nnrf_NFDiscovery_Request) to the NRF to select a suitable NF service provider (NFp), such as NWDAF containing MTLF. This network element discovery request includes the analysis ID.

[0135] Step 4a: The NF service consumer (NFc), such as the NWDAF containing AnLF, sends a token acquisition request (e.g., an Nnrf_AccessToken_Get request) to the NRF to request an access token from the NRF. This token acquisition request includes, but is not limited to, the vendor ID and / or analytics ID of the NWDAF containing AnLF.

[0136] Step 4b: The NRF checks whether the NWDAF containing AnLF is authorized to access the requested service in the NWDAF containing MTLF, verifies whether the vendor ID of the NF service consumer (NFc) is included in the NWADF containing the interoperability indicator of the MTLF analysis ID, and grants token 1 based on the vendor ID provided by the NF service consumer (NFc) during registration.

[0137] Step 5: The NF service consumer (NFc) sends a model provisioning request (e.g., Nnwdaf_MLModelProvision request) to the NWDAF containing the MTLF to retrieve the ML model corresponding to the analytics ID. This model provisioning request includes one or more of the following: analytics ID, vendor ID, and token 1.

[0138] Step 6a: The NFp (e.g., NWDAF containing MTLF) authorizes the NFc and stores the NFc ID. The NWDAF containing MTLF authenticates the NF service consumer (NFc) and verifies access token 1, ensuring that access token 1 contains the analytics ID. If authentication is successful, the NWDAF containing MTLF determines the ML model to be shared for the requested analytics ID and stores the NF instance ID of the NWDAF containing AnLF as part of the allowed NFc list corresponding to the ML model.

[0139] Step 6b: If it is determined that the ML model to be shared is stored in the ADRF, and the NF service consumer (NFc) is not yet in the allowed NFc list stored in the ADRF, then the NWDAF containing the MTLF triggers an update at the ADRF by sending a model storage update message (e.g., Nadrf_MLModelManagement_StorageRequest) to the ADRF. This model storage update message contains one or more of the following: the NWDAF containing the MTLF ID, the model ID, or the allowed NFc list. The ADRF then stores the allowed NFc list for the ML model corresponding to the model ID.

[0140] In step 6c, ADRF sends a response to NWDAF containing MTLF, which includes the model ID.

[0141] Step 7: The NWDAF containing the MTLF sends a model provisioning response (e.g., Nnwdaf_MLModelProvision Response) to the NF service consumer (NFc). This response contains the model ID and / or identifies the address of the ML model to be shared. This address can be the address where the ML model is stored in the NWDAF containing the MTLF (i.e., URL1), or it can be the address where the ML model is stored in the ADRF (i.e., URL2). If the model is stored in the ADRF, this message may also contain the ADRF ID.

[0142] Step 8a, the NF service consumer (NFc) requests an access token from the NRF to authorize it to retrieve the model stored in the ADRF.

[0143] Step 8b: The NRF verifies whether the NF service consumer (NFc), such as NWDAF containing AnLF, is authorized to access the model provided by the ADRF. If the verification is successful, the NRF will grant token 2 based on the information provided in the ADRF's NF profile.

[0144] Step 9: The NF service consumer (NFc), such as an NWDAF containing AnLF, retrieves the target model by sending a model retrieval / retrieval request (e.g., Nadrf_MLModelManagement_Retrieval Request). This model retrieval / retrieval request includes the analytics ID and / or token2.

[0145] Step 10: ADRF authenticates the NF service consumer (NFc) and verifies the access token (token2). ADRF also verifies whether the NF service consumer's (NFc) NF ID is included in the ML model's allowed NFc list. If the verification is successful, ADRF sends a model retrieval / get response (e.g., Nadrf_MLModelManagement_Retrieval Response) to the NF service consumer (NFc). This model retrieval / get response contains the address where the model is stored in ADRF.

[0146] Step 11, conditionally decrypt the ML model. The NF service consumer (NFc) retrieves the ML model from the ADRF and decrypts it according to the vendor's implementation.

[0147] It is understood that the full name of "interoperability indicator" in this application is ML Model interoperability indicator, and for the sake of brevity, it is simply referred to as interoperability indicator.

[0148] From the above Figure 2 It can be seen that, Figure 2 The AI / ML model sharing process shown only considers the scenario where NF service consumers directly obtain / retrieve models from model providers (such as NWDAF containing MTLF). However, for model delegation acquisition scenarios, how to authorize consumers is a problem worth considering. Currently, in model delegation acquisition scenarios, model providers or model producers cannot verify whether model consumers have the authority to obtain the requested model.

[0149] In view of this, embodiments of this application provide a model authorization method, apparatus and readable storage medium, which helps to realize model authorization and model acquisition in model delegation acquisition scenarios and improve the security of models in model delegation acquisition scenarios.

[0150] In one possible implementation, the "model delegation acquisition scenario" mentioned in this application can be understood as network element A requesting a model from network element C on behalf of (or on behalf of) network element B. For example, in some scenarios, the first NWDAF network element containing the MTLF may not be able to generate a model that meets the requirements of a consumer (e.g., an NWDAF containing an ANLF), and the consumer cannot directly request the model from the model provider. In this case, the first NWDAF network element containing the MTLF can request the model from the model provider (e.g., a second NWDAF network element containing the MTLF) on behalf of the consumer. Alternatively, if the training of the ML model is triggered by a request from an NWDAF containing an ANLF, and the NWDAF containing the MTLF determines that a federated learning (FL) mechanism is needed, but it cannot act as an FL server, then the NWDAF containing the MTLF can discover the FL server NWDAF and request the FL server NWDAF to provide the ML model for training. The request message sent to the FL server NWDAF provides the NWDAF containing an ANLF subscription endpoint address. The FL server NWDAF can determine to initiate the FL process before providing the ML model. After a successful ML model training, the FL server NWDAF sends the ML model information to a notification endpoint (e.g., an NWDAF containing AnLF). For example, during the analysis of subscription transfers or context transfers, a source NWDAF element containing AnLF can request the transferred model from a model provider (e.g., an NWDAF containing MTLF) for a target NWDAF element containing AnLF.

[0151] The technical solution provided in this application will be described in detail below with reference to more accompanying drawings.

[0152] The technical solutions provided in this application are illustrated through multiple embodiments, with specific reference to the descriptions of the various embodiments below. The same or similar parts between the various embodiments or implementations can be referred to mutually. In the various embodiments of this application, and in the various implementation methods / methods / implementations within each embodiment, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the various implementation methods / methods / implementations within each embodiment are consistent and can be mutually referenced. The technical features in different embodiments and the various implementation methods / methods / implementations within each embodiment can be combined according to their inherent logical relationships to form new embodiments, implementation methods, methods, or implementation approaches. The embodiments described below do not constitute a limitation on the scope of protection of this application.

[0153] In the embodiments of this application, "network element A sends information A to network element B" can be understood as network element B being the destination of information A or an intermediate network element in the transmission path between the destination and network element B, which may include sending information directly or indirectly to network element B. "Network element B receives information A from network element A" can be understood as network element A being the source of information A or an intermediate network element in the transmission path between the source and network element A, which may include receiving information directly or indirectly from network element A. Information may undergo necessary processing, such as format changes, between the source and destination, but the destination can understand the valid information from the source. Similar expressions in this application can be understood in a similar way and will not be elaborated further here.

[0154] It should be understood that in this application, the indication includes direct indication (also known as explicit indication) and implicit indication. Direct indication information A refers to information A being included; implicit indication information A refers to information A being indicated through the correspondence between information A and information B, and through direct indication information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0155] It should be understood that in this application, information D is determined based on information C, which includes both situations where information D is determined solely based on information C and situations where information D is determined based on information C and other information. Furthermore, the use of information C to determine information D can also include indirect determination, such as when information D is determined based on information E, and information E is determined based on information C.

[0156] It can be understood that an NWDAF containing an AnLF can request an NWDAF containing an MTLF to train a model that fulfills a certain function, which can be represented by an "analysis ID". In other words, an NWDAF containing an AnLF can send a model training request to an NWDAF containing an MTLF, and this request includes the analysis ID. The NWDAF containing an MTLF then trains the model corresponding to that analysis ID. Therefore, there is a correspondence between the analysis ID and the model, and this association can be established through the model's functionality.

[0157] The various embodiments will be described in detail below.

[0158] See Figure 3 , Figure 3This is a flowchart illustrating a model licensing method provided in this application. In this method, the first model training logic function network element can be a first network element with model training logic function, such as a first NWDAF network element containing MTLF (NWDAF1 containing MTLF), which can be simply referred to as MTLF1. The second model training logic function network element can be a second network element with model training logic function, such as a second NWDAF network element containing MTLF (NWDAF2 containing MTLF), which can be simply referred to as MTLF2. The analysis logic function network element can be a network element with analysis logic function, such as an NWDAF network element containing AnLF (NWDAF containing AnLF), which can be simply referred to as AnLF. This method mainly describes MTLF1 requesting the model from MTLF2 for AnLF.

[0159] like Figure 3 As shown, the model licensing method includes, but is not limited to, the following steps:

[0160] S101, the analysis logic function network element (such as AnLF) sends a first model acquisition request to the first model training logic function network element (such as MTLF1). The first model acquisition request includes an analysis identifier and is used to request information about the model corresponding to the analysis identifier.

[0161] Correspondingly, the first model training logic function network element (such as MTLF1) receives the first model acquisition request.

[0162] S102, the first model training logic function network element (such as MTLF1) sends a token acquisition request to the NRF network element. The token acquisition request includes one or more of the following: the aforementioned analysis identifier, the identifier of the analysis logic function network element (such as AnLF ID), or the identifier of the second model training logic function network element (such as MTLF2 ID). The second model training logic function network element (such as MTLF2) can be used to train and / or provide information about the model corresponding to the aforementioned analysis identifier.

[0163] Accordingly, the NRF network element receives the token acquisition request.

[0164] In one possible implementation, the first model acquisition request may include, but is not limited to, an analysis identifier (analysis ID), the address (such as a URL or fully qualified domain name (FQDN)) of an analysis logic function network element (such as AnLF), and / or token1. This first model acquisition request can be used to request information about the model corresponding to the analysis ID. For example, the address of the analysis logic function network element (such as AnLF) can be carried by a subscription endpoint address. This subscription endpoint address can be used to represent the address for receiving model notification messages. token1 can be used by the first model training logic function network element (such as MTLF1) to verify the identity of the analysis logic function network element (such as AnLF). If token1 is successfully verified, the first model training logic function network element (such as MTLF1) can determine the model to be shared for the requested analysis ID. The methods for obtaining and using token1 can be referred to the foregoing. Figure 2 The relevant steps are not detailed here.

[0165] In one possible implementation, after receiving the first model acquisition request, the first model training logic function network element (e.g., MTLF1) determines that the second model training logic function network element will produce / train / provide the corresponding model for the analysis logic function network element. Specifically, based on a local strategy, such as discovering that it cannot generate the model corresponding to the analysis ID, the first model training logic function network element decides to find other model training logic function network elements (MTLFs) to provide the model for the analysis logic function network element (e.g., AnLF). For example, the first model training logic function network element (e.g., MTLF1) can obtain a list of candidate network elements from the NRF network elements through a network element discovery process. This list of candidate network elements may include one or more model training logic function network elements (MTLFs). The first model training logic function network element (e.g., MTLF1) can select one model training logic function network element (MTLF) from the list of candidate network elements to provide the model corresponding to the aforementioned analysis ID for the analysis logic function network element (e.g., AnLF). For ease of description, the Model Training Logic Function Network (MTLF) selected from the candidate network element list will be denoted as the Second Model Training Logic Function Network (e.g., MTLF2). In other words, this Second Model Training Logic Function Network (e.g., MTLF2) can generate / train / provide information about the model corresponding to the aforementioned Analysis ID for the Analysis Logic Function Network (e.g., AnLF).

[0166] Furthermore, the first model training logic function network element (such as MTLF1) can send a token acquisition request to the NRF network element. This token acquisition request may include, but is not limited to, the aforementioned analysis ID, the identifier of the analysis logic function network element (such as AnLFID), and / or the identifier of the second model training logic function network element (such as MTLF2 ID). The analysis ID can be the identifier of the analysis service corresponding to the requested authorized model. For example, this token acquisition request can be used to request a first token (token2). Alternatively, this token acquisition request can be used to request (the NRF network element) authorization for the analysis logic function network element (such as AnLF) to obtain the model corresponding to the analysis ID from the second model training logic function network element (such as MTLF2). Or, this token acquisition request can be used for the first model training logic function network element (such as MTLF1) to request a first token for (or on behalf of) the analysis logic function network element (such as AnLF) to obtain the model corresponding to the analysis ID.

[0167] In one possible implementation, the token acquisition request may further include one or more of the following: the identifier of the first model training logic function network element (e.g., MTLF1 ID), the vendor identifier of the analysis logic function network element (e.g., AnLF's Vendor ID), or first indication information. The vendor identifier of the analysis logic function network element (e.g., AnLF's Vendor ID) can be used by the NRF network element to verify whether it can be authorized to obtain the model corresponding to the analysis ID from the second model training logic function network element (e.g., MTLF2). The specific verification method is described below. The first indication information can be used to instruct the first model training logic function network element (e.g., MTLF1) to request the first token for (or on behalf of) the analysis logic function network element (e.g., AnLF). Alternatively, the first indication information can be used to indicate that the NRF network element is requesting authorization for the analysis logic function network element (e.g., AnLF) to obtain the model from the second model training logic function network element (e.g., MTLF2). Or, the first indication information can be used to indicate that the token acquisition request is an access token acquisition request (Nnrf_AccessToken_Get request) for a model delegation acquisition scenario.

[0168] It is understood that the model in this application can be either an ML model or an AI model, without any restrictions.

[0169] It is understood that the IDs of the various network elements mentioned in this application can be Network Function Instance IDs (NF instanceIDs), which will not be elaborated further below. The NF instance ID can be used to uniquely identify a Network Function Instance (NFInstance ID: Unique identity of the NF Instance).

[0170] In one possible implementation, before step S101, the model authorization method further includes: the analysis logic function network element (e.g., AnLF), the first model training logic function network element (e.g., MTLF1), and the second model training logic function network element (e.g., MTLF2) can each send a registration request message to the NRF network element. For example, the first model training logic function network element (e.g., MTLF1) and the second model training logic function network element (e.g., MTLF2) register their respective analysis IDs and interoperability indicators with the NRF network element; the specific registration process can be found in the foregoing. Figure 2 Step 0a is shown and will not be repeated here. The analysis logic function network element (such as AnLF) registers its own analysis ID and vendor ID with the NRF network element. The specific registration process can be found in the previous section. Figure 2 Step 0b is shown and will not be repeated here. The interoperability indicator can be used to represent a list of NWDAF providers (or vendors) that allow ML models to be retrieved from NWDAF containing MTLF.

[0171] In one possible implementation, the method by which the first model training logic function network element (such as MTLF1) obtains the candidate network element list may include: the first model training logic function network element (such as MTLF1) sends a network element discovery request to the NRF network element. This network element discovery request includes one or more of the following: the aforementioned analysis ID, the identifier of the analysis logic function network element (such as AnLFID), and / or the vendor identifier of the analysis logic function network element (such as AnLF's Vendor ID). Upon receiving the network element discovery request, the NRF network element can obtain the vendor identifier of the analysis logic function network element (such as AnLF's Vendor ID) based on the network element discovery request, and then determine the candidate network element list based on the NF configuration files of each network element stored locally. For example, if the network element discovery request includes the identifier of the analysis logic function network element (such as AnLF ID), the NRF network element can determine the NF configuration file 1 corresponding to the identifier of the analysis logic function network element (such as AnLF ID) from multiple NF configuration files stored locally, and then obtain the vendor identifier of the analysis logic function network element (such as AnLF's Vendor ID) from NF configuration file 1. It is understandable that if the network element discovery request includes the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF), the NRF network element can obtain the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF) from the network element discovery request without having to search the locally stored NF configuration file. After obtaining the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF), the NRF network element can then determine the NF configuration files of the model producers (i.e., NWDAF containing MTLF) in the multiple locally stored model producers (i.e., NWDAF containing MTLF) whose interoperability indicators corresponding to the aforementioned analysis ID contain the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF). These model producers (i.e., NWDAF containing MTLF) constitute the candidate network element list. In other words, the interoperability indicators corresponding to the aforementioned analysis ID of each model training logic function network element (such as MTLF) in the candidate network element list include the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF). NRF elements can send element discovery responses to the first model training logic function element (such as MTLF1), which include a list of candidate elements.

[0172] S103, whether the vendor identifier (such as the Vendor ID of AnLF) of the NRF network element verification analysis logic function network element is included in the interoperability indicator corresponding to the above analysis identifier of the second model training logic function network element (such as MTLF2).

[0173] S104, if the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF) is in the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element (such as MTLF2), the NRF network element sends a first token to the first model training logic function network element (such as MTLF1), the first token including one or more of the following: the identifier of the analysis logic function network element (such as AnLF ID), or the identifier of the second model training logic function network element (such as MTLF2 ID).

[0174] Correspondingly, the first model training logic function network element (such as MTLF1) receives the first token.

[0175] In one possible implementation, after receiving the token acquisition request, the NRF network element can verify whether the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF) is included in the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element (such as MTLF2). Alternatively, after receiving the token acquisition request, the NRF network element can verify whether the analysis logic function network element (such as AnLF) has permission to obtain the model from the second model training logic function network element (such as MTLF2). For example, the token acquisition request may include one or more of the following: analysis ID, the identifier of the analysis logic function network element (such as AnLF ID), or the identifier of the second model training logic function network element (such as MTLF2 ID). The NRF network element can determine the NF configuration file 1 corresponding to the identifier of the analysis logic function network element (such as AnLF ID) from multiple locally stored NF configuration files, and can obtain the vendor identifier (such as the Vendor ID of AnLF) of the analysis logic function network element from NF configuration file 1. It is understood that when the aforementioned token acquisition request includes the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF), the NRF network element can obtain the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF) from the token acquisition request without having to search the locally stored NF configuration file. The NRF network element can then determine the NF configuration file 2 corresponding to the identifier of the second model training logic function network element (such as the MTLF2 ID) from multiple locally stored NF configuration files, and can obtain the interoperability indicator corresponding to the aforementioned analysis ID (the analysis ID carried in the token acquisition request) from NF configuration file 2.

[0176] Then, the NRF element can verify whether the interoperability indicator corresponding to the analytics ID contains the vendor identifier of the analytics logic function element (such as the Vendor ID of AnLF). If the interoperability indicator corresponding to the analytics ID in NF configuration file 2 contains the vendor identifier of the analytics logic function element (such as the Vendor ID of AnLF), it indicates that the analytics logic function element (such as AnLF) has the authority to obtain the model from the second model training logic function element (such as MTLF2). The NRF element can then generate an authorization token for the model (i.e., the first token, token2) and send the first token (token2) to the first model training logic function element (such as MTLF1). The first token (token2) may include some or all of the content in the token acquisition request mentioned above. For example, the first token may include, but is not limited to, one or more of the following: the analytics ID, the identifier of the analytics logic function element (such as the AnLF ID), or the identifier of the second model training logic function element (such as the MTLF2 ID). The first token can be used to indicate that an authorized analytics logic function element (such as AnLF) is authorized to obtain information about the model corresponding to the analytics ID from a second model training logic function element (such as MTLF2). Alternatively, the first token can be used to indicate that an authorized first model training logic function element (such as MTLF1) is authorized (or represents half) for an analytics logic function element (such as AnLF) to obtain information about the model corresponding to the analytics ID from a second model training logic function element (such as MTLF2). It can be understood that the authorization information of an NRF element is specific to each analytics ID, or in other words, the aforementioned first token uniquely corresponds to the analytics ID in the aforementioned token acquisition request. For different analytics IDs, NRF elements can have different authorization information, such as tokens, and the tokens and analytics IDs can correspond one-to-one.

[0177] In one possible implementation, if the aforementioned token acquisition request also includes the identifier of the first model training logic function network element (e.g., MTLF1 ID) and the vendor identifier of the analysis logic function network element (e.g., AnLF's Vendor ID), then the first token (token2) may also include the identifier of the first model training logic function network element (e.g., MTLF1 ID) and the vendor identifier of the analysis logic function network element (e.g., AnLF's Vendor ID). For example, the first token may also include second indication information. This second indication information can be used to instruct the authorized analysis logic function network element (e.g., AnLF) to obtain the model information corresponding to the aforementioned analysis ID from the second model training logic function network element (e.g., MTLF2). Alternatively, the second indication information can be used to indicate that the authorized first model training logic function network element (e.g., MTLF1) is (or represents behalf) to allow the analysis logic function network element (e.g., AnLF) to obtain the model information corresponding to the analysis ID from the second model training logic function network element (e.g., MTLF2). Furthermore, the second indication information can be used to indicate that the first token is an authorization token for a model delegation acquisition scenario.

[0178] In one possible implementation, if the interoperability indicator corresponding to the analysis ID in NF configuration file 2 does not contain the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF), it indicates that the analysis logic function network element (such as AnLF) does not have permission to obtain the model from the second model training logic function network element (such as MTLF2). The NRF network element can send a response message to the first model training logic function network element (such as MTLF1) to reject the aforementioned token acquisition request. This response message can carry the reason for rejection, such as the analysis logic function network element (such as AnLF) being unable to obtain the model from the second model training logic function network element (such as MTLF2), or the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF) not being included in the interoperability indicator of the second model training logic function network element (such as MTLF2), etc.

[0179] In one possible implementation, if the token acquisition request includes the first indication information, after receiving the token acquisition request, the NRF network element can determine, based on the first indication information, that the token acquisition request is a request from the first model training logic function network element (e.g., MTLF1) to authorize the NRF network element to authorize the analysis logic function network element (e.g., AnLF) to acquire the model of the second model training logic function network element (e.g., MTLF2). Then, the verification in step S103 above is performed.

[0180] S105, the first model training logic function network element (e.g., MTLF1) sends a second model acquisition request to the second model training logic function network element (e.g., MTLF2). The second model acquisition request includes one or more of the following: the aforementioned analysis identifier, the identifier of the analysis logic function network element (e.g., AnLF ID), or the aforementioned first token. This second model acquisition request is used to obtain information about the model corresponding to the analysis identifier for the analysis logic function network element (e.g., AnLF). The first token can be used to verify the second model acquisition request.

[0181] Correspondingly, the second model training logic function network element (such as MTLF2) receives the second model acquisition request.

[0182] S106, The second model training logic function network element (such as MTLF2) verifies the first token mentioned above.

[0183] S107, if the first token verification is successful, the second model training logic function network element (such as MTLF2) sends a model notification message to the analysis logic function network element (such as AnLF), which includes information about the model corresponding to the analysis identifier.

[0184] Correspondingly, the analysis logic function network element (such as AnLF) receives the model notification message.

[0185] In one possible implementation, after receiving the first token (token2), the first model training logic function network element (such as MTLF1) can send a second model acquisition request to the second model training logic function network element (such as MTLF2). This second model acquisition request can be used to obtain information about the model corresponding to the aforementioned analysis ID for the analysis logic function network element (such as AnLF). The second model acquisition request may include, but is not limited to, one or more of the following: the aforementioned analysis ID (here, the analysis ID carried in the command token acquisition request, which is also the analysis ID carried in the first model acquisition request), the identifier of the analysis logic function network element (such as the AnLF ID), or the first token (token2). The first token can be used to verify the second model acquisition request, or it can be used to verify various identifiers in the second model acquisition request. Alternatively, the first token can be used to verify the permission of the analysis logic function network element (such as AnLF) to obtain a model (which can be the model corresponding to the aforementioned analysis ID) from the second model training logic function network element (such as MTLF2). Alternatively, the first token can be used to verify the permission of the first model training logic function element (such as MTLF1) to (or represent the behavior) the analysis logic function element (such as AnLF) to obtain the model (which can be the model corresponding to the above analysis ID) from the second model training logic function element (such as MTLF2).

[0186] In one possible implementation, after receiving the second model acquisition request, the second model training logic function network element (such as MTLF2) can verify the aforementioned first token (token2). For example, the second model training logic function network element (such as MTLF2) can verify whether the analysis ID in the second model acquisition request is consistent (or identical, matched) with the analysis ID in the first token (token2), and whether the identifier of the analysis logic function network element in the second model acquisition request (such as AnLF ID) is consistent (or identical, matched) with the identifier of the analysis logic function network element in the first token (token2). If both are consistent (or identical), it can be concluded that the first token (token2) has passed verification. Here, "matching" can be interpreted as: the analysis ID(s) in the second model acquisition request is located within the analysis ID(s) contained in the first token.

[0187] In one possible implementation, the second model acquisition request may further include one or more of the following: the identifier of the first model training logic function network element (e.g., MTLF1 ID), the address (e.g., URL or FQDN) of the analysis logic function network element (e.g., AnLF's Vendor ID), or third indication information. For example, the address of the analysis logic function network element (e.g., AnLF) may be carried by a subscription endpoint address. This subscription endpoint address may be used to represent the address for receiving model notification messages. The third indication information may be used to instruct the first model training logic function network element (e.g., MTLF1) to acquire information about the model corresponding to the aforementioned analysis ID for (or on behalf of) the analysis logic function network element (e.g., AnLF). Alternatively, the third indication information may be used to indicate that the second model acquisition request is an ML model provision request (Nnwdaf_MLModelProvision request) for a model delegation acquisition scenario.

[0188] Correspondingly, after receiving the second model acquisition request, when verifying the first token, the second model training logic function network element (such as MTLF2) may verify, in addition to verifying whether the analysis ID and the identifier of the analysis logic function network element (such as AnLF ID) in the second model acquisition request are consistent (or the same) with the analysis ID and the identifier of the analysis logic function network element (such as AnLF ID) in the first token (token2), one or more of the following may also be verified: whether the identifier of the first model training logic function network element (such as MTLF1 ID) in the second model acquisition request is consistent (or the same) with the identifier of the first model training logic function network element (such as MTLF1 ID) in the first token (token2); and whether the vendor identifier of the analysis logic function network element in the second model acquisition request (such as the Vendor ID of AnLF) is consistent (or the same) with the vendor identifier of the analysis logic function network element (such as the Vendor ID of AnLF) in the first token (token2). The second model training logic function element (such as MTLF2) can also verify whether the vendor identifier (such as the Vendor ID of AnLF) of the analysis logic function element in the second model acquisition request is included in the interoperability indicator corresponding to the analysis ID of the second model training logic function element (such as MTLF2). If all are consistent (or identical), and the vendor identifier (such as the Vendor ID of AnLF) of the analysis logic function element is included in the interoperability indicator corresponding to the analysis ID of the second model training logic function element (such as MTLF2), it can be concluded that the first token (token2) has been verified successfully.

[0189] In one possible implementation, after the first token verification is successful, the second model training logic function network element (such as MTLF2) can send a model notification message to the analysis logic function network element (such as AnLF). It is understood that the second model training logic function network element (such as MTLF2) can send the model notification message to the analysis logic function network element (such as AnLF) directly or through an intermediate network element; this embodiment does not impose any restrictions. For example, the second model training logic function network element (such as MTLF2) can send the model notification message to the analysis logic function network element (such as AnLF) through the first model training logic function network element (such as MTLF1). For instance, the second model training logic function network element (such as MTLF2) sends the model notification message to the first model training logic function network element (such as MTLF1), and the first model training logic function network element (such as MTLF1) can then forward it to the analysis logic function network element (such as AnLF). This forwarding can be a transparent transmission or processing of the model notification message before forwarding; this embodiment does not impose any restrictions. However, the model notification message received by the analysis logic function network element (such as AnLF) may include information about the model corresponding to the analysis ID. For example, the model notification message may also include the identifier (such as ADRFID) of the ADRF network element storing the model. After receiving the model notification message, the analysis logic function network element (such as AnLF) can obtain (or download) the model file of the model based on the model notification message and save it locally.

[0190] In this application, "model information" may include, but is not limited to, one or more of the following: model identifier (model ID), the address of the model in the second model training logic function network element (such as MTLF2), or model file, etc.

[0191] The model ID mentioned in this application can be used to uniquely identify a model (ML Model identifier: uniqueML Model identifier). The address of the model in the second model training logical function network (such as MTLF2) can be used by the analysis logical function network (such as AnLF) to obtain (e.g., download) the model file from the second model training logical function network (such as MTLF2) based on the address and store it locally.

[0192] In one possible implementation, after the first token verification passes, the second model training logic function network element (such as MTLF2) can also add the identifier of the analysis logic function network element (such as AnLF ID) to the allowed NF consumer list. This allowed NFc list is associated with the model corresponding to the analysis ID. Alternatively, the allowed NFc list is a list of network function instance identifiers that allow access to / retrieval of the model corresponding to the analysis ID. For example, the second model training logic function network element (such as MTLF2) can store the identifier of the analysis logic function network element (such as AnLFID) as part of the model's allowed NFc list and can send a Nadrf_MLModelManagement_StorageRequest (Nadrf Machine Learning Model Management Storage Request) to the ADRF network element to trigger an update at the ADRF network element. The Nadrf_MLModelManagement_StorageRequest can contain the identifier of the second model training logic function network element (such as MTLF2 ID), the model ID, and the allowed NFc list.

[0193] In the embodiments of this application, the "allowed NF consumer list" can be understood as a list of network function instance IDs (NF instance IDs) that are allowed to obtain / retrieve / access / query the model. The "allowed NF consumer list" can also be called the "allowed NF instance ID list," or the "allowed network function list," etc., and this application does not impose any restrictions.

[0194] In this embodiment of the application, after receiving a model acquisition request from AnLF, MTLF1, based on its internal policy, discovers that it cannot provide a model that meets the requirements. MTLF1 can request a model that meets the requirements from other MTLFs (such as MTLF2) on behalf of (or on behalf of) AnLF. For example, MTLF1 first requests an authorization token (i.e., the first token mentioned above) from the NRF on behalf of (or on behalf of) AnLF. This request includes AnLF ID and MTLF2 ID. After verifying that AnLF has the right to acquire the model from MTLF2, the NRF returns the authorization token (i.e., the first token mentioned above) to MTLF1. After obtaining the authorization token, MTLF1 requests information about the model that meets the requirements from MTLF2 on behalf of (or on behalf of) AnLF. This request includes AnLF ID and the authorization token. After MTLF2 verifies that the authorization token is valid, it sends the information about the model that meets the requirements to AnLF. Through the above process, it is helpful to realize model authorization and model acquisition in the model delegation acquisition scenario, and to authorize the actual model consumer (i.e., AnLF) in the model delegation acquisition scenario, thereby improving the security of the model.

[0195] See Figure 4 , Figure 4 This is another flowchart illustrating the model licensing method provided in this application. In this method, the source analysis logic function network element can be a network element with analysis logic function elements, such as a source NWDAF network element containing AnLF, which can be simply referred to as the source AnLF. The target analysis logic function network element can be another network element with analysis logic function elements, such as a target NWDAF network element containing AnLF, which can be simply referred to as the target AnLF. The model training logic function network element can be a network element with model training logic function, such as an NWDAF network element containing MTLF, which can be simply referred to as the MTLF. This method mainly describes how, during the analysis subscription transfer or analysis context transfer process, the source AnLF requests the model in the analysis context from the MTLF for the target AnLF.

[0196] like Figure 4 As shown, the model licensing method includes, but is not limited to, the following steps:

[0197] S201, the target analysis logic function network element (such as Target AnLF) sends an analysis context transfer request to the source analysis logic function network element (such as SourceAnLF). The analysis context transfer request includes the identifier of the analysis context and is used to request the transfer of information of the first model in the analysis context.

[0198] Correspondingly, the source analysis logic function network element (such as Source AnLF) receives the analysis context transfer request.

[0199] In one possible implementation, before step S201, the model authorization method further includes: the source analysis logic function network element (e.g., Source AnLF) and the target analysis logic function network element (e.g., Target AnLF) can each send a registration request message to the NRF network element. For example, the source analysis logic function network element (e.g., Source AnLF) can send registration request message 1 to the NRF network element. Registration request message 1 includes the analysis ID and vendor ID of the source analysis logic function network element (e.g., Source AnLF), and optionally also includes a first operation indicator of the source analysis logic function network element (e.g., Source AnLF). The NRF network element can store the information contained in registration request message 1 in the NF configuration file of the source analysis logic function network element (e.g., Source AnLF). Again, for example, the target analysis logic function network element (e.g., Target AnLF) can send registration request message 2 to the NRF network element. Registration request message 2 includes the analysis ID and vendor ID of the target analysis logic function network element (e.g., Target AnLF), and optionally also includes a second operation indicator of the target analysis logic function network element (e.g., Target AnLF). The NRF network element can store the information contained in the registration request message 2 in the NF configuration file of the target analysis logic function network element (such as Target AnLF). The first operation indicator and the second operation indicator can be a new type of operation indicator provided in this application embodiment. For example, the first operation indicator can be used to indicate the model that the source analysis logic function network element (such as Source AnLF) can use, and the second operation indicator can be used to indicate the model that the target analysis logic function network element (such as Target AnLF) can use.

[0200] The operation indicators provided in the embodiments of this application will be described below.

[0201] For example, operation indicators can correspond to analysis logic function network elements (such as AnLF), that is, the operation indicator is at the AnLF granularity. Alternatively, operation indicators can correspond to analysis identifiers, that is, the operation indicator is at the analysis identifier granularity.

[0202] In one possible implementation, the operation indicator corresponds to an AnLF, meaning one AnLF corresponds to one operation indicator. The operation indicator may include a list of vendor identifiers (or a vendor list), or be described as a list of NWDAF providers (or vendors). AnLF allows retrieving or using models provided by vendors in the vendor list. The operation indicator also indicates that AnLF supports using models provided by vendors for network elements (e.g., NWDAFs) of vendors in that vendor list. In other words, the operation indicator applies to each analysis identifier.

[0203] For example, the operation indicator includes the identifiers of vendor 1 and vendor 2. That is, AnLF can use the model provided by vendor 1 and the model provided by vendor 2. Or, it can be understood that if the vendor of MTLF1 is vendor 1 or vendor 2, then AnLF can use the model trained by MTLF1. For example, assuming that the model provided by vendor 1 includes a model corresponding to analysis identifier 1 and a model corresponding to analysis identifier 2, then AnLF can use both models.

[0204] It can be understood that the model provided by vendor 1 can be understood as a model produced (or trained) by vendor 1, or a model produced (or trained) by MTLF, and the vendor of the MTLF is vendor 1.

[0205] In another possible implementation, if the operation indicator corresponds to the analysis identifier, that is, one AnLF can correspond to one or more operation indicators. Different operation indicators can correspond to different analysis identifiers. The operation indicator corresponding to an analysis identifier includes a list of vendor identifiers (or a vendor list), or is described as a list of NWDAF providers (or vendors). AnLF allows retrieving or using models provided by vendors in the vendor list. The operation indicator also indicates that AnLF supports using models provided by vendors for network elements (e.g., NWDAFs) of vendors in the vendor list, and that these models correspond to a specific analysis identifier.

[0206] For example, suppose AnLF's operation indicators include operation indicator 'a' corresponding to analysis identifier 1 and operation indicator 'b' corresponding to analysis identifier 2. Operation indicator 'a' corresponding to analysis identifier 1 includes the identifiers of vendor 1 and vendor 2, meaning AnLF can use models provided by vendor 1 and vendor 2, and these models correspond to analysis identifier 1. For instance, suppose vendor 1 provides models corresponding to analysis identifier 1 and analysis identifier 2, then AnLF can use the model corresponding to analysis identifier 1 but cannot use the model corresponding to analysis identifier 2. Similarly, operation indicator 'b' corresponding to analysis identifier 2 includes the identifier of vendor 4, meaning AnLF can use models provided by vendor 4, and these models correspond to analysis identifier 2. For instance, suppose vendor 4 provides models corresponding to analysis identifier 1 and analysis identifier 2, then AnLF can use the model corresponding to analysis identifier 2 but cannot use the model corresponding to analysis identifier 1.

[0207] Therefore, the aforementioned first operation indicator may include a list of vendor identifiers (or a vendor list). This first operation indicator may indicate that the source analysis logic function network element (such as Source AnLF) supports using a model provided by a vendor in the vendor list. Alternatively, this first operation indicator may indicate that the source analysis logic function network element (such as Source AnLF) supports using a model provided by a vendor in the vendor list corresponding to a specific analysis identifier. In other words, the first operation indicator can be used to indicate which models provided by which model manufacturers the source analysis logic function network element (e.g., Source AnLF) supports. Alternatively, the first operation indicator can be used to indicate which models provided by which model manufacturers the source analysis logic function network element (e.g., Source AnLF) supports. Similarly, the second operation indicator can also include a list of vendor identifiers (or a vendor list). This second operation indicator can indicate that the target analysis logic function network element (e.g., Target AnLF) supports models provided by vendors in the vendor list. Alternatively, this second operation indicator can indicate that the target analysis logic function network element (e.g., Target AnLF) supports models provided by vendors in the vendor list that correspond to a specific analysis identifier. In other words, the second operation indicator can be used to indicate which models provided by which model manufacturers the target analysis logic function network element (e.g., Target AnLF) supports. Alternatively, the second operation indicator can be used to indicate which models provided by which model manufacturers the target analysis logic function network element (e.g., Target AnLF) supports.

[0208] In one possible implementation, a target analytics logic function network element (such as a Target AnLF) can send an analytics context transfer request to a source analytics logic function network element (such as a Source AnLF). This analytics context transfer request may include, but is not limited to, an identifier for the analytics context, such as a Subscription Correlation ID. The Subscription Correlation ID can be used to identify the analytics subscription for which the related analytics context is requested. This analytics context may include model-related information, such as the identifier of the model producer / provider / trainer (e.g., an NWDAF containing an MTLF), the model identifier, the model's file address, or the analytics identifier corresponding to the model. It is understood that this analytics context may include the identifiers of multiple model producers / providers / trainers (e.g., an NWDAF containing an MTLF). For simplicity, this embodiment uses a single model producer / provider / trainer as an example. The aforementioned analytics context transfer request can be used to request the transfer of information for one or more models within the analytics context. For simplicity, this embodiment uses an example of the analytics context transfer request requesting the transfer of information for the first model within the aforementioned analytics context.

[0209] In one possible implementation, after receiving the aforementioned analysis context transfer request, the source analysis logic function network element (such as Source AnLF) can return analysis context information to the target analysis logic function network element (such as Target AnLF). This analysis context information may include other information besides model-related information from the analysis context transfer request, such as the active data source identifier (ID) and subscription association identifier.

[0210] In one possible implementation, the aforementioned analysis context transfer request may further include one or more of the following: a second operation indicator of the target analysis logic function network element (such as Target AnLF), or a vendor identifier of the target analysis logic function network element (such as the Vendor ID of Target AnLF). For a description of the second operation indicator, please refer to the preceding description; it will not be repeated here.

[0211] In one possible implementation, if the aforementioned analysis context transfer request includes a second operation indicator, after receiving the analysis context transfer request, the source analysis logic function network element (such as Source AnLF) can determine whether the second operation indicator of the target analysis logic function network element (such as Target AnLF) belongs to the first operation indicator of the source analysis logic function network element (such as Source AnLF). In other words, the source analysis logic function network element (such as Source AnLF) can confirm whether the target analysis logic function network element (such as Target AnLF) has the ability or permission to use the model in the aforementioned analysis context. For example, the source analysis logic function network element (such as Source AnLF) can determine whether the provider / producer of the aforementioned first model is located in the second operation indicator. If the provider / producer of the aforementioned first model is located in the second operation indicator, it indicates that the target analysis logic function network element (such as Target AnLF) can use the first model in the aforementioned analysis context. The source analysis logic function network element (such as Source AnLF) can then return analysis context information to the target analysis logic function network element (such as Target AnLF). For an explanation of the analysis context information, please refer to the preceding description; it will not be repeated here.

[0212] In another possible implementation, if the aforementioned analysis context transfer request includes the vendor identifier of the target analysis logic function network element (e.g., the Vendor ID of Target AnLF), the source analysis logic function network element (e.g., Source AnLF), upon receiving the request, can determine whether the vendor identifier of the target analysis logic function network element (e.g., the Vendor ID of Target AnLF) is included in the interoperability indicator of the information provider of the first model (e.g., MTLF). If the vendor identifier of the target analysis logic function network element (e.g., the Vendor ID of Target AnLF) is included in the interoperability indicator of the information provider of the first model, it indicates that the target analysis logic function network element (e.g., Target AnLF) can acquire / retrieve / query the first model. It can be understood that the information provider of the first model can be either the producer of the first model or not the producer but merely the provider of the first model (it does not produce the first model). The source analysis logic function network element (e.g., Source AnLF) can then return analysis context information to the target analysis logic function network element (e.g., Target AnLF). For an explanation of the analysis context information, please refer to the preceding description; it will not be repeated here. It's understandable that interoperability indicators can be per Analytics ID, meaning one interoperability indicator corresponds to one analytics ID, with a one-to-one correspondence. Different analytics IDs can have different interoperability indicators. Similarly, interoperability indicators can also be per Model Producer LF (MTLF), meaning one interoperability indicator corresponds to one model producer LF, with a one-to-one correspondence. Different model producers LFs can have different interoperability indicators.

[0213] In one possible implementation, before step S201 (and after the network element registration process), the model authorization method further includes: the NWDAF service consumer sending an analysis subscription service request to the source analysis logic function network element (such as SourceAnLF), carrying the analysis ID. Upon receiving the analysis subscription service request, the source analysis logic function network element (such as SourceAnLF) can subscribe to the model associated with the analysis ID from the model training logic function network element (such as MTLF). The model training logic function network element (such as MTLF) returns a corresponding response message, carrying subscription association identifier 1. Optionally, the model training logic function network element (such as MTLF) can send the model ID associated with the analysis ID to the source analysis logic function network element (such as SourceAnLF), and the source analysis logic function network element (such as SourceAnLF) can obtain the model identified by the model ID through the model ID. The source analysis logic function network element (such as SourceAnLF) sends an analysis subscription service response to the NWDAF service consumer, containing subscription association identifier 2 (i.e., the identifier of the analysis context mentioned above). The NWDAF service consumer decides to initiate an analysis context transfer process and identifies a target analysis logic function network element (such as Target AnLF). The NWDAF service consumer sends an analysis subscription request to the target analysis logic function network element (such as Target AnLF), including subscription association identifier 2 (i.e., the identifier of the aforementioned analysis context). After receiving the analysis subscription request, the target analysis logic function network element (such as Target AnLF) can execute step S201.

[0214] S202, the source analysis logic function network element (such as Source AnLF) sends a token acquisition request to the NRF network element. The token acquisition request includes one or more of the following: the analysis identifier corresponding to the first model, the identifier of the target analysis logic function network element (such as Target AnLF ID), or the identifier of the model training logic function network element (such as MTLF ID). Among them, the model training logic function network element (such as MTLF) can be used to train and / or provide information about the first model.

[0215] Accordingly, the NRF network element receives the token acquisition request.

[0216] In one possible implementation, after receiving the aforementioned analysis context transfer request, the source analysis logic function network element (such as Source AnLF) determines a model training logic function network element (such as MTLF) to produce / train / provide the first model for the target analysis logic function network element (such as Target AnLF ID). In other words, the producer / trainer / provider of the first model is this model training logic function network element. The source analysis logic function network element (such as Source AnLF) can send a token acquisition request to the NRF network element. This token acquisition request includes one or more of the following: the analysis identifier corresponding to the aforementioned first model, the identifier of the target analysis logic function network element (such as Target AnLF ID), or the identifier of this model training logic function network element (such as MTLF ID). The analysis ID can be the identifier of the analysis service corresponding to the first model for which authorization is requested. The role of the token acquisition request can be referred to the foregoing. Figure 3 The relevant descriptions in the illustrated embodiments.

[0217] It is understood that the target analysis logic function network element (such as Target AnLF) in the embodiments of this application can be compared with the aforementioned Figure 3 The analysis logic function network element (such as AnLF) in the illustrated embodiment and the source analysis logic function network element (such as Source AnLF) in the embodiments of this application can be compared with the aforementioned Figure 3 The first model training logic function network element (such as MTLF1) in the illustrated embodiment. The model training logic function network element (such as MTLF) in the embodiments of this application can be compared with the aforementioned Figure 3 The second model training logic function network element (such as MTLF2) in the illustrated embodiment will not be described in detail below.

[0218] In one possible implementation, the token acquisition request may further include one or more of the following: the identifier of the source analysis logic function network element (e.g., Source AnLF ID), the vendor identifier of the target analysis logic function network element (e.g., Vendor ID of Target AnLF), the identifier of the first model, or first indication information. The vendor identifier of the target analysis logic function network element (e.g., Vendor ID of Target AnLF) can be used by the NRF network element to verify whether it is authorized to obtain the information of the first model from the model training logic function network element (e.g., MTLF). The specific verification method is described below. The role of the first indication information can be referred to the foregoing. Figure 3 The relevant descriptions in the illustrated embodiments will not be repeated here.

[0219] S203, NRF element verification: Does the vendor identifier (e.g., Vendor ID of Target AnLF) of the target analysis logic function element be included in the interoperability indicator corresponding to the aforementioned analysis identifier of the model training logic function element (e.g., MTLF)?

[0220] S204, if the vendor identifier of the target analysis logic function network element (such as the Vendor ID of the Target AnLF) is included in the interoperability indicator corresponding to the aforementioned analysis identifier of the model training logic function network element (such as the MTLF), the NRF network element sends a first token to the source analysis logic function network element (such as the Source AnLF), the first token including the identifier of the target analysis logic function network element (such as the Target AnLF ID) and / or the identifier of the model training logic function network element (such as the MTLF ID).

[0221] Correspondingly, the source analysis logic function network element (such as Source AnLF) receives the first token.

[0222] In one possible implementation, after receiving the token acquisition request, the NRF network element can verify whether the vendor identifier (e.g., the Vendor ID of Target AnLF) of the target analytics logic function network element is included in the interoperability indicator corresponding to the analytics identifier of the model training logic function network element (e.g., MTLF). Alternatively, after receiving the token acquisition request, the NRF network element can verify whether the target analytics logic function network element (e.g., Target AnLF) has permission to obtain the first model from the model training logic function network element (e.g., MTLF). For example, the NRF network element can determine the NF configuration file 3 corresponding to the target analytics logic function network element (e.g., Target AnLF) from multiple locally stored NF configuration files, and can obtain the vendor identifier (e.g., the Vendor ID of Target AnLF) of the target analytics logic function network element from NF configuration file 3. It is understood that when the token acquisition request includes the vendor identifier of the target analytics logic function network element (such as the Vendor ID of Target AnLF), the NRF network element can obtain the vendor identifier of the target analytics logic function network element (such as the Vendor ID of Target AnLF) from the token acquisition request without having to search the locally stored NF configuration file. The NRF network element can then determine the NF configuration file 4 corresponding to the identifier of the model training logic function network element (such as the MTLF ID) from multiple locally stored NF configuration files, and can obtain the interoperability indicator corresponding to the analytics ID (the analytics ID carried in the token acquisition request) from NF configuration file 4.

[0223] Then, the NRF element can verify whether the interoperability indicator corresponding to the analytics ID contains the vendor identifier of the target analytics logic function element (e.g., the Vendor ID of Target AnLF). If the interoperability indicator corresponding to the analytics ID in NF configuration file 4 contains the vendor identifier of the target analytics logic function element (e.g., the Vendor ID of Target AnLF), it indicates that the target analytics logic function element (e.g., TargetAnLF) has the authority to obtain the model from the model training logic function element (e.g., MTLF). The NRF element can then generate an authorization token for the model (i.e., the first token, token2) and send the first token (token2) to the source analytics logic function element (e.g., Source AnLF). The first token (token2) may include some or all of the content in the token acquisition request mentioned above. For example, the first token may include, but is not limited to, one or more of the following: the analytics ID corresponding to the first model, the identifier of the target analytics logic function element (e.g., TargetAnLF ID), or the identifier of the model training logic function element (e.g., MTLF ID). For a description of the first token, please refer to the foregoing. Figure 3 The relevant descriptions in the illustrated embodiments will not be repeated here.

[0224] In one possible implementation, the first token may further include one or more of the following: the analysis ID, the identifier of the source analysis logic function network element (e.g., Source AnLF ID), the vendor identifier of the target analysis logic function network element (e.g., Vendor ID of Target AnLF), the identifier of the first model, or second indication information. The role of the second indication information can be referred to the foregoing. Figure 3 The relevant descriptions of the embodiments shown are not repeated here.

[0225] In one possible implementation, if the interoperability indicator corresponding to the analysis ID in the NF configuration file 4 does not contain the vendor identifier of the target analysis logic function network element (such as the Vendor ID of Target AnLF), it indicates that the target analysis logic function network element (such as Target AnLF) does not have permission to obtain the model from the model training logic function network element (such as MTLF). The NRF network element can send a response message to the source analysis logic function network element (such as Source AnLF) to reject the aforementioned token acquisition request. For an explanation of this response message, please refer to the preceding... Figure 3 The relevant descriptions in the illustrated embodiments will not be repeated here.

[0226] In one possible implementation, if the token acquisition request includes the first indication information, after receiving the token acquisition request, the NRF network element can determine, based on the first indication information, that the token acquisition request is a request from a source analysis logic function network element (e.g., Source AnLF) to authorize a target analysis logic function network element (e.g., TargetAnLF) to acquire the model of a model training logic function network element (e.g., MTLF). Then, the verification in step S203 is performed.

[0227] S205, the source analysis logic function network element (such as Source AnLF) sends a model acquisition request to the model training logic function network element (such as MTLF). This model acquisition request includes one or more of the following: the aforementioned analysis identifier, the identifier of the target analysis logic function network element (such as Target AnLF ID), or the aforementioned first token. This model acquisition request is used to obtain information about the aforementioned first model for the target analysis logic function network element (such as Target AnLF). The first token can be used to verify the model acquisition request.

[0228] Correspondingly, the model training logic function network element (such as MTLF) receives the model acquisition request.

[0229] S206, The model training logic function network element (such as MTLF) verifies the first token mentioned above.

[0230] S207, if the first token verification is successful, the model training logic function network element (such as MTLF) sends a model notification message to the target analysis logic function network element (such as Target AnLF), which includes information about the first model.

[0231] Correspondingly, the target analysis logic function network element (such as Target AnLF) receives the model notification message.

[0232] In one possible implementation, after receiving the first token, the source analysis logic function element (e.g., Source AnLF) can send a model acquisition request to the model training logic function element (e.g., MTLF). This model acquisition request is used to acquire information about the first model for the target analysis logic function element (e.g., Target AnLF). The model acquisition request may include, but is not limited to, one or more of the following: the analysis identifier corresponding to the first model, the identifier of the target analysis logic function element (e.g., Target AnLF ID), or the first token. The first token can be used to verify the model acquisition request, or it can be used to verify various identifiers in the model acquisition request. Alternatively, the first token can be used to verify the permission of the target analysis logic function element (e.g., Target AnLF) to acquire the first model from the model training logic function element (e.g., MTLF). Alternatively, the first token can be used to verify the permission of the source analysis logic function element (e.g., Source AnLF) to (or on behalf of) the target analysis logic function element (e.g., Target AnLF) to acquire the first model from the model training logic function element (e.g., MTLF).

[0233] In one possible implementation, after receiving a model acquisition request, the model training logic function network element (such as MTLF) can verify the aforementioned first token (token2). The method by which the model training logic function network element (such as MTLF) verifies the first token is the same as described above. Figure 3 In the embodiments shown, the second model training logic function network element (such as MTLF2) verifies the first token in the same way, which will not be repeated here.

[0234] In one possible implementation, the model acquisition request may further include one or more of the following: the identifier of the source analysis logic function network element (e.g., Source AnLF ID), the address of the target analysis logic function network element (e.g., URL or FQDN), the identifier of the first model, the vendor identifier of the target analysis logic function network element (e.g., VendorID of Target AnLF), or third indication information. For example, the address of the target analysis logic function network element can be carried by a subscription endpoint address. This subscription endpoint address can be used to represent the address for receiving model notification messages. The explanation of the third indication information can be found above. Figure 3 The relevant descriptions in the illustrated embodiments are not repeated here. It can be understood that the model acquisition request in the embodiments of this application can be compared to the aforementioned... Figure 3 The second model acquisition request in the illustrated embodiment.

[0235] In one possible implementation, after the first token verification is successful, the model training logic function network element (such as MTLF) can send a model notification message to the target analysis logic function network element (such as Target AnLF). It is understood that the model training logic function network element (such as MTLF) can send the model notification message to the target analysis logic function network element (such as Target AnLF) directly or through an intermediate network element; this embodiment does not impose any restrictions. For example, the model training logic function network element (such as MTLF) can send the model notification message to the target analysis logic function network element (such as Target AnLF) through a source analysis logic function network element (such as Source AnLF). For instance, the model training logic function network element (such as MTLF) sends the model notification message to the source analysis logic function network element (such as Source AnLF), which can then forward it to the target analysis logic function network element (such as Target AnLF). This forwarding can be a transparent transmission or processing of the model notification message before forwarding; this embodiment does not impose any restrictions. However, the model notification message received by the target analysis logic function network element (such as Target AnLF) may include information about the first model, such as the ID of the first model, the address of the first model in the model training logic function network element (such as MTLF), or the model file. For example, the model notification message may also include the identifier (such as ADRFID) of the ADRF network element storing the first model. After receiving the model notification message, the analysis logic function network element (such as AnLF) can obtain (or download) the model file of the first model to its local storage based on the model notification message.

[0236] In one possible implementation, after the first token verification passes, the model training logic function network element (such as MTLF) can also add the identifier of the target analysis logic function network element (such as the Target AnLF ID) to the allowed NF consumer list. This allowed NFc list is associated with the first model. Alternatively, this allowed NFc list is a list of network function instance identifiers that are allowed to acquire / retrieve the first model.

[0237] In this embodiment of the application, after receiving an analysis context transfer request from the Target AnLF, the Source AnLF requests an authorization token (i.e., the aforementioned first token) from the NRF on behalf of (or on behalf of) the Target AnLF. This request includes the Target AnLF ID and the MTLF ID. After verifying that the Target AnLF has the authority to retrieve the first model from the analysis context in the MTLF, the NRF returns the authorization token (i.e., the aforementioned first token) to the Source AnLF. Upon obtaining the authorization token, the Source AnLF requests information about the first model from the MTLF on behalf of (or on behalf of) the Target AnLF. This request includes the Target AnLF ID and the authorization token. After verifying the authorization token, the MTLF sends the information about the first model to the Target AnLF. This process facilitates model authorization and model retrieval in a model delegation retrieval scenario, and authorizes the actual model consumer (i.e., the Target AnLF) in the model delegation retrieval scenario, thereby improving model security.

[0238] The foregoing details the method of this application. To facilitate better implementation of the above-described solutions in the embodiments of this application, corresponding apparatus or devices are also provided.

[0239] This application embodiment can divide the network elements of this application into functional modules according to the above method example, and also divide the network elements into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or in software functional modules. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The following will combine... Figures 5 to 7 The communication device of the present application embodiment is described in detail.

[0240] See Figure 5 , Figure 5 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application. Figure 5 As shown, the communication device includes a transceiver unit 10 and a processing unit 20. The transceiver unit 10 can implement corresponding communication functions, and the processing unit 20 is used for data processing. The transceiver unit 10 can also be called a communication interface or a communication unit, etc.

[0241] In some embodiments of this application, the communication device may be the first model training logic function network element shown above. That is... Figure 5The communication device shown can be used to execute the steps or functions performed by the first model training logic function network element in the above method embodiments. For example, the communication device may be the first model training logic function network element or a chip or functional module configured in the first model training logic function network element, etc., and this application embodiment does not limit this. The transceiver unit 10 is used to execute operations related to the transmission and reception of the first model training logic function network element in the above method embodiments, and the processing unit 20 is used to execute operations related to the processing of the first model training logic function network element in the above method embodiments.

[0242] For example, the transceiver unit 10 is configured to receive a first model acquisition request from an analysis logic function network element, the first model acquisition request including an analysis identifier, the first model acquisition request being used to request information about the model corresponding to the analysis identifier; the transceiver unit 10 is further configured to send a token acquisition request to a network storage function (NRF) network element, the token acquisition request including the analysis identifier, the identifier of the analysis logic function network element, and the identifier of a second model training logic function network element, the second model training logic function network element being used to provide information about the model; the transceiver unit 10 is further configured to receive a first token from the NRF network element, the first token including the identifier of the analysis logic function network element and the identifier of the second model training logic function network element; the transceiver unit 10 is further configured to send a second model acquisition request to the second model training logic function network element, the second model acquisition request including the analysis identifier, the identifier of the analysis logic function network element, and the first token, the second model acquisition request being used to obtain information about the model for the analysis logic function network element, the first token being used to verify the second model acquisition request.

[0243] For example, the processing unit 20 is used to generate various information sent by the transceiver unit 10, such as token acquisition request and second model acquisition request; the processing unit 20 is also used to control the transceiver unit 10 to send or receive various information.

[0244] For example, the transceiver unit 10 is further configured to send a network element discovery request to the NRF network element, the network element discovery request including the analysis identifier, and the identifier of the analysis logic function network element and / or the vendor identifier of the analysis logic function network element; the transceiver unit 10 is further configured to receive a network element discovery response from the NRF network element, the network element discovery response including a candidate network element list, the network element list including a second model training logic function network element, and the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element including the vendor identifier of the analysis logic function network element.

[0245] In this embodiment of the application, for detailed descriptions of the first model acquisition request, token acquisition request, first token, second model acquisition request, network element discovery request, network element discovery response, and various network elements, please refer to the above text. Figure 3The method embodiments shown will not be described in detail here.

[0246] It is understood that the specific descriptions of the transceiver unit and processing unit shown in the embodiments of this application are merely examples. For the specific functions or execution steps of the transceiver unit and processing unit, please refer to the above descriptions. Figure 3 The method embodiments shown will not be described in detail here. Furthermore, the technical effects of the embodiments of this application are described above. Figure 3 The technical effects of the method embodiments shown are not elaborated here for the sake of simplicity.

[0247] Reuse Figure 5 In other embodiments of this application, the communication device may be the source analysis logic function network element shown above. That is... Figure 5 The communication device shown can be used to execute the steps or functions performed by the source analysis logic function network element in the above method embodiments. For example, the communication device can be the source analysis logic function network element or a chip or functional module configured in the source analysis logic function network element, etc., and this application embodiment does not limit this. The transceiver unit 10 is used to execute operations related to the transmission and reception of the source analysis logic function network element in the above method embodiments, and the processing unit 20 is used to execute operations related to the processing of the source analysis logic function network element in the above method embodiments.

[0248] For example, the transceiver unit 10 is configured to receive an analysis context transfer request from a target analysis logic function network element. The analysis context transfer request includes an identifier of the analysis context and is used to request the transfer of information of the first model in the analysis context. The transceiver unit 10 is also configured to send a token acquisition request to an NRF network element. The token acquisition request includes an analysis identifier corresponding to the first model, an identifier of the target analysis logic function network element, and an identifier of a model training logic function network element. The model training logic function network element is used to provide information of the first model. The transceiver unit 10 is also configured to receive a first token from an NRF network element. The first token includes the identifier of the target analysis logic function network element and the identifier of the model training logic function network element. The transceiver unit 10 is also configured to send a model acquisition request to the model training logic function network element. The model acquisition request includes the analysis identifier, the identifier of the target analysis logic function network element, and the first token. The model acquisition request is used to acquire information of the first model for the target analysis logic function network element, and the first token is used to verify the model acquisition request.

[0249] For example, the processing unit 20 is used to generate various information sent by the transceiver unit 10, such as token acquisition requests and model acquisition requests; the processing unit 20 is also used to control the transceiver unit 10 to send or receive various information.

[0250] For example, the processing unit 20 is further configured to determine whether the provider of the first model is located in the second operation indicator of the target analysis logic function network element. The second operation indicator is used to indicate the provider of the model that the target analysis logic function network element can use.

[0251] For example, the processing unit 20 is also configured to determine that the supplier identifier of the target analysis logic function network element is included in the interoperability indicator of the information provider of the first model.

[0252] For example, the transceiver unit 10 is also configured to send a network element registration request to the NRF network element, the network element registration request including a first operation indicator of the source analysis logic function network element, the first operation indicator being used to indicate the provider of the model that the source analysis logic function network element can use.

[0253] In this embodiment of the application, for detailed descriptions of the context transfer request, token acquisition request, first token, model acquisition request, network element registration request, first operation indicator, second operation indicator, and various network elements, please refer to the above text. Figure 4 The method embodiments shown will not be described in detail here.

[0254] It is understood that the specific descriptions of the transceiver unit and processing unit shown in the embodiments of this application are merely examples. For the specific functions or execution steps of the transceiver unit and processing unit, please refer to the above descriptions. Figure 4 The method embodiments shown will not be described in detail here. Furthermore, the technical effects of the embodiments of this application are described above. Figure 4 The technical effects of the method embodiments shown are not elaborated here for the sake of simplicity.

[0255] Reuse Figure 5 In some other embodiments of this application, the communication device may be an NRF network element as shown above. Figure 5 The communication device shown can be used to perform the steps or functions executed by the NRF network element in the above method embodiments. For example, the communication device can be an NRF network element or a chip or functional module configured in the NRF network element, etc., and this application embodiment does not limit this. The transceiver unit 10 is used to perform NRF network element transmission and reception related operations in the above method embodiments, and the processing unit 20 is used to perform NRF network element processing related operations in the above method embodiments.

[0256] For example, the transceiver unit 10 is configured to receive a token acquisition request from a first model training logic function network element. The token acquisition request includes an analysis identifier, an identifier of the analysis logic function network element, and an identifier of a second model training logic function network element. The second model training logic function network element is configured to provide information about the model corresponding to the analysis identifier. The processing unit 20 is configured to verify whether the supplier identifier of the analysis logic function network element is included in the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element. The transceiver unit 10 is further configured to send a first token to the first model training logic function network element when the supplier identifier is included in the interoperability indicator. The first token includes the identifier of the analysis logic function network element and the identifier of the second model training logic function network element.

[0257] For example, the processing unit 20 is further configured to obtain the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element from the NF configuration file corresponding to the identifier of the second model training logic function network element.

[0258] For example, the processing unit 20 is further configured to obtain the vendor identifier of the analysis logical function network element from the NF configuration file corresponding to the identifier of the analysis logical function network element.

[0259] For example, the transceiver unit 10 is further configured to receive a network element discovery request from a first model training logic function network element, the network element discovery request including the analysis identifier, and the identifier of the analysis logic function network element and / or the vendor identifier of the analysis logic function network element; the processing unit 20 is further configured to obtain the vendor identifier of the analysis logic function network element based on the network element discovery request; the processing unit 20 is further configured to determine a candidate network element list based on the stored NF configuration files of each network element, the network element list including a second model training logic function network element, the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element including the vendor identifier of the analysis logic function network element; the transceiver unit 10 is further configured to send a network element discovery response to the first model training logic function network element, the network element discovery response including the candidate network element list.

[0260] For example, the processing unit 20 is further configured to obtain the vendor identifier of the analysis logic function network element from the NF configuration file corresponding to the identifier of the analysis logic function network element.

[0261] In this embodiment of the application, for detailed descriptions of the token acquisition request, the first token, the network element discovery request, the network element discovery response, and each network element, please refer to the above text. Figure 3 The method embodiments shown will not be described in detail here.

[0262] It is understood that the specific descriptions of the transceiver unit and processing unit shown in the embodiments of this application are merely examples. For the specific functions or execution steps of the transceiver unit and processing unit, please refer to the above descriptions. Figure 3 The method embodiments shown will not be described in detail here. Furthermore, the technical effects of the embodiments of this application are described above. Figure 3 The technical effects of the method embodiments shown are not elaborated here for the sake of simplicity.

[0263] For example, the transceiver unit 10 is configured to receive a token acquisition request from a source analysis logic function network element. The token acquisition request includes an analysis identifier, an identifier of a target analysis logic function network element, and an identifier of a model training logic function network element. The model training logic function network element is configured to provide information about a first model corresponding to the analysis identifier. The processing unit 20 is configured to verify whether the supplier identifier of the target analysis logic function network element is included in the interoperability indicator corresponding to the analysis identifier of the model training logic function network element. The transceiver unit 10 is further configured to send a first token to the source analysis logic function network element when the supplier identifier is included in the interoperability indicator. The first token includes the identifier of the target analysis logic function network element and the identifier of the model training logic function network element.

[0264] For example, the processing unit 20 is further configured to obtain the interoperability indicator corresponding to the analysis identifier of the model training logic function network element from the NF configuration file corresponding to the identifier of the model training logic function network element.

[0265] For example, the processing unit 20 is further configured to obtain the vendor identifier of the target analysis logic function network element from the NF configuration file corresponding to the identifier of the target analysis logic function network element.

[0266] For example, the transceiver unit 10 is further configured to receive a first network element registration request from a source analysis logic function network element, the first network element registration request including a first operation indicator of the source analysis logic function network element, the first operation indicator being used to indicate the provider of the model that the source analysis logic function network element can use.

[0267] For example, the transceiver unit 10 is further configured to receive a second network element registration request from the target analysis logic function network element, the second network element registration request including a second operation indicator of the target analysis logic function network element, the second operation indicator being used to indicate the provider of the model that the target analysis logic function network element can use.

[0268] In this embodiment of the application, for detailed descriptions of the token acquisition request, the first token, the first network element registration request, the second network element registration request, and each network element, please refer to the above text. Figure 4 The method embodiments shown will not be described in detail here.

[0269] It is understood that the specific descriptions of the transceiver unit and processing unit shown in the embodiments of this application are merely examples. For the specific functions or execution steps of the transceiver unit and processing unit, please refer to the above descriptions. Figure 4 The method embodiments shown will not be described in detail here. Furthermore, the technical effects of the embodiments of this application are described above. Figure 4 The technical effects of the method embodiments shown are not elaborated here for the sake of simplicity.

[0270] Reuse Figure 5 In some further embodiments of this application, the communication device may be the second model training logic function network element shown above. That is... Figure 5 The communication device shown can be used to execute the steps or functions performed by the second model training logic function network element in the above method embodiments. For example, the communication device can be the second model training logic function network element or a chip or functional module configured in the second model training logic function network element, etc., and this application embodiment does not limit this. The transceiver unit 10 is used to execute operations related to the transmission and reception of the second model training logic function network element in the above method embodiments, and the processing unit 20 is used to execute operations related to the processing of the second model training logic function network element in the above method embodiments.

[0271] For example, the transceiver unit 10 is configured to receive a second model acquisition request from a first model training logic function network element. The second model acquisition request includes an analysis identifier, an identifier of the analysis logic function network element, and a first token. The second model acquisition request is used to acquire information about the model corresponding to the analysis identifier for the analysis logic function network element. The processing unit 20 is configured to verify the first token. The transceiver unit 10 is further configured to send a model notification message to the analysis logic function network element if the first token is verified successfully. The model notification message includes information about the model corresponding to the analysis identifier.

[0272] For detailed descriptions of the second model acquisition request, model notification message, and various network elements in this embodiment, please refer to the above text. Figure 3 The method embodiments shown will not be described in detail here.

[0273] It is understood that the specific descriptions of the transceiver unit and processing unit shown in the embodiments of this application are merely examples. For the specific functions or execution steps of the transceiver unit and processing unit, please refer to the above descriptions. Figure 3 The method embodiments shown will not be described in detail here. Furthermore, the technical effects of the embodiments of this application are described above. Figure 3 The technical effects of the method embodiments shown are not elaborated here for the sake of simplicity.

[0274] Reuse Figure 5In some further embodiments of this application, the communication device may be the model training logic function network element shown above. That is... Figure 5 The communication device shown can be used to execute the steps or functions performed by the model training logic function network element in the above method embodiments. For example, the communication device can be the model training logic function network element or a chip or functional module configured in the model training logic function network element, etc., and this application embodiment does not limit this. The transceiver unit 10 is used to perform operations related to the transmission and reception of the model training logic function network element in the above method embodiments, and the processing unit 20 is used to perform operations related to the processing of the model training logic function network element in the above method embodiments.

[0275] For example, the transceiver unit 10 is configured to receive a model acquisition request from a source analysis logic function network element. The model acquisition request includes an analysis identifier, an identifier of a target analysis logic function network element, and a first token. The model acquisition request is used to acquire information of a first model corresponding to the analysis identifier for the target analysis logic function network element. The processing unit 20 is configured to verify the first token. The transceiver unit 10 is further configured to send a model notification message to the target analysis logic function network element if the first token is verified successfully. The model notification message includes the information of the first model mentioned above.

[0276] For detailed descriptions of model acquisition requests, model notification messages, and various network elements in this embodiment, please refer to the above text. Figure 4 The method embodiments shown will not be described in detail here.

[0277] It is understood that the specific descriptions of the transceiver unit and processing unit shown in the embodiments of this application are merely examples. For the specific functions or execution steps of the transceiver unit and processing unit, please refer to the above descriptions. Figure 4 The method embodiments shown will not be described in detail here. Furthermore, the technical effects of the embodiments of this application are described above. Figure 4 The technical effects of the method embodiments shown are not elaborated here for the sake of simplicity.

[0278] The communication device according to embodiments of this application has been described above. The following describes possible product forms of the communication device. It should be understood that any device possessing the above-described features... Figure 5 Any form of the communication device described herein falls within the protection scope of the embodiments of this application. It should also be understood that the following description is merely illustrative and does not limit the form of the communication device in the embodiments of this application to this specific example.

[0279] In one possible implementation, Figure 5In the communication device shown, the processing unit 20 can be one or more processors, and the transceiver unit 10 can be a transceiver, or the transceiver unit 10 can also be a transmitting unit and a receiving unit. The transmitting unit can be a transmitter, and the receiving unit can be a receiver. The transmitting unit and the receiving unit are integrated into one device, such as a transceiver. In the embodiments of this application, the processor and the transceiver can be coupled, etc., and the connection method between the processor and the transceiver is not limited in the embodiments of this application. In the process of executing the above method, the process of sending information in the above method can be understood as the process of the processor outputting the above information. When outputting the above information, the processor outputs the above information to the transceiver so that the transceiver can transmit it. After the above information is output by the processor, it may need to undergo other processing before reaching the transceiver. Similarly, the process of receiving information in the above method can be understood as the process of the processor receiving the input above information. When the processor receives the input information, the transceiver receives the above information and inputs it into the processor. Furthermore, after the transceiver receives the above information, the above information may need to undergo other processing before being input into the processor.

[0280] See Figure 6 , Figure 6 This is another structural schematic diagram of the communication device provided in the embodiments of this application. For example... Figure 6 As shown, the communication device provided in this application embodiment can be used to implement the methods described in any of the above method embodiments, and reference can be made to the descriptions in the above method embodiments. The communication device may be the aforementioned first model training logic function network element, analysis logic function network element, second model training logic function network element, NRF network element, source analysis logic function network element, target analysis logic function network element, model training logic function network element, or a chip or circuit thereof. For example, the communication device includes one or more processors 1001 and transceivers 1002. The communication device may further include a memory 1003. In one implementation, the communication device also includes an input / output device (not shown in the figure).

[0281] The processor 1001 is mainly used to process communication protocols and communication data, control the entire communication device, execute software programs, and process the data of the software programs. The memory 1003 is mainly used to store software programs and data. The transceiver 1002 may include control circuitry and an antenna. The control circuitry is mainly used for converting baseband signals to radio frequency signals and processing radio frequency signals. The antenna is mainly used for transmitting and receiving radio frequency signals in the form of electromagnetic waves. Input / output devices, such as touchscreens, displays, and keyboards, are mainly used to receive user input data and output data to the user.

[0282] When the communication device is powered on, the processor 1001 can read the software program in the memory 1003, interpret and execute the instructions of the software program, and process the data of the software program. When data needs to be transmitted wirelessly, the processor 1001 performs baseband processing on the data to be transmitted and outputs the baseband signal to the radio frequency (RF) circuit. The RF circuit processes the baseband signal and transmits the RF signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the RF circuit receives the RF signal through the antenna, converts the RF signal into a baseband signal, and outputs the baseband signal to the processor 1001. The processor 1001 converts the baseband signal into data and processes the data.

[0283] In another implementation, the radio frequency circuitry and antenna can be set up independently of the processor performing baseband processing. For example, in a distributed scenario, the radio frequency circuitry and antenna can be arranged remotely, independent of the communication device.

[0284] The processor 1001, transceiver 1002, and memory 1003 can be connected via a communication bus.

[0285] For example, when the communication device is used to execute the above method embodiment one (such as... Figure 3 When analyzing the steps, methods, or functions executed by the logical functional network element in the process, the processor 1001 can be used to generate a first model acquisition request, and / or to execute other processes of the technology described herein; the transceiver 1002 can be used to execute Figure 3 Step S101 in the document, and / or other processes used in the techniques described herein.

[0286] For example, when the communication device is used to execute the above method embodiment one (such as... Figure 3 When the first model training logic function network element executes the steps, methods, or functions, the processor 1001 can be used to generate a token acquisition request and a second model acquisition request, and / or to execute other processes of the technology described herein; the transceiver 1002 can be used to execute Figure 3 Steps S102 and S105 in the document, and / or other processes used in the techniques described herein.

[0287] For example, when the communication device is used to execute the above method embodiment one (such as... Figure 3 When an NRF network element performs a step, method, or function, the processor 1001 can be used to execute... Figure 3 Step S103, and / or other processes for performing the techniques described herein; transceiver 1002 can be used to perform Figure 3 Step S104 in the document, and / or other processes used in the techniques described herein.

[0288] For example, when the communication device is used to execute the above method embodiment one (such as... Figure 3 When the second model training logic function element executes the steps, methods, or functions, the processor 1001 can be used to execute... Figure 3 Step S106, and / or other processes for performing the techniques described herein; transceiver 1002 can be used to perform Figure 3 Step S107 in the document, and / or other processes used in the techniques described herein.

[0289] For example, when the communication device is used to execute the above method embodiment two (such as... Figure 4 When the target analysis logic function network element executes the steps, methods, or functions, the processor 1001 can be used to generate an analysis context transfer request, and / or to perform other processes of the techniques described herein; the transceiver 1002 can be used to execute Figure 4 Step S201 in the document, and / or other processes used in the techniques described herein.

[0290] For example, when the communication device is used to execute the above method embodiment two (such as... Figure 4 When the source analysis logic function network element executes the steps, methods, or functions, the processor 1001 can be used to generate token acquisition requests and model acquisition requests, and / or to execute other processes of the technology described herein; the transceiver 1002 can be used to execute Figure 4 Steps S202 and S205 in the document, and / or other processes used in the techniques described herein.

[0291] For example, when the communication device is used to execute the above method embodiment two (such as... Figure 4 When an NRF network element performs a step, method, or function, the processor 1001 can be used to execute... Figure 4 Step S203, and / or other processes for performing the techniques described herein; transceiver 1002 can be used to perform Figure 4 Step S204 in the document, and / or other processes used in the techniques described herein.

[0292] For example, when the communication device is used to execute the above method embodiment two (such as... Figure 4 When the model training logic function element executes the steps, methods, or functions in the network, the processor 1001 can be used to execute... Figure 4 Step S206, and / or other processes for performing the techniques described herein; transceiver 1002 can be used to perform Figure 4 Step S207 in the document, and / or other processes used in the techniques described herein.

[0293] In any of the above implementations, the processor 1001 may include a transceiver for implementing receiving and transmitting functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing receiving and transmitting functions may be separate or integrated. The aforementioned transceiver circuit, interface, or interface circuit can be used for reading and writing code / data, or it can be used for transmitting or relaying signals.

[0294] In any of the above implementations, the processor 1001 may store instructions, which may be computer programs. These computer programs, running on the processor 1001, cause the communication device to execute the methods described in the above method embodiments. The computer program may be embedded in the processor 1001; in this case, the processor 1001 may be implemented in hardware.

[0295] In one implementation, the communication device may include a circuit that can perform the functions of transmitting, receiving, or communicating in the aforementioned method embodiments. The processor and transceiver described in this application can be implemented on integrated circuits (ICs), analog ICs, radio frequency integrated circuits (RFICs), mixed-signal ICs, application-specific integrated circuits (ASICs), printed circuit boards (PCBs), electronic devices, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal-oxide semiconductors (CMOS), n-metal-oxide-semiconductor (NMOS), positive-channel metal-oxide semiconductors (PMOS), bipolar junction transistors (BJTs), bipolar CMOS (BiCMOS), silicon-germanium (SiGe), gallium arsenide (GaAs), etc.

[0296] It is understood that the communication device shown in the embodiments of this application may also have more than Figure 6 This application does not limit the use of other components or other related elements. The methods performed by the processor and transceiver shown above are merely examples; for the specific steps performed by the processor and transceiver, please refer to the descriptions of the various method embodiments above.

[0297] In another possible implementation, Figure 5 In the communication device shown, the processing unit 20 can be one or more logic circuits, and the transceiver unit 10 can be an input / output interface, or a communication interface, or an interface circuit, or an interface, etc. Alternatively, the transceiver unit 10 can also be a transmitting unit and a receiving unit. The transmitting unit can be an output interface, and the receiving unit can be an input interface. The transmitting unit and the receiving unit are integrated into one unit, such as an input / output interface. See also Figure 7 , Figure 7 This is another structural schematic diagram of the communication device provided in the embodiments of this application. For example... Figure 7 As shown, Figure 7 The communication device shown includes logic circuitry 901 and interface 902. That is, the processing unit 20 can be implemented using logic circuitry 901, and the transceiver unit 10 can be implemented using interface 902. The logic circuitry 901 can be a chip, processing circuit, integrated circuit, or system-on-a-chip (SoC) chip, etc., and the interface 902 can be a communication interface, input / output interface, pins, etc. For example, Figure 7 The above-mentioned communication device is used as an example of a chip, which includes a logic circuit 901 and an interface 902.

[0298] In this embodiment, the logic circuit and the interface can also be coupled to each other. The specific connection method between the logic circuit and the interface is not limited in this embodiment.

[0299] For example, when the communication device is used to execute the aforementioned method embodiment one (such as... Figure 3 When the first model training logic function network element executes the method, function or step, interface 902 is used to input the first model acquisition request; logic circuit 901 is used to generate the token acquisition request; interface 902 is also used to output the token acquisition request and input the first token; logic circuit 901 is also used to generate the second model acquisition request; interface 902 is also used to output the second model acquisition request.

[0300] For example, when the communication device is used to execute the aforementioned method embodiment one (such as... Figure 3 When the NRF network element executes a method, function, or step, interface 902 is used to input a token acquisition request; logic circuit 901 is used to verify whether the vendor identifier of the analysis logic function network element is included in the interoperability indicator of the second model training logic function network element; interface 902 is used to output the first token.

[0301] In this embodiment of the application, specific descriptions of the first model acquisition request, token acquisition request, first token, second model acquisition request, etc., can be found in the method embodiment one shown above (e.g., Figure 3(These will not be detailed here.)

[0302] For example, when the communication device is used to execute the aforementioned method embodiment two (such as... Figure 4 When the source analysis logic function network element executes a method, function or step, interface 902 is used to input an analysis context transfer request; logic circuit 901 is used to generate a token acquisition request; interface 902 is also used to output the token acquisition request and input a first token; logic circuit 901 is also used to generate a model acquisition request; interface 902 is also used to output the model acquisition request.

[0303] For example, when the communication device is used to execute the aforementioned method embodiment two (such as... Figure 4 When the NRF network element executes a method, function, or step, interface 902 is used to input a token acquisition request; logic circuit 901 is used to verify whether the vendor identifier of the target analysis logic function network element is included in the interoperability indicator of the model training logic function network element; and interface 902 is used to output the first token.

[0304] In this embodiment of the application, for specific descriptions of context transfer requests, token acquisition requests, first tokens, model acquisition requests, etc., please refer to the method embodiment two shown above (e.g., ...). Figure 4 (These will not be detailed here.)

[0305] This application also provides a communication system, which includes at least two of the following: a first model training logic function network element, a second model training logic function network element, an analysis logic function network element, and an NRF network element. At least two of the first model training logic function network element, the second model training logic function network element, the analysis logic function network element, and the NRF network element can be used to perform the aforementioned functions. Figure 3 The method in the illustrated embodiment.

[0306] This application also provides a communication system, which includes at least two of the following: a source analysis logic function network element, a target analysis logic function network element, a model training logic function network element, and an NRF network element. At least two of these network elements can be used to perform the aforementioned functions. Figure 4 The method in the illustrated embodiment.

[0307] In addition, this application also provides a computer program for implementing the operations and / or processes performed by the first model training logic function network element in the method provided in this application.

[0308] This application also provides a computer program for implementing the operations and / or processes performed by the second model training logic function network element in the method provided in this application.

[0309] This application also provides a computer program for implementing the operations and / or processes performed by the analysis logic function network element in the method provided in this application.

[0310] This application also provides a computer program for implementing the operations and / or processes performed by NRF network elements in the method provided in this application.

[0311] This application also provides a computer program for implementing the operations and / or processes performed by the source analysis logic function network element in the method provided in this application.

[0312] This application also provides a computer program for implementing the operations and / or processes performed by the target analysis logic function network element in the method provided in this application.

[0313] This application also provides a computer program for implementing the operations and / or processes performed by the model training logic function network element in the method provided in this application.

[0314] This application also provides a computer-readable storage medium storing computer code that, when executed on a computer, causes the computer to perform operations and / or processes performed by the first model training logic function network element in the method provided in this application.

[0315] This application also provides a computer-readable storage medium storing computer code that, when executed on a computer, causes the computer to perform operations and / or processes performed by the second model training logic function network element in the method provided in this application.

[0316] This application also provides a computer-readable storage medium storing computer code that, when executed on a computer, causes the computer to perform operations and / or processes performed by the analysis logic function network element in the method provided in this application.

[0317] This application also provides a computer-readable storage medium storing computer code that, when executed on a computer, causes the computer to perform the operations and / or processes performed by the NRF network element in the method provided in this application.

[0318] This application also provides a computer-readable storage medium storing computer code that, when executed on a computer, causes the computer to perform operations and / or processes performed by the source analysis logic function network element in the method provided in this application.

[0319] This application also provides a computer-readable storage medium storing computer code that, when executed on a computer, causes the computer to perform operations and / or processes performed by the target analysis logic function network element in the method provided in this application.

[0320] This application also provides a computer-readable storage medium storing computer code that, when executed on a computer, causes the computer to perform operations and / or processes performed by the model training logic function network element in the method provided in this application.

[0321] This application also provides a computer program product, which includes computer code or a computer program that, when run on a computer, causes the operations and / or processes performed by the first model training logic function network element in the method provided in this application to be executed.

[0322] This application also provides a computer program product, which includes computer code or a computer program that, when run on a computer, causes the operations and / or processes performed by the second model training logic function network element in the method provided in this application to be executed.

[0323] This application also provides a computer program product, which includes computer code or a computer program that, when run on a computer, causes the operations and / or processes performed by the analysis logic function network element in the method provided in this application to be executed.

[0324] This application also provides a computer program product, which includes computer code or a computer program that, when run on a computer, causes the operations and / or processes performed by the NRF network element in the method provided in this application to be executed.

[0325] This application also provides a computer program product, which includes computer code or a computer program that, when run on a computer, causes the operations and / or processes performed by the source analysis logic function network element in the method provided in this application to be executed.

[0326] This application also provides a computer program product, which includes computer code or a computer program that, when run on a computer, causes the operations and / or processes performed by the target analysis logic function network element in the method provided in this application to be executed.

[0327] This application also provides a computer program product, which includes computer code or a computer program that, when run on a computer, causes the operations and / or processes performed by the model training logic function network element in the method provided in this application to be executed.

[0328] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, or it may be an electrical, mechanical, or other form of connection.

[0329] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the technical effects of the solutions provided in the embodiments of this application.

[0330] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0331] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0332] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A model authorization method characterized by, Comprising: The first model training logical function network element receives a first model obtaining request from an analysis logical function network element, the first model obtaining request comprising an analysis identifier, the first model obtaining request being used to request information of a model corresponding to the analysis identifier; The first model training logical function network element sends a token obtaining request to a network storage function NRF network element, the token obtaining request comprising the analysis identifier, an identifier of the analysis logical function network element, and an identifier of a second model training logical function network element used to provide information of the model; The first model training logical function network element receives a first token from the NRF network element, the first token comprising the identifier of the analysis logical function network element and the identifier of the second model training logical function network element; The first model training logical function network element sends a second model obtaining request to the second model training logical function network element, the second model obtaining request comprising the analysis identifier, the identifier of the analysis logical function network element, and the first token, the second model obtaining request being used to obtain information of the model for the analysis logical function network element, and the first token being used to verify the second model obtaining request.

2. The method of claim 1, wherein, The token obtaining request further comprises one or more of the following: the identifier of the first model training logical function network element, a vendor identifier of the analysis logical function network element, or first indication information; The first indication information is used to indicate that the first model training logical function network element requests a first token for the analysis logical function network element.

3. The method according to claim 1 or 2, characterized in that, The first token further comprises one or more of the following: the analysis identifier, the identifier of the first model training logical function network element, a vendor identifier of the analysis logical function network element, or second indication information; The second indication information is used to indicate that the analysis logical function network element is authorized to obtain information of the model from the second model training logical function network element.

4. The method according to any one of claims 1 to 3, characterized in that, The second model obtaining request further comprises one or more of the following: the identifier of the first model training logical function network element, an address of the analysis logical function network element, a vendor identifier of the analysis logical function network element, or third indication information; The third indication information is used to indicate that the first model training logical function network element obtains information of the model for the analysis logical function network element.

5. The method according to any one of claims 1 to 4, characterized in that, Before the first model training logical function network element sends a token obtaining request to a network storage function NRF network element, the method further comprises: The first model training logical function network element sends a network element discovery request to the NRF network element, the network element discovery request comprising the analysis identifier, and the identifier of the analysis logical function network element and / or the vendor identifier of the analysis logical function network element; The first model training logic function network element receives a network element discovery response from the NRF network element, the network element discovery response comprising a list of candidate network elements, the list of candidate network elements including a second model training logic function network element, the analysis identifier of the second model training logic function network element corresponding to an interoperability indicator comprising a vendor identifier of the analysis logic function network element.

6. A model authorization method characterized by comprising: Comprising: The network storage function, NRF, network element receives a token acquisition request from a first model training logic function network element, the token acquisition request comprising an analysis identifier, an identifier of an analysis logic function network element, and an identifier of a second model training logic function network element configured to provide information of a model corresponding to the analysis identifier; The NRF network element verifies whether the vendor identifier of the analysis logic function network element is included in the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element; If the vendor identifier is included in the interoperability indicator, the NRF network element sends a first token to the first model training logic function network element, the first token comprising the identifier of the analysis logic function network element and the identifier of the second model training logic function network element.

7. The method of claim 6, wherein, Before the NRF network element verifies whether the vendor identifier of the analysis logic function network element is included in the interoperability indicator of the second model training logic function network element, the method further comprises: The NRF network element obtains the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element from a network function, NF, profile corresponding to the identifier of the second model training logic function network element.

8. The method according to claim 6 or 7, characterized in that, Before the NRF network element verifies whether the vendor identifier of the analysis logic function network element is included in the interoperability indicator of the second model training logic function network element, the method further comprises: The NRF network element obtains the vendor identifier of the analysis logic function network element from an NF profile corresponding to the identifier of the analysis logic function network element.

9. The method according to any one of claims 6 to 8, characterized in that, The token acquisition request further comprises one or more of: an identifier of the first model training logic function network element, the vendor identifier of the analysis logic function network element, or first indication information; The first indication information is used to indicate that the first model training logic function network element requests a first token for the analysis logic function network element.

10. The method according to any one of claims 6 to 9, characterized in that, The first token further comprises one or more of: the analysis identifier, the identifier of the first model training logic function network element, the vendor identifier of the analysis logic function network element, or second indication information; The second indication information is used to indicate that the analysis logic function network element is authorized to obtain the information of the model from the second model training logic function network element.

11. The method according to any one of claims 6 to 10, characterized in that, Before the network storage function, NRF, network element receives a token acquisition request from a first model training logic function network element, the method further comprises: The NRF network element receives a network element discovery request from a first model training logic function network element, the network element discovery request comprising the analysis identifier, and an identifier of the analysis logic function network element and / or a vendor identifier of the analysis logic function network element; The NRF network element acquires the vendor identifier of the analysis logic function network element based on the network element discovery request; The NRF network element determines a candidate network element list based on the stored NF profile of each network element, the network element list including a second model training logic function network element, and the interoperability indicator corresponding to the analysis identifier of the second model training logic function network element including the vendor identifier of the analysis logic function network element; The NRF network element sends a network element discovery response to the first model training logic function network element, the network element discovery response including the candidate network element list.

12. The method of claim 11, wherein, The network element discovery request includes the identifier of the analysis logic function network element; The NRF network element acquires the vendor identifier of the analysis logic function network element based on the network element discovery request, including: The NRF network element acquires the vendor identifier of the analysis logic function network element from the NF profile corresponding to the identifier of the analysis logic function network element.

13. A model authorization method characterized by comprising: Including: The source analysis logic function network element receives an analysis context transfer request from a target analysis logic function network element, the analysis context transfer request including an identifier of an analysis context, and the analysis context transfer request being used to request to transfer information of a first model in the analysis context; The source analysis logic function network element sends a token acquisition request to a network storage function NRF network element, the token acquisition request including an analysis identifier corresponding to the first model, an identifier of the target analysis logic function network element, and an identifier of a model training logic function network element, the model training logic function network element being used to provide information of the first model; The source analysis logic function network element receives a first token from the NRF network element, the first token including the identifier of the target analysis logic function network element and the identifier of the model training logic function network element; The source analysis logic function network element sends a model acquisition request to the model training logic function network element, the model acquisition request including the analysis identifier, the identifier of the target analysis logic function network element, and the first token, the model acquisition request being used to acquire information of the first model for the target analysis logic function network element, and the first token being used to verify the model acquisition request.

14. The method of claim 13, wherein, The analysis context transfer request further includes one or more of the following: a second operation indicator of the target analysis logic function network element, or a vendor identifier of the target analysis logic function network element; the second operation indicator being used to indicate a provider of a model that can be used by the target analysis logic function network element.

15. The method of claim 14, wherein, Before the source analysis logic function network element sends the token acquisition request to the network storage function NRF network element, the method further includes: The source analysis logic function network element determines whether the provider of the first model is located in the second operation indicator of the target analysis logic function network element.

16. The method of claim 14, wherein, Before the source analysis logic function network element sends the token acquisition request to the network storage function NRF network element, the method further includes: The source analytics logic function determines that the vendor identity of the target analytics logic function network element is contained in the interoperability indicator of the information provider of the first model.

17. The method according to any one of claims 13 to 16, characterized in that, The method further comprises, before the source analytics logic function network element receives the analytics context transfer request from the target analytics logic function network element: The source analytics logic function network element sends a network element registration request to the NRF network element, the network element registration request comprising a first operation indicator of the source analytics logic function network element, the first operation indicator being used to indicate the provider of the model that the source analytics logic function network element can use.

18. The method according to any one of claims 13 to 17, characterized in that, The token obtaining request further comprises one or more of the following: the identity of the source analytics logic function network element, the vendor identity of the target analytics logic function network element, the identity of the first model, or first indication information; The first indication information is used to indicate that the source analytics logic function network element requests a first token for the target analytics logic function network element.

19. The method according to any one of claims 13 to 18, characterized in that, The first token further comprises one or more of the following: the analytics identity, the identity of the source analytics logic function network element, the vendor identity of the target analytics logic function network element, the identity of the first model, or second indication information; The second indication information is used to indicate that the target analytics logic function network element is authorized to obtain the information of the first model from the model training logic function network element.

20. The method of any one of claims 13-19, wherein, The model obtaining request further comprises one or more of the following: the identity of the source analytics logic function network element, the address of the target analytics logic function network element, the identity of the first model, the vendor identity of the target analytics logic function network element, or third indication information; The third indication information is used to indicate that the source analytics logic function network element obtains the information of the first model for the target analytics logic function network element.

21. A model authorization method characterized by comprising: Comprise: The network storage function (NRF) network element receives a token obtaining request from a source analytics logic function network element, the token obtaining request comprising an analytics identity, an identity of a target analytics logic function network element, and an identity of a model training logic function network element used to provide information of a first model corresponding to the analytics identity; The NRF network element verifies whether a vendor identity of the target analytics logic function network element is contained in an interoperability indicator corresponding to the analytics identity of the model training logic function network element; If the vendor identity is contained in the interoperability indicator, the NRF network element sends a first token to the source analytics logic function network element, the first token comprising the identity of the target analytics logic function network element and the identity of the model training logic function network element.

22. The method of claim 21, wherein, The method further comprises, before the NRF network element verifies whether the vendor identity of the target analytics logic function network element is contained in the interoperability indicator of the model training logic function network element: The NRF network element obtains the interoperability indicator corresponding to the analytics identity of the model training logic function network element from a network function (NF) configuration file corresponding to the identity of the model training logic function network element.

23. The method of claim 21 or 22, wherein, Before the NRF network element verifies whether the vendor identifier of the target analytics logical function network element is contained in the interoperability indicator of the model training logical function network element, the method further comprises: The NRF network element obtains the vendor identifier of the target analytics logical function network element from the NF profile corresponding to the identification of the target analytics logical function network element.

24. The method of any one of claims 21-23, wherein, The token obtaining request further comprises one or more of the following: the identification of the source analytics logical function network element, the vendor identifier of the target analytics logical function network element, the identification of the first model, or first indication information; The first indication information is used to indicate that the source analytics logical function network element requests a first token for the target analytics logical function network element.

25. The method of any one of claims 21-24, wherein, The first token further comprises one or more of the following: the analysis identifier, the identification of the source analytics logical function network element, the vendor identifier of the target analytics logical function network element, the identification of the first model, or second indication information; The second indication information is used to indicate that the target analytics logical function network element is authorized to obtain the information of the first model from the model training logical function network element.

26. The method of any one of claims 21-25, wherein, Before the network storage function NRF network element receives the token obtaining request from the source analytics logical function network element, the method further comprises: The NRF network element receives a first network element registration request from the source analytics logical function network element, and the first network element registration request comprises a first operation indicator of the source analytics logical function network element, and the first operation indicator is used to indicate the provider of the model that can be used by the source analytics logical function network element.

27. The method of any one of claims 21-26, wherein, Before the network storage function NRF network element receives the token obtaining request from the source analytics logical function network element, the method further comprises: The NRF network element receives a second network element registration request from the target analytics logical function network element, and the second network element registration request comprises a second operation indicator of the target analytics logical function network element, and the second operation indicator is used to indicate the provider of the model that can be used by the target analytics logical function network element.

28. A communications device, characterized by The communication device comprises a processor and a readable storage medium storing program instructions.

29. A readable storage medium, characterized by, The readable storage medium stores program instructions, and when the program instructions run on the communication device, the communication device executes the method in any one of claims 1 to 27.

30. A communication system, characterized by The communication system comprises: The first model training logical function network element for executing the method in any one of claims 1 to 5 and the NRF network element for executing the method in any one of claims 6 to 12; or the communication system comprises: the source analytics logical function network element for executing the method in any one of claims 13 to 20 and the NRF network element for executing the method in any one of claims 21 to 27.

Images