Information interaction method and device and readable storage medium

Abstract

The invention relates to the technical field of communication, in particular to an information interaction method and device and a readable storage medium, and the method comprises the steps that an ADRF receives a model storage request sent by an NWDAF including an MTLF, the request is used for storing a model, and the request does not include an allowed NFc list corresponding to the model; the ADRF generates an allowed NFc list for the model, wherein the allowed NFc list comprises an NF instance identifier of a second network element; the method is convenient to use during subsequent NWDAF retrieval containing the AnLF; and the ADRF returns a model storage response. By adopting the method and the device, the storage scheme of the model can be perfected, and under the condition that the NWDAF containing the MTLF does not specify an allowed NFc list, the model acquisition permissions at the two ends of the NWDAF containing the MTLF and the ADRF containing the MTLF can be aligned (or synchronized).

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to an information interaction method, device and readable storage medium. Background Art

[0002] The network data analytics function (NWDAF) network element has functions such as data collection, model training, data analysis, and model reasoning. The NWDAF network element containing the analytics logical function (AnLF) can be used to infer and export analysis information and expose analysis services. The NWDAF network element containing the 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, provide trained AI models or ML models. The analytics data repository functional (ADRF) network element can provide storage, deletion, and retrieval of AI / ML model services.

[0003] AI / ML models can be stored in ADRF network elements in the following ways: the consumer (for example, NWDAF network elements containing MTLF) sends a Nadrf_MLModelManagement_StorageRequest (Nadrf machine learning model management storage request) to the ADRF network element, which contains the model or the address of the model to be stored; the ADRF network element returns a response and provides an indication of the result. AI / ML models can be retrieved from ADRF network elements in the following ways: the consumer (for example, NWDAF network elements containing AnLF) sends a Nadrf_MLModelManagement_Retrieval Request (Nadrf machine learning model management retrieval request) to the ADRF network element, which contains one or more of the following: the analytics identifier (ID), the model ID stored in the ADRF network element, or the storage transaction ID stored in the ADRF network element; the ADRF network element returns a response and provides an indication of the result. AI / ML models can be deleted from ADRF network elements in the following ways: the consumer (for example, NWDAF network element containing MTLF) sends Nadrf_MLModelManagement_DeleteRequest (Nadrf machine learning model management deletion request) to the ADRF network element, which contains the model or the address of the model to be deleted; the ADRF network element returns a response and provides a result indication.

[0004] Currently, the storage and retrieval scheme of the model is imperfect. Summary of the invention

[0005] The embodiment of the present application provides an information interaction method, device and readable storage medium, which can improve the storage solution of the model. When the model producer does not specify the allowed network function consumer list (allowed NFc list), or the allowed NFc list does not exist in the model storage request, it can also align (or synchronize) the model acquisition permissions of the NWDAF and ADRF containing MTLF, and clarify the judgment logic of ADRF during model authorization check. Furthermore, the security of model acquisition can also be improved.

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

[0007] In a first aspect, the present application provides an information interaction method, the method comprising: a first network element receives a first request from a second network element, the first request being used to request a storage model, the first request including a network function (NF) instance identifier (NF instance ID) of the second network element, and the first request not including an allowed NF consumer (NF consumer, NFc) list (allowed NFc list) corresponding to the model; the first network element generates an allowed NF consumer list (allowed NFc list) for the model, wherein the allowed NF consumer list includes the NF instance identifier of the second network element, and the NF instance identifier of the second network element included in the allowed NF consumer list is used to authorize the model; the first network element sends a first response to the first request to the second network element.

[0008] In the present application, the first network element may be an ADRF. The second network element may be an NWDAF including an MTLF, or an NWDAF including an MTLF and an AnLF. The details will not be described in detail below.

[0009] In this application, when the storage request (i.e., the first request mentioned above) does not carry the allowed NFc list of the model, ADRF generates an allowed NFc list for the model, and the allowed NFc list includes the NF instanceID of the second network element. In this way, the model authorization check logic of ADRF can be used, that is, to determine whether the NFinstance ID carried by the model retrieval / acquisition request is in the allowed NFc list to determine the authorization status of the model. Therefore, this application aligns (or synchronizes) the model acquisition permissions at both ends of the first network element and the second network element by improving the storage solution of the model.

[0010] In combination with the first aspect, in a possible implementation, the first request further includes a model identifier of the model. After the first network element generates an allowed NF consumer list (allowed NFc list) for the model, the method further includes: the first network element stores the NF instance identifier of the second network element, the allowed NF consumer list, and the model identifier for subsequent use. For example, it is used in subsequent model retrieval or model acquisition. For details, please refer to the description below, which will not be elaborated here.

[0011] Exemplarily, the first request further includes but is not limited to: the address of the model in the second network element.

[0012] Exemplarily, if the first network element generates a storage transaction identifier in response to the first request, the first network element may further store the storage transaction identifier for subsequent use.

[0013] In combination with the first aspect, in a possible implementation, the first response includes the model identifier, or the first response includes the model identifier and the storage transaction identifier. After the first network element sends the first response to the first request to the second network element, the method further includes: the first network element receives a second request, the second request is used to request to obtain the model; when the NF instance identifier carried by the second request is in the allowed NF consumer list, the first network element sends a second response to the second request, the second response carries the information of the model stored by the first network element. Among them, the second request includes the NF instance identifier, and the second request also includes the model identifier or the storage transaction identifier; the model identifier or the storage transaction identifier can be used to index the model. The second response includes one or more of the following: the storage address of the model in the first network element, or the model file of the model. Optionally, the second response also includes the identifier of the first network element.

[0014] Exemplarily, when the NF instance identifier carried in the second request is not in the allowed NF consumer list, the first network element rejects the second request.

[0015] This application does not carry the allowed NFc list of the model when storing the model. When retrieving / obtaining the model, the model will not be returned to network elements other than the model producer (i.e., the second network element). The judgment logic of ADRF during model authorization check is clarified, which can not only reduce the risk of model leakage caused by the fact that the allowed NFc list does not exist and ADRF believes that the model has no permission restrictions and sends the model to unauthorized network elements, but also improve security; it can also solve the problem that because the allowedNFc list does not exist, ADRF believes that all network elements cannot obtain the model and rejects all retrieval requests, resulting in the model producer (i.e., the second network element) being unable to obtain the model.

[0016] In combination with the first aspect, in a possible implementation, the first request further includes first indication information, and the first indication information is used to indicate that the second network element has not authorized other network elements to obtain the above model. Alternatively, the first indication information is used to indicate that the above model is not allowed to be obtained by other network elements (i.e., other network elements except the second network element), or is used to indicate that the second network element has not authorized any network element to obtain the above model.

[0017] The "other network elements" in this application may refer to other NWDAF network elements, or any network element in the network except the second network element, and this application does not limit this. Similarly, the "any network element" in this application may refer to any NWDAF network element, or any network element in the network. This will not be repeated below.

[0018] The present application indicates that the second network element has not authorized other network elements to obtain the above model by carrying indication information in the storage request (i.e. the above first request). Its meaning is clear and its implementation is simple.

[0019] In combination with the first aspect, in a possible implementation, after the first network element receives a first request from the second network element, the method also includes: the first network element determines that the second network element has not authorized other network elements to obtain the above-mentioned model, or determines that the above-mentioned model is not allowed to be obtained by other network elements (i.e., other network elements except the second network element) based on the fact that the first request does not include the allowed NF consumer list corresponding to the above-mentioned model.

[0020] Exemplarily, before the first network element receives the first request from the second network element, such as in the network element registration process, the method further includes: the first network element sends a third request to the network repository function (NRF) network element, the third request is used to notify or register the NF configuration file of the first network element to the NRF network element, the third request includes second indication information, the second indication information is used to indicate that when the allowed network function NF consumer list corresponding to the model does not exist, other network elements cannot obtain the model. Then, the second network element discovers the first network element according to the network element discovery process, and can obtain the model authorization logic of the first network element when the allowed NFc list does not exist from the NRF network element. Then, the second network element decides to store the model in the first network element according to the model authorization logic of the first network element and its own storage policy, such as sending the above-mentioned first request. Therefore, after the first network element receives the above-mentioned first request, it can be determined that the second network element does not authorize other network elements to obtain the above-mentioned model, or the model is not allowed to be obtained by other network elements (other network elements except the second network element) according to the first request does not include the allowed NFc list corresponding to the above-mentioned model and the locally pre-configured model authorization logic.

[0021] The present application pre-configures the model authorization logic when the allowed NFc list does not exist in advance, so as to not only align (or synchronize) the model acquisition permissions at both ends of the first network element and the second network element, but also save signaling overhead.

[0022] Exemplarily, when the allowed NFc list corresponding to the predefined model in the standard protocol does not exist, it means that the model producer (such as the NWDAF network element containing MTLF) has not authorized other network elements to obtain the model, or the model is not allowed to be obtained by other network elements (other network elements except the model producer). Then, when the above-mentioned first request does not include the allowed NF consumer list corresponding to the above-mentioned model, it means that the second network element has not authorized other network elements to obtain the above-mentioned model.

[0023] The present application predefines the model authorization logic when the allowed NFc list does not exist in the standard protocol, which can not only align (or synchronize) the model acquisition permissions at both ends of the first network element and the second network element, but also reduce signaling interaction and save overhead.

[0024] In combination with the first aspect, in a possible implementation, after the first network element sends a first response to the above-mentioned first request to the second network element, the method also includes: the first network element receives a fourth request, the fourth request is used to request to update or delete the above-mentioned model, and the fourth request includes an NF instance identifier; if the NF instance identifier carried by the fourth request is the NF instance identifier of the second network element, the first network element processes the above-mentioned model according to the fourth request.

[0025] Exemplarily, the fourth request may include an NF instance identifier, and the fourth request may also include the above-mentioned model identifier or storage transaction identifier. The model identifier or storage transaction identifier may be used to index the model, and may also be used to index the NF instance identifier of the second network element.

[0026] In a second aspect, the present application provides an information interaction method, which includes: a second network element sends a first request to a first network element, the first request is used to request a storage model, the first request includes an NF instance identifier (NFinstance ID) of the second network element, and the first request does not include an allowed NF consumer list (allowed NFclist) corresponding to the model; the second network element receives a first response from the first network element.

[0027] In combination with the second aspect, in a possible implementation manner, the first request further includes a model identifier of the model.

[0028] In combination with the second aspect, in a possible implementation, the above-mentioned first response includes the above-mentioned model identifier, or the above-mentioned first response includes the above-mentioned model identifier and the storage transaction identifier. After the second network element receives the first response from the first network element, the method also includes: the second network element sends a second request to the first network element, and the second request is used to request to obtain the above-mentioned model; the second network element receives a second response from the first network element, and the second response carries the information of the model stored by the first network element. Among them, the second request includes the NF instance identifier, and the second request also includes the above-mentioned model identifier or the storage transaction identifier; the model identifier or the storage transaction identifier can be used to index the above-mentioned model. The second response includes one or more of the following: the storage address of the above-mentioned model in the first network element, or the model file of the above-mentioned model. Optionally, the second response also includes the identifier of the first network element.

[0029] In conjunction with the second aspect, in a possible implementation, the first request further includes first indication information, and the first indication information is used to indicate that the second network element has not authorized other network elements to obtain the above model. Alternatively, the first indication information is used to indicate that the above model is not allowed to be obtained by other network elements (i.e., other network elements except the second network element), or is used to indicate that the second network element has not authorized any network element to obtain the above model.

[0030] In combination with the second aspect, in a possible implementation method, when the allowed NFc list corresponding to the predefined model in the standard protocol does not exist, it means that the model producer (such as the NWDAF network element containing MTLF) has not authorized other network elements to obtain the model, or the model is not allowed to be obtained by other network elements (other network elements except the model producer).

[0031] In combination with the second aspect, in a possible implementation, after the second network element receives the first response from the first network element, the method further includes: the second network element sends a fourth request to the first network element, the fourth request is used to request to update or delete the above-mentioned model, and the fourth request includes an NF instance identifier. Exemplarily, the fourth request may include an NF instance identifier, and the fourth request may also include the above-mentioned model identifier or storage transaction identifier. Among them, the model identifier or storage transaction identifier can be used to index the model, and can also be used to index the NF instance identifier of the second network element.

[0032] In a third aspect, the present application provides an information interaction method, the method comprising: a first network element receives a first request from a second network element, the first request is used to request the storage of a model, the first request includes: a model identifier of the model, and an NF instance identifier of the second network element, the first request does not include a list of allowed NF consumers corresponding to the model; the first network element stores the NF instance identifier of the second network element and the model identifier; the first network element sends a first response to the first request to the second network element; the first network element receives a second request, the second request is used to request to obtain the model; when the NF instance identifier carried by the second request is the stored NF instance identifier of the second network element, the first network element sends a second response to the second request, the second response carrying information of the model stored by the first network element.

[0033] Exemplarily, when the NF instance identifier carried in the second request is not the stored NF instance identifier of the second network element, the first network element rejects the second request.

[0034] The first network element may be an ADRF, and the second network element may be an NWDAF including an MTLF, or an NWDAF including an MTLF and an AnLF.

[0035] When the storage request (i.e., the first request mentioned above) does not carry the allowed NFc list of the model, this application indicates that the model producer (i.e., the second network element) has not authorized other network elements to obtain the model, which can improve the storage solution of the model and align (or synchronize) the model acquisition permissions of the first network element and the second network element. When retrieving / acquiring the model, ADRF will not return the model to other network elements except the model producer (i.e., the second network element), and clarifies the judgment logic of ADRF during model authorization check. It can not only reduce the risk of model leakage caused by the non-existence of the allowed NFc list and the sending of the model to unauthorized network elements by ADRF as it believes that the model has no permission restrictions, but also improve security; it can also solve the problem that the model producer (i.e., the second network element) cannot access the model because ADRF believes that all network elements cannot access the model due to the non-existence of the allowed NFclist.

[0036] In combination with the third aspect, in a possible implementation, after the first network element receives the first request from the second network element, the method further includes: the first network element generates an allowed NF consumer list for the above model, wherein the allowed NF consumer list is empty.

[0037] The first network element of the present application generates an empty allowed NF consumer list for the above model, which is conducive to the subsequent update of the allowed NF consumer list.

[0038] In conjunction with the third aspect, in a possible implementation, the first request further includes first indication information, and the first indication information is used to indicate that the second network element has not authorized other network elements to obtain the above model. Alternatively, the first indication information is used to indicate that the above model is not allowed to be obtained by other network elements (i.e., other network elements except the second network element), or is used to indicate that the second network element has not authorized any network element to obtain the above model.

[0039] The present application indicates that the second network element has not authorized other network elements to obtain the above model by carrying indication information in the storage request (i.e. the above first request). Its meaning is clear and its implementation is simple.

[0040] In combination with the third aspect, in a possible implementation, after the first network element receives the first request from the second network element, the method also includes: the first network element determines that the second network element has not authorized other network elements to obtain the above-mentioned model, or determines that the above-mentioned model is not allowed to be obtained by other network elements (i.e., other network elements except the second network element) based on the fact that the first request does not include the allowed NF consumer list corresponding to the above-mentioned model.

[0041] Exemplarily, before the first network element receives the first request from the second network element, such as in the network element registration process, the method further includes: the first network element sends a third request to the NRF network element, the third request is used to notify or register the NF configuration file of the first network element to the NRF network element, the third request includes second indication information, the second indication information is used to indicate that when the allowed network function NF consumer list corresponding to the model does not exist, other network elements cannot obtain the model. Then, the second network element discovers the first network element according to the network element discovery process, and can obtain the model authorization logic of the first network element when the allowed NFc list does not exist from the NRF network element. Then, the second network element decides to store the model in the first network element according to the model authorization logic of the first network element and its own storage policy, such as sending the above-mentioned first request. Therefore, after the first network element receives the above-mentioned first request, it can be determined that the second network element does not authorize other network elements to obtain the above-mentioned model, or the model is not allowed to be obtained by other network elements (other network elements except the second network element) according to the first request does not include the allowed NFc list corresponding to the above-mentioned model and the locally pre-configured model authorization logic.

[0042] The present application pre-configures the model authorization logic when the allowed NFc list does not exist in advance, so as to not only align (or synchronize) the model acquisition permissions at both ends of the first network element and the second network element, but also save signaling overhead.

[0043] Exemplarily, when the allowed NFc list corresponding to the predefined model in the standard protocol does not exist, it means that the model producer (such as the NWDAF network element containing MTLF) has not authorized other network elements to obtain the model, or the model is not allowed to be obtained by other network elements (other network elements except the model producer). Then, when the above-mentioned first request does not include the allowed NF consumer list corresponding to the above-mentioned model, it means that the second network element has not authorized other network elements to obtain the above-mentioned model.

[0044] The present application predefines the model authorization logic when the allowed NFc list does not exist in the standard protocol, which can not only align (or synchronize) the model acquisition permissions at both ends of the first network element and the second network element, but also reduce signaling interaction and save overhead.

[0045] In combination with the third aspect, in a possible implementation, after the first network element sends a first response to the above-mentioned first request to the second network element, the method also includes: the first network element receives a fourth request, the fourth request is used to request to update or delete the above-mentioned model, and the fourth request includes an NF instance identifier; if the NF instance identifier carried by the fourth request is the NF instance identifier of the second network element, the first network element processes the above-mentioned model according to the fourth request.

[0046] Exemplarily, the fourth request may include an NF instance identifier, and the fourth request may also include the above-mentioned model identifier or storage transaction identifier. The model identifier or storage transaction identifier may be used to index the model, and may also be used to index the NF instance identifier of the second network element.

[0047] In a fourth aspect, the present application provides an information interaction method, the method comprising: a second network element sends a first request to a first network element, the first request is used to request the storage of a model, the first request includes: a model identifier of the model, and an NF instance identifier of the second network element, the first request does not include an allowed NF consumer list (allowed NFclist) corresponding to the model; the second network element receives a first response from the first network element; the second network element sends a second request to the first network element, the second request is used to request to obtain the model; the second network element receives a second response from the first network element, the second response carries information about the model stored by the first network element.

[0048] In conjunction with the fourth aspect, in a possible implementation, the first request further includes first indication information, and the first indication information is used to indicate that the second network element has not authorized other network elements to obtain the above model. Alternatively, the first indication information is used to indicate that the above model is not allowed to be obtained by other network elements (i.e., other network elements except the second network element), or is used to indicate that the second network element has not authorized any network element to obtain the above model.

[0049] In combination with the fourth aspect, in a possible implementation method, when the allowed NFc list corresponding to the predefined model in the standard protocol does not exist, it means that the model producer (such as the NWDAF network element containing MTLF) has not authorized other network elements to obtain the model, or the model is not allowed to be obtained by other network elements (other network elements except the model producer).

[0050] In combination with the fourth aspect, in a possible implementation, after the second network element receives the first response from the first network element, the method also includes: the second network element sends a fourth request to the first network element, the fourth request is used to request to update or delete the above-mentioned model, and the fourth request includes an NF instance identifier.

[0051] Exemplarily, the fourth request may include an NF instance identifier, and the fourth request may also include the above-mentioned model identifier or storage transaction identifier. The model identifier or storage transaction identifier may be used to index the model, and may also be used to index the NF instance identifier of the second network element.

[0052] In a fifth aspect, the present application provides an information interaction method, the method comprising: a first network element receives a first request from a second network element, the first request being used to request storage of a model, the first request comprising a model identifier of the model, and indication information, the indication information being used to indicate that the second network element authorizes all network elements to obtain the model (or being used to indicate that the model is allowed to be obtained by all network elements); the first network element sends a first response to the first request to the second network element; the first network element receives a second request from a third network element, the second request being used to request acquisition of the model; the first network element sends a second response to the second request to the third network element according to the indication information, the second response carrying information of the model stored by the first network element.

[0053] Exemplarily, the second response includes one or more of the following: the storage address of the above-mentioned model in the first network element, or the model file of the above-mentioned model. Optionally, the second response also includes the identifier of the first network element. The second request includes the NF instance identifier, and the second request also includes the above-mentioned model identifier or the storage transaction identifier; the model identifier or the storage transaction identifier can be used to index the above-mentioned model.

[0054] The first network element may be an ADRF. The second network element may be an NWDAF including an MTLF, or an NWDAF including an MTLF and an AnLF. The third network element may be an NWDAF including an AnLF. This will not be described in detail below.

[0055] "All network elements" in this application may refer to all NWDAF network elements or any network element in the network. This application does not impose any limitation and will not be further described below.

[0056] The present application carries the indication information of the model in the storage request (i.e., the first request mentioned above) to indicate that all network elements can obtain the model, thereby improving the storage solution of the model and aligning (or synchronizing) the model acquisition permissions at both the first network element and the second network element.

[0057] In conjunction with the fifth aspect, in a possible implementation, after the first network element receives the first request from the second network element, the method further includes: the first network element stores the above-mentioned model identifier and the above-mentioned indication information for subsequent use. Here, the first network element storing the indication information can be understood as the first network element storing the content indicated by the indication information carried by the above-mentioned first request, that is, the indication information stored by the first network element may not be the information element carrying the indication information in the first request, but the content actually indicated by the indication information.

[0058] In combination with the fifth aspect, in a possible implementation, the first request further includes a list of allowed NF consumers corresponding to the model, and the indication information is located in the list of allowed NF consumers.

[0059] In combination with the fifth aspect, in a possible implementation manner, the first response includes the model identifier, or the first response includes the model identifier and the storage transaction identifier.

[0060] Exemplarily, the first network element sends a second response to the second request to the third network element based on the indication information, including: if the model identifier or storage transaction identifier carried by the second request corresponds to the indication information, the first network element sends a second response to the second request to the third network element.

[0061] In conjunction with the fifth aspect, in a possible implementation, the first request also includes the NF instance identifier of the second network element. After the first network element receives the first request from the second network element, the first network element may also store the NF instance identifier of the second network element, thereby recording the NF instance identifier of the second network element, the model identifier, and the indication information. It is understood that if the first network element generates a storage transaction identifier for the first request, the first network element may also store the storage transaction identifier for subsequent use.

[0062] Exemplarily, the first request also includes, but is not limited to: the address of the above model in the second network element.

[0063] Exemplarily, after the first network element sends a first response to the above-mentioned first request to the second network element, the method further includes: the first network element receives a fourth request from the second network element, the fourth request is used to request to update or delete the model, and the fourth request includes an NF instance identifier; if the NF instance identifier carried by the fourth request is the NF instance identifier of the second network element, the first network element processes the model according to the fourth request. The fourth request may include the NF instance identifier, and the fourth request may also include the above-mentioned model identifier or storage transaction identifier. The model identifier or the storage transaction identifier can be used to index the model, and can also be used to index the NF instance identifier of the second network element.

[0064] In a sixth aspect, the present application provides an information interaction method, the method comprising: a second network element sends a first request to a first network element, the first request is used to request a storage model, the first request comprises: a model identifier of the model, and indication information, the indication information is used to indicate that the second network element authorizes all network elements to obtain the model; the second network element receives a first response from the first network element.

[0065] In conjunction with the sixth aspect, in a possible implementation, the first request further includes a list of allowed NF consumers corresponding to the model, and the indication information is located in the list of allowed NF consumers. Exemplarily, the first request further includes but is not limited to: an NF instance identifier of the second network element, and / or an address of the model in the second network element.

[0066] In combination with the sixth aspect, in a possible implementation manner, the first response includes the model identifier, or the first response includes the model identifier and the storage transaction identifier.

[0067] In combination with the sixth aspect, in a possible implementation, the first response includes the model identifier and the storage transaction identifier. After the second network element receives the first response from the first network element, the method further includes: the second network element receives a model provision request from a third network element, the model provision request includes the analysis identifier of the model, and the model provision request is used to request the second network element to provide the model; the second network element sends a model provision response to the third network element. Among them, when the model authorized to be obtained by the third network element in the model corresponding to the analysis identifier has a storage transaction identifier, and all the models corresponding to the storage transaction identifier are authorized to be obtained by the third network element, the model provision response includes the storage transaction identifier. In other cases, the model provision response includes the model identifier of the model. For example: when the model authorized to be obtained by the third network element in the model corresponding to the analysis identifier has a storage transaction identifier, and the model corresponding to the storage transaction identifier contains a model that is not authorized to be obtained by the third network element, the model provision response includes the model identifier of the model.

[0068] This application returns the storage transaction identifier to the third network element when all the models corresponding to the storage transaction identifier of a certain model authorized to be obtained by the third network element in the model corresponding to the analysis identifier are authorized to be obtained by the third network element; otherwise, the model identifier authorized to be obtained by the third network element in the model corresponding to the analysis identifier is returned to the third network element. This not only clarifies the processing logic of the second network element returning the storage transaction identifier or the model identifier, but also reduces the risk of the third network element unauthorizedly obtaining the model from the first network element (such as ADRF) through the storage transaction identifier.

[0069] In combination with the sixth aspect, in a possible implementation method, the above-mentioned first request also includes the NF instance identifier of the second network element.

[0070] In conjunction with the sixth aspect, in a possible implementation, after the second network element receives the first response from the first network element, the method further includes: the second network element sends a fourth request to the first network element, the fourth request is used to request to update or delete the model, and the fourth request includes an NF instance identifier. Among them, the fourth request may include the NF instance identifier, and the fourth request may also include the above-mentioned model identifier or storage transaction identifier. The model identifier or the storage transaction identifier can be used to index the model, and can also be used to index the NF instance identifier of the second network element.

[0071] In a seventh aspect, the present application provides an information interaction method, the method comprising: a third network element sends a second request to a first network element, the second request is used to request to obtain the model; the third network element receives a second response from the first network element, the second response carries information about the model stored by the first network element. The second request includes an NF instance identifier, and also includes a model identifier or a storage transaction identifier.

[0072] Exemplarily, the second response includes one or more of the following: the storage address of the above-mentioned model in the first network element, or the model file of the above-mentioned model. Optionally, the second response also includes the identifier of the first network element. The second request includes the NF instance identifier, and the second request also includes the above-mentioned model identifier or the storage transaction identifier; the model identifier or the storage transaction identifier can be used to index the above-mentioned model.

[0073] In conjunction with the seventh aspect, in a possible implementation, before the third network element sends the second request to the first network element, the method further includes: the third network element sends a model provision request to the second network element, the model provision request includes the analysis identifier of the model, and the model provision request is used to request the second network element to provide the model; the third network element receives a model provision response from the second network element, and the model provision response includes the model identifier or storage transaction identifier of the model. Wherein, when the model authorized to be obtained by the third network element in the model corresponding to the analysis identifier has a storage transaction identifier, and all the models corresponding to the storage transaction identifier are authorized to be obtained by the third network element, the model provision response includes the storage transaction identifier. In other cases, the model provision response includes the model identifier of the model. For example: when the model authorized to be obtained by the third network element in the model corresponding to the analysis identifier has a storage transaction identifier, and the model corresponding to the storage transaction identifier contains a model that is not authorized to be obtained by the third network element, the model provision response includes the model identifier of the model.

[0074] This application returns the storage transaction identifier to the third network element when all the models corresponding to the storage transaction identifier of a certain model authorized to be obtained by the third network element in the model corresponding to the analysis identifier are authorized to be obtained by the third network element; otherwise, the model identifier authorized to be obtained by the third network element in the model corresponding to the analysis identifier is returned to the third network element. This not only clarifies the processing logic of the second network element returning the storage transaction identifier or the model identifier, but also reduces the risk of the third network element unauthorizedly obtaining the model from the first network element (such as ADRF) through the storage transaction identifier.

[0075] In an eighth aspect, the present application provides an information interaction method, the method comprising: the second network element determines a second model based on the first model; the second network element sends a storage request to the first network element, the storage request being used to request storage of the second model in the first network element, the storage request comprising: a list of allowed NF consumers corresponding to the second model; wherein the list of allowed NF consumers corresponding to the second model is determined based on the list of allowed NF consumers corresponding to the first model.

[0076] Exemplarily, the storage request also includes, but is not limited to: the NF instance ID of the second network element, the model ID of the second model, and the storage address of the second model in the second network element.

[0077] The first network element may be an ADRF. The second network element may be an NWDAF including an MTLF, or an NWDAF including an MTLF and an AnLF. Details will not be given hereinafter.

[0078] The embodiment of the present application determines the second model based on the existing first model, and uses the allowed NFc list of the existing model (i.e., the first model) to replace the allowed NFc list of the latest generated model (i.e., the second model), thereby clarifying / improving the setting method of model acquisition permissions in the retraining scenario.

[0079] In conjunction with the eighth aspect, in a possible implementation, the second network element determines the second model based on the first model, including: the second network element re-provides the second model based on the accuracy of the first model. For example, the second network element finds that the accuracy of the first model is lower than a preset threshold according to its own internal logic, and determines to regenerate a new model (i.e., the second model) to implement the same or similar function.

[0080] Exemplarily, the second network element re-provides the second model based on the accuracy of the first model, and also includes: the second network element retrains the first model to obtain the second model.

[0081] In conjunction with the eighth aspect, in a possible implementation, the allowed NF consumer list corresponding to the second model is determined based on the allowed NF consumer list corresponding to the first model, including: the allowed NF consumer list corresponding to the second model is the same as the allowed NF consumer list corresponding to the first model. Exemplarily, the second network element uses the allowed NF consumer list corresponding to the first model as the allowed NF consumer list corresponding to the second model.

[0082] In a ninth aspect, the present application provides an information interaction method, the method comprising: a first network element receives a storage request from a second network element, the storage request is used to request to store a second model in the first network element, the storage request includes: a list of allowed NF consumers corresponding to the second model. Exemplarily, the storage request also includes but is not limited to: an NF instance ID of the second network element, a model ID of the second model, and a storage address of the second model in the second network element.

[0083] In a tenth aspect, the present application provides an information interaction method, the method comprising: a second network element receives a model provision request from a third network element, the model provision request includes an analysis identifier, the model provision request is used to request the second network element to provide a first model corresponding to the analysis identifier, and the analysis identifier corresponds to a storage transaction identifier; the second network element sends a model provision response to the third network element. Wherein, when the second model corresponding to the storage transaction identifier is authorized to the third network element for acquisition, the model provision response includes the storage transaction identifier. Or, when the second model corresponding to the storage transaction identifier is not authorized to the third network element for acquisition, the model provision response does not include the storage transaction identifier.

[0084] Exemplarily, the second models corresponding to the above-mentioned storage transaction identifier are not all authorized to be acquired by the third network element. It can be understood that the second model corresponding to the storage transaction identifier includes a model that is not authorized to be acquired by the third network element.

[0085] Exemplarily, the above-mentioned model provides a response that does not include the storage transaction identifier. It can be understood that the model provides a response that includes the identifier of the model in the first model corresponding to the above-mentioned analysis identifier that is authorized to be obtained by the third network element.

[0086] It can be understood that the analysis identifier can be used to identify the function / role of the model, and there may be multiple models used to implement the same function. Therefore, one analysis identifier may correspond to one or more models. A storage transaction identifier can be understood as a credential for one storage, and one or more models can be stored at one time, so a storage transaction identifier can index one or more models. Therefore, the analysis identifier and the storage transaction identifier can generate a corresponding relationship through the model. For example, one analysis identifier can correspond to one or more storage transaction identifiers.

[0087] Exemplarily, the analysis identifier carried in the above-mentioned model providing request corresponds to the storage transaction identifier, which can be understood as: the first model corresponding to the analysis identifier carried in the above-mentioned model providing request contains a model authorized to be acquired by the third network element, and the model authorized to be acquired by the third network element has a storage transaction identifier. Then, when all the models corresponding to this storage transaction identifier are authorized to be acquired by the third network element, the model providing response includes this storage transaction identifier. Or, in other cases other than this, that is, the models corresponding to this storage transaction identifier are not all authorized to be acquired by the third network element, the model providing response does not include this storage transaction identifier, for example, the model providing response includes the identifier of the model authorized to be acquired by the third network element in the first model corresponding to the analysis identifier.

[0088] The second network element may be a NWDAF including a MTLF, or a NWDAF including a MTLF and an AnLF. The third network element may be a NWDAF including an AnLF.

[0089] This application returns the storage transaction identifier to the third network element when all the models corresponding to the storage transaction identifier of a certain model authorized to be obtained by the third network element in the model corresponding to the analysis identifier are authorized to be obtained by the third network element; otherwise, the model identifier authorized to be obtained by the third network element in the model corresponding to the analysis identifier is returned to the third network element. This not only clarifies the processing logic of the second network element returning the storage transaction identifier or the model identifier, but also reduces the risk of the third network element unauthorizedly obtaining the model from the first network element (such as ADRF) through the storage transaction identifier.

[0090] In an eleventh aspect, the present application provides an information interaction method, the method comprising: a third network element sends a model provision request to a second network element, the model provision request includes an analysis identifier of the model, the model provision request is used to request the second network element to provide a first model corresponding to the analysis identifier, and the analysis identifier corresponds to a storage transaction identifier; the third network element receives a model provision response from the second network element. The model provision response includes an identifier of a model authorized to be obtained by the third network element in the first model corresponding to the analysis identifier or the storage transaction identifier.

[0091] In a twelfth aspect, the present application provides an information interaction method, the method comprising: a first network element receives a second request from a third network element, the second request is used to request to obtain a model from the first network element, and the second request includes a storage transaction identifier; the first network element sends a second response to the second request to the third network element. Wherein, if there is a model authorized to be obtained by the third network element in the model corresponding to the storage transaction identifier carried by the second request, the second response may include the model authorized to be obtained by the third network element in the model corresponding to the storage transaction identifier and / or the address of the model in the first network element. Alternatively, if the model corresponding to the storage transaction identifier carried by the second request is not fully authorized to be obtained by the third network element, the second response can be used to reject the second request.

[0092] It can be understood that the storage transaction identifier carried in the second request may be obtained by the third network element from the second network element (such as NWDAF including MTLF) through a model providing request.

[0093] The first network element is ADRF, and the third network element is NWDAF including AnLF.

[0094] When the third network element of the present application uses a storage transaction identifier to retrieve / acquire a model, after receiving the storage transaction identifier, the first network element returns to the third network element only the model corresponding to the storage transaction identifier that is authorized for the third network element to acquire; or, if not all the models corresponding to the storage transaction identifier are authorized for the third network element to acquire, the request of the third network element is rejected. The processing logic after the ADRF side receives the storage transaction identifier is clarified, and the solution is improved.

[0095] In a thirteenth aspect, the present application provides a communication device, which may be a first network element or a second network element, or a chip therein. The communication device includes a unit and / or module for executing the method provided by any one of the first to twelfth aspects, or any possible implementation of any one of the aspects, such as a transceiver unit and / or a processing unit, and the transceiver unit is used to send and receive various information or signaling, so that the beneficial effects (or advantages) of the method provided in any of the above aspects can also be achieved.

[0096] In a fourteenth aspect, the present application provides a communication device, which may include a processor and a transceiver. The transceiver is used to send and receive various information or signaling, and the computer program includes program instructions. When the processor runs the program instructions, the communication device executes the information interaction method described in any one of the first aspect to the twelfth aspect, or any possible implementation of any one of the aspects. 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 and output interface of a chip or circuit. Optionally, the communication device also includes a memory, which is used to store the computer program.

[0097] In a fifteenth aspect, the present application provides a readable storage medium having program instructions stored thereon, which, when executed on a communication device, enables the communication device to execute the information interaction method described in any one of the first to twelfth aspects, or any possible implementation of any one of the aspects.

[0098] In a sixteenth aspect, the present application provides a program product comprising instructions, which, when executed, enables the information interaction method described in any possible implementation of any one of the first to twelfth aspects to be executed.

[0099] In the seventeenth aspect, the present application provides a communication device, which can be implemented in the form of a chip or in the form of a device, and the device includes a processor. The processor is used to read and execute a program stored in a memory to execute one or more of any aspects of the first aspect to the twelfth aspect, or one or more of any possible implementation methods of any aspect thereof. Optionally, the device also includes a memory, which is connected to the processor through a circuit. Further optionally, the device also includes a communication interface, and the processor is connected to the communication interface. The communication interface is used to receive information and / or signaling to be processed, and the processor obtains the information and / or signaling from the communication interface, processes the information and / or signaling, and outputs the processing results through the communication interface. The communication interface can be an input and output interface.

[0100] Optionally, the processor and memory mentioned above may be physically independent units, or the memory may be integrated with the processor.

[0101] In an eighteenth aspect, the present application provides a communication system, which includes the above-mentioned first network element and the above-mentioned second network element, and optionally includes an NRF network element; or the communication system includes the above-mentioned second network element and the above-mentioned third network element; or the communication system includes the above-mentioned first network element, the above-mentioned second network element and the above-mentioned third network element.

[0102] The technical effects achieved in the above-mentioned aspects can be referred to each other or to the beneficial effects in the method embodiments shown below, and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0103] Figure 1 It is a schematic diagram of the system architecture provided by the embodiment of the present application;

[0104] Figure 2 It is a schematic diagram of a secure and authorized AI / ML model sharing process provided by an embodiment of the present application;

[0105] Figure 3 It is a first flow chart of the information interaction method provided in the application embodiment;

[0106] Figure 4 It is a second flow chart of the information interaction method provided in the application embodiment;

[0107] Figure 5 It is a third flow chart of the information interaction method provided in the application embodiment;

[0108] Figure 6 It is a fourth flow chart of the information interaction method provided in the application embodiment;

[0109] Figure 7 It is a fifth flow chart of the information interaction method provided in the application embodiment;

[0110] Figure 8 It is a sixth flow chart of the information interaction method provided in the application embodiment;

[0111] Fig. 9 It is a seventh flow chart of the information interaction method provided in the application embodiment;

[0112] Fig.10 is a schematic diagram of a structure of a communication device provided in an embodiment of the present application;

[0113] Fig.11 is another structural schematic diagram of a communication device provided in an embodiment of the present application;

[0114] Fig.12 This is another structural diagram of the communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0115] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0116] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "plurality" 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 plural items. For example, at least one of a, b, or c can mean: a, b, c; a and b; a and c; b and c; or a, b, and c. Among them, a, b, and c can be single or multiple.

[0117] In the description of the present application, the words "first", "second", etc. are only used to distinguish different objects, and do not limit the quantity and execution order, and the words "first", "second", etc. do not necessarily limit them to be different. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. 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 that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0118] In this application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described in this application as "exemplary", "for example" or "for example" should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the words "exemplary", "for example" or "for example" is intended to present the related concepts in a concrete way.

[0119] It should be understood that in the present application, "when", "if" and "if" all mean that the device will take corresponding actions under certain objective circumstances, and do not limit the time, nor do they require that the device must have a judgment action when it is implemented, nor do they mean that there are other limitations.

[0120] Elements used in the singular herein are intended to mean "one or more" rather than "one and only one" unless specifically stated otherwise.

[0121] Additionally, the terms "system" and "network" are often used interchangeably herein.

[0122] It can be understood that in each embodiment of the present application, "A corresponds to B" means that there is a corresponding relationship between A and B, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0123] The following is a brief description of the network elements and system architecture involved in this application.

[0124] The network data analytics function (NWDAF) network element supports collecting data from other network function and application function (AF) network elements, supports collecting data from operation administration and maintenance (OAM) network elements, supports providing analysis information to other network function and AF network elements, etc.

[0125] The NWDAF network element has functions such as data collection, model training, data analysis, and model reasoning. The NWDAF network element can be used to collect relevant data from network function network elements, third-party service servers, terminal devices, or network management systems, perform data analysis based on the relevant data to obtain analysis results, and provide analysis results to network function network elements, third-party service servers, terminal devices, or network management systems. The analysis results can assist the network in selecting service quality parameters for the service, or assist the network in performing traffic routing, or assist the network in selecting background data transmission strategies, etc. In addition, the NWDAF network element can also be used to collect relevant data from network function network elements, third-party service servers, terminal devices, or network management systems, and perform model training based on the relevant data to obtain an artificial intelligence (AI) model or a machine learning (ML) model, and provide AI models / ML models to other NWDAF network elements. The AI ​​model / ML model can be used to assist the NWDAF network element in generating data analysis results based on relevant data.

[0126] NWDAF containing AnLF can be used to perform inference and derive analytical information (i.e., derive statistics and / or predictions based on analytical consumer requests) and expose analytical services. NWDAF containing MTLF can be used to train machine learning (ML) models and expose new training services; for example, to provide trained ML models.

[0127] For the convenience of description in this application, "NWDAF network element containing AnLF (NWDAF containing AnLF)" can be simply expressed as "AnLF". In some cases, the two can be used interchangeably; "NWDAF network element containing MTLF (NWDAFcontaining MTLF)" can be simply expressed as "MTLF". In some cases, the two can be used interchangeably.

[0128] The analytics data repository functional (ADRF) network element can provide storage, deletion, and retrieval services for AI / ML models. The ADRF network element can also provide storage and retrieval services for data, as well as storage and retrieval services for analysis. Exemplarily, the consumer sends a data management storage request (Nadrf DataManagement Storage Request) to the ADRF network element, which contains the data or analysis that needs to be stored; or, the consumer sends a data management storage subscription request (Nadrf Data Management Storage Subscription Request) to the ADRF network element, requesting the ADRF network element to subscribe to the data or analysis for storage, and then the ADRF network element subscribes to the NWDAF network element or the data collection control function (DCCF) network element to obtain the data or analysis. 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 (the messaging frameworkadaptor function, MFAF) data management (Nmfaf_3caDataManagement) service.

[0129] The technical solution provided in this application can be applied to various communication systems deployed with virtual network functions. For example: the fifth generation (5G) communication system or new radio (NR), equipped with network functions virtualization infrastructure (NFVI) or other long term evolution (LTE) networks with virtual network functions, MulteFire networks (creating new wireless networks by independently running LTE technology on unlicensed spectrum (such as the 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 networks access mobile networks), and other future communication systems, such as the sixth generation mobile communication system.

[0130] For example, the technical solution provided in this application can be applied to the 5G system architecture defined in the 3rd Generation Partnership Project Technical Specifications (3GPP TS) 23.288.

[0131] See also Figure 1 , Figure 1 Schematic diagram of the system architecture provided by the embodiment of the present application. Figure 1 1(a) shows the architecture used for data collection, the 5G System architecture allows NWDAF to collect data from any 5G core (5G core, 5GC) network function (NF). The NWDAF belongs to the same PLMN as the 5GC NF that provides the data.

[0132] like Figure 1 1(b) shows the Network Data Analytics Exposure architecture, the 5G System architecture allows any 5GC NF to request network analytics information from NWDAF containing Analytics logical function (AnLF). The NWDAF belongs to the same PLMN as the 5GC NF that consumes the analytics information.

[0133] like Figure 11(c) shows a trained ML Model Provisioning architecture, the 5G System architecture allows NWDAF network elements containing analytics logical functions (AnLF) to use trained ML model provisioning services from another NWDAF network element containing model training logical functions (MTLF).

[0134] Understandably, Figure 1 The "Any NF" shown here indicates any network function element of 5GC, and "Nnf" and "Nnwdaf" indicate the names of service-oriented interfaces. For details, please refer to the relevant descriptions in the 3GPP standard protocol, which will not be described here. Figure 1 For the functions or roles of each network element shown, please refer to relevant protocols or standards, etc., which will not be described in detail here.

[0135] It is also understood that as standards develop and evolve, the above Figure 1 The NWDAF network element in the communication system may also be a network element having the same or similar functions as the NWDAF network element in a future communication system, and this application does not impose any limitation thereto.

[0136] In order to better understand the technical solution of the embodiments of the present application, the following briefly introduces the detailed procedure for secured and authorized AI / ML model sharing between different vendors.

[0137] See also Figure 2 , Figure 2 Schematic diagram of the secure and authorized AI / ML model sharing process provided by the embodiment of the present application. Figure 2 As shown, the secure and authorized AI / ML model sharing process between different vendors includes but is not limited to:

[0138] Step 0a, register NWDAF containing MTLF, which contains Analytics ID and Interoperability ID. NF Service producer (NFp), i.e. NWDAF containing MTLF, registers its NF profile in network repository function (NRF) using ML model interoperability indicator according to Analytics ID. ML model interoperability indicator can be used to indicate the list of NWDAF providers (or vendors) that are allowed to retrieve ML models from NWDAF containing MTLF.

[0139] Step 0b, registering NWDAF containing AnLF, which includes analysis ID and vendor ID. NF Service consumer (NFc), such as NWDAF containing AnLF function in NRF, includes its vendor ID.

[0140] Step 0c, conditionally encrypt ML models. 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.

[0141] Step 1, NWDAF containing MTLF triggers Nadrf_MLModelManagement_StorageRequest (Nadrf machine learning model management storage request). Nadrf_MLModelManagement_StorageRequest includes NWDAF containing MTLF ID, model ID, model address in NWDAF containing MTLF (such as uniform resource locator 1 (URL1)), and optionally also includes allowed NFc list (allowedNFc list).

[0142] Step 2: ADRF sends a response to NWDAF containing MTLF. The response includes the model ID and the model address in ADRF (such as URL2).

[0143] Step 3, Discovery of NWDAF containing MTLF. The NF service consumer (NFc), such as NWDAFcontainingAnLF, performs a Nnrf_NFDiscovery_Request operation using the requested analysis ID to select a suitable NF service provider (NFp), such as NWDAF containing MTLF.

[0144] In step 4a, the NF service consumer (NFc), such as NWDAF containingAnLF, requests an access token from the NRF using a Nnrf_AccessToken_Get request operation. The Nnrf_AccessToken_Get request message includes but is not limited to: the vendor ID and analysis ID of NWDAF containingAnLF.

[0145] In step 4b, the NRF checks whether the NWDAF containingAnLF is authorized to access the service requested in the NWDAF containing MTLF, and verifies whether the vendor ID of the NF service consumer (NFc) is contained in the NWADF containing the interoperability indicator of the MTLF analysis ID, and grants token 1 (token1) based on the vendor ID provided by the NF service consumer (NFc) during registration.

[0146] Step 5: NF service consumer (NFc) executes Nnwdaf_MLModelProvision request service operation on NWDAF containing MTLF to retrieve the ML model of the analysis ID. Nnwdaf_MLModelProvision request contains analysis ID, vendor ID and token 1.

[0147] Step 6a, Authorize NFc and store NFc ID. The NWDAF containing MTLF authenticates the NF service consumer (NFc) and verifies access token 1 and ensures that the analysis ID is contained in access token 1. If the verification is successful, the NWDAF containing MTLF determines the ML model to be shared for the requested analysis ID and stores the NF instance ID containing NWDAF containingAnLF as part of the allowed NFc list of ML models.

[0148] Step 6b, if it is determined that the ML model to be shared is stored in ADRF, and the NF service consumer (NFc) is not in the allowed NFc list stored in ADRF, the NWDAF containing MTLF triggers an update at ADRF through Nadrf_MLModelManagement_StorageRequest (Nadrf machine learning model management storage request). Nadrf_MLModelManagement_StorageRequest contains the NWDAF containing MTLF ID, model ID, and allowed NFc list. Then, ADRF stores the allowed NFc list for the ML model corresponding to the model ID.

[0149] In step 6c, ADRF sends a response to NWDAF containing MTLF, which includes the model ID.

[0150] Step 7, NWDAF containing MTLF sends Nnwdaf_MLModelProvisionResponse (Nnwdaf machine learning model provision response) to the NF service consumer (NFc), which contains the model ID and the address of the ML model to be shared; the address can be the address where the ML model is stored in NWDAF containing MTLF (i.e., URL1), or the address can be the address where the ML model is stored in ADRF (i.e., URL2). If the model is stored in ADRF, this message may also contain ADRFID. Optionally, Nnwdaf_MLModelProvisionResponse also includes a storage transaction ID.

[0151] In 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.

[0152] Step 8b, NRF verifies whether the NF service consumer (NFc), such as NWDAF containingAnLF, is authorized to access the services provided by ADRF. If the verification is successful, NRF will grant token 2 (token2) based on the information provided in the NF profile of ADRF.

[0153] Step 9, NF service consumer (NFc), such as NWDAF containingAnLF, retrieves the target model by sending Nadrf_MLModelManagement_Retrieval Request. Nadrf_MLModelManagement_Retrieval Request includes analysis ID and token2.

[0154] Step 10, ADRF authenticates the NF service consumer (NFc) and verifies the access token (token2). ADRF also verifies whether the NF ID of the NF service consumer (NFc) is included in the allowed NFc list of the ML model. If the verification is successful, ADRF sends Nadrf_MLModelManagement_RetrievalResponse to the NF service consumer (NFc), which contains the address where the model is stored in ADRF.

[0155] Step 11, conditionally decrypt the ML model. The NF service consumer (NFc) retrieves the ML model from ADRF and decrypts the model according to the vendor’s implementation.

[0156] By the above Figure 2 It can be seen that the storage and sharing (or acquisition) solutions of the above AI / ML models are imperfect. Figure 2 In step 1, NWDAF containing MTLF does not carry the allowed NFc list in the storage request, so ADRF will check the model authorization (such as Figure 2 There is uncertainty in step 10), and the model acquisition permissions at both ends of NWDAF containing MTLF and ADRF may be out of sync, resulting in the expected purpose of NWDAF containing MTLF being inconsistent with the judgment logic of ADRF, which may further lead to model leakage.

[0157] For example, the model consumer requests the model from ADRF by constructing a model ID. At this time, the AllowedNFlist of the model corresponding to the ModelID does not exist (because the NWDAF containing MTLF does not carry the AllowedNFlist in the model storage request, and the NWDAF containing MTLF does not receive the model acquisition request, so the above is not executed. Figure 2At this time, ADRF is not clear about how to authorize the model. Then ADRF will check the model authorization (such as Figure 2 There is uncertainty in step 10), and the model acquisition permissions at both ends of NWDAF containing MTLF and ADRF may be out of sync, resulting in the expected purpose of NWDAF containing MTLF being inconsistent with the judgment logic of ADRF, which may further lead to model leakage.

[0158] In view of this, the embodiments of the present application provide an information interaction method, device and readable storage medium, which can improve the storage solution of the model. When the model producer does not specify the allowed NFc list, or the allowed NFc list does not exist in the model storage request, it is also possible to align (or synchronize) the model acquisition permissions of NWDAF containing MTLF and ADRF, and clarify the judgment logic of ADRF during model authorization check; further, it can also reduce the risk of model leakage and improve the security of model acquisition.

[0159] The technical solution provided by this application will be described in detail below with reference to more drawings.

[0160] The technical solution provided in the present application is described through multiple embodiments, with specific reference to the description of each embodiment below. Among them, the same or similar parts between each embodiment or implementation can refer to each other. In each embodiment in the present application, and each implementation method / implementation method / implementation method in each embodiment, if there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments and each implementation method / implementation method / implementation method in each embodiment are consistent and can be referenced to each other, and the technical features in different embodiments and each implementation method / implementation method / implementation method in each embodiment can be combined to form new embodiments, implementation methods, implementation methods, or implementation methods according to their inherent logical relationships. The implementation methods of the present application described below do not constitute a limitation on the scope of protection of the present application.

[0161] In this application, the "allowed NFc list" can be understood as: a list of network function instance identifiers (NF instance ID) that are allowed to obtain / retrieve / access / query models. The "allowed NFc list" can also be called the "allowed NF instance identifier list (Allowed NF Instance ID list)", or the "allowed network function list (Allowed NF list)", etc., and this application does not limit it.

[0162] In addition, the "obtaining model" in this application can be understood as: downloading (or obtaining) the model from ADRF to the local, and can also be understood as "retrieve model" or "access model" or "query model" and so on.

[0163] Each embodiment is described in detail below.

[0164] Embodiment 1

[0165] Embodiment 1 of the present application mainly introduces that when a storage request sent by NWDAF containing MTLF does not carry an allowed NFc list, ADRF generates an allowed NFc list for a model, and the allowed NFclist includes the NF instance ID of NWDAF containing MTLF.

[0166] See also Figure 3 , Figure 3 This is a first flow chart of the information interaction method provided in the embodiment of the application. In this method, the first network element may be an ADRF, and the second network element may be an NWDAF including an MTLF. Of course, the second network element may also be an NWDAF including an MTLF and an AnLF, and this embodiment of the application does not limit this.

[0167] like Figure 3 As shown, the information interaction method includes but is not limited to the following steps:

[0168] S101, a second network element (such as NWDAF containing MTLF) sends a first request to a first network element (such as ADRF), where the first request is used to request to store model A in the first network element, and the first request includes the NF instance ID of the second network element, and the first request does not include an allowed NFc list corresponding to model A.

[0169] Correspondingly, the first network element (such as ADRF) receives the first request.

[0170] In a possible implementation, the above-mentioned first request may be used to request the storage of one or more models in the first network element. Exemplarily, the first request may be Nadrf_MLModelManagement_StorageRequest. The first request may include, but is not limited to: the NF instance ID of the second network element, the model identifier (i.e., model ID) of each model in the one or more models, and the address of each model in the second network element (which may be represented by a URL or a fully qualified domain name (FQDN)). For ease of description in the embodiments of the present application, the following takes the storage of model A in the first network element as an example. Then the first request may include, but is not limited to: the NF instanceID of the second network element, the model ID of model A, and the address of model A in the second network element (such as URL1). In addition, the first request does not include the allowed NF consumer list (allowed NFc list) corresponding to model A.

[0171] It can be understood that the NF instance ID can be used to uniquely identify a network function instance (NF Instance ID: Unique identity of the NF Instance). The model ID can be used to uniquely identify a model (MLModel identifier: unique ML Model identifier). The address of the model in the second network element can be used by the first network element to obtain (such as download) the model file from the second network element according to the address and store it locally.

[0172] It can be understood that the model in this application can be an ML model or an AI model without limitation.

[0173] S102, the first network element (such as ADRF) generates an allowed NFc list for model A, wherein the allowed NFc list includes the NF instance ID of the second network element, and the NF instance ID of the second network element included in the allowed NFc list is used to authorize model A.

[0174] In a possible implementation, after receiving the first request, the first network element can obtain (for example, download) the model A from the second network element according to the address of the model A in the second network element (such as URL1) and store it locally. Since the first request does not carry the allowed NFc list corresponding to the model A, the first network element can generate an allowedNFc list for the model A. Among them, the allowed NFc list generated by the first network element includes the NF instance ID of the second network element. Exemplarily, the first network element can generate an empty allowed NFc list for the model A, and then add the NF instance ID of the second network element carried by the first request to the allowed NFc list. The first network element can also generate an allowed NFc list including the NF instance ID of the second network element for the model A. This embodiment of the present application is not limited.

[0175] In a possible implementation, the first request further includes first indication information, which may be used to indicate that the second network element does not authorize other network elements to obtain model A, or model A is not allowed to be obtained by other network elements (i.e., other network elements except the second network element), or the second network element does not authorize any network element to obtain model A. Therefore, after receiving the first request, the first network element may generate an allowed NFc list for model A, and include the NF instance ID of the second network element in the allowed NFc list.

[0176] In a possible implementation, before step S102, the information interaction method may further include: the first network element determines that the second network element does not authorize other network elements to obtain the model A, or determines that the model A is not allowed to be obtained by other network elements (other network elements except the second network element), or determines that the second network element does not authorize any network element to obtain the model A. It can be understood that the "other network elements" in the embodiment of the present application may refer to other NWDAF network elements, or any network element in the network except the second network element, and the embodiment of the present application is not limited. Similarly, the "any network element" in the embodiment of the present application may refer to any NWDAF network element, or any network element in the network. For example: there are 3 NWDAFs in the network system, represented as NF1, NF2, and NF3 respectively; NF1 stores the model M1 and does not carry the AllowedNFclist. ADRF determines that NF1 can obtain the model, and other NWDAFs (such as NF2 and NF3) cannot obtain the model.

[0177] For example, before step S101, such as in the network element registration process, the first network element (such as ADRF) sends a third request to the network storage function (NRF) network element. The third request can be used to notify or register the NF configuration file of the first network element to the NRF network element. The third request may include second indication information for indicating that when the allowed NFc list corresponding to the model does not exist, other network elements cannot obtain the model. In other words, the second indication information is used to indicate that when the first network element receives a model management storage request, if the model management storage request does not include the allowed NFc list corresponding to the model, the model authorization logic of the first network element is that the model producer (such as NWDAF containing MTLF) does not authorize other network elements to obtain the model, or the model is not allowed to be obtained by other network elements (other network elements except the second network element). The second network element discovers the first network element according to the network element discovery process, and can obtain the model authorization logic of the first network element when the allowed NFc list does not exist from the NRF network element. Then the second network element decides to store the model in the first network element according to the model authorization logic of the first network element and its own storage policy, such as executing step S101. Therefore, after the first network element receives the above-mentioned first request, it can be determined that the second network element has not authorized other network elements to obtain model A, or that model A is not allowed to be obtained by other network elements (other network elements except the second network element) according to the fact that the first request does not include the allowed NFc list corresponding to model A and the locally pre-configured model authorization logic.

[0178] Alternatively, before step S101, for example, in the network element registration process, the second network element (such as NWDAF containing MTLF) sends a third request to the network storage function (NRF) network element. The third request can be used to notify or register the NF configuration file of the second network element to the NRF network element. The third request may include second indication information for indicating that when the allowed NFc list corresponding to the model does not exist, other network elements cannot obtain the model. In other words, the second indication information is used to indicate that when the allowed NFc list corresponding to the model does not exist in the model management storage request, the model authorization logic of the second network element is that the model producer (such as NWDAF containing MTLF) does not authorize other network elements to obtain the model, or the model is not allowed to be obtained by other network elements (other network elements except the second network element). The first network element discovers the second network element according to the network element discovery process, and can obtain the model authorization logic of the second network element from the NRF network element when the allowed NFc list does not exist. Then, after the first network element receives the above-mentioned first request, according to the fact that the first request does not include the allowed NFclist corresponding to model A and the model authorization logic of the second network element, it can be determined that the second network element has not authorized other network elements to obtain model A, or that model A is not allowed to be obtained by other network elements (other network elements except the second network element).

[0179] For another example, when the allowed NFc list corresponding to the predefined model in the standard protocol does not exist, it means that the model producer (such as NWDAF containing MTLF) has not authorized other network elements to obtain the model, or the model is not allowed to be obtained by other network elements (other network elements except the model producer). Then, when the above-mentioned first request does not include the allowed NFc list corresponding to model A, it can be used to indicate that the second network element has not authorized other network elements to obtain model A, or the model A is not allowed to be obtained by other network elements (other network elements except the second network element). Therefore, after the first network element receives the above-mentioned first request, it can be determined that the second network element has not authorized other network elements to obtain model A, or the model A is not allowed to be obtained by other network elements (other network elements except the second network element) according to the fact that the first request does not include the allowed NFc list corresponding to model A.

[0180] In a possible implementation, after the first network element receives the above-mentioned first request, the first network element may store the NF instanceID of the second network element, the model ID of model A, and the allowed NFc list generated in step S102, thereby recording the correspondence between them for subsequent use. If the first network element generates a storage transaction ID (Storage Transaction ID) for all models requested to be stored in the above-mentioned first request, the first network element may also store the StorageTransaction ID, thereby recording the correspondence between the NF instance ID of the second network element, the model ID of model A, the allowed NFclist, and the Storage Transaction ID, for subsequent use. Among them, the StorageTransaction ID can be understood as a credential for one-time storage, which can be used to index the stored model; however, because one or more models may be stored at one time, one Storage Transaction ID may index one or more models.

[0181] S103: The first network element (such as ADRF) sends a first response to the second network element (such as NWDAF containing MTLF), where the first response includes the model ID of model A, or the first response includes the model ID of model A and a storage transaction ID.

[0182] In a possible implementation, the above-mentioned first response is a response returned for the above-mentioned first request. Exemplarily, the first response may be a Nadrf_MLModelManagement_Storage Response. The first response may include, but is not limited to: the model ID of model A, and the address of model A in the first network element (such as URL2). Optionally, if the first network element generates a Storage Transaction ID, the first response may also include the Storage Transaction ID; of course, the first response may not include the Storage Transaction ID. In other words, when the first network element generates a Storage Transaction ID, whether the first response carries the Storage Transaction ID is determined by the first network element, and the embodiments of the present application do not limit it.

[0183] It can be understood that in the embodiment of the present application, when the storage request (i.e., the first request mentioned above) does not carry the allowedNFc list of the model, ADRF generates an allowed NFc list for the model, and the allowed NFc list includes the NF instance ID of the second network element. In this way, the model authorization check logic of ADRF can be used, that is, to determine whether the NF instance ID carried by the model retrieval / acquisition request is in the allowed NFc list to determine the authorization status of the model. Therefore, the embodiment of the present application aligns (or synchronizes) the model acquisition permissions at both ends of the first network element and the second network element by improving the storage solution of the model.

[0184] In a possible implementation, after step S103, if the model is to be retrieved / acquired from the first network element (such as ADRF), the above Figure 3 The information interaction method shown may also include but is not limited to the following steps:

[0185] S104, the second network element (such as NWDAF containing MTLF) sends a second request to the first network element (such as ADRF), where the second request is used to request to obtain model A, and the second request includes the NF instance ID, and the second request also includes the model ID or storage transaction ID of model A.

[0186] Correspondingly, the first network element (such as ADRF) receives the second request.

[0187] In a possible implementation, the second request may be used to request to obtain model A from the first network element. Exemplarily, the second request may be a Nadrf_MLModelManagement_Retrieval Request. The second request may include, but is not limited to: NF instance ID, and model ID or Storage Transaction ID of model A. Optionally, the second request also includes analysis ID of model A.

[0188] In one possible implementation, before the second network element sends the second request to the first network element, the second network element may request an access token from the NRF network element, as described above. Figure 2 As shown in step 8a and step 8b, the description is not expanded here. Then correspondingly, the first request also includes the token.

[0189] The "obtaining model" in the embodiment of the present application can be understood as: downloading (or obtaining) the model from ADRF to the local, and can also be understood as "retrieve model" or "access model" or "query model" and so on.

[0190] S105, the first network element (such as ADRF) verifies whether the NF instance ID carried in the second request is in the allowed NFc list of the model A.

[0191] S106, if the NF instance ID carried in the second request is in the allowed NFc list of the model A, the first network element (such as ADRF) sends a second response to the second network element (such as NWDAF containing MTLF), and the second response includes the information of the model A stored in the first network element.

[0192] Correspondingly, the second network element (such as NWDAF containing MTLF) receives the second response, wherein the second response is a response returned for the second request, such as Nadrf_MLModelManagement_Retrieval Response.

[0193] In a possible implementation, after receiving the second request, the first network element can verify whether the NF instance ID carried by the second request is in the allowed NFc list of the model A, or verify whether the NF instance ID carried by the second request is the same as the NF instance ID of the second network element. In the case where the second request carries an access token, the first network element can also verify the validity of the token. It can be understood that the first network element may also need to verify other information, which is not listed one by one in the embodiments of the present application. If the verification is passed, the first network element sends a second response to the second network element, and the second response may include information about the model A stored in the first network element. For example, the second response includes one or more of the following: the storage address of model A in the first network element (such as URL2), or the model file of model A. Optionally, the second response also includes the ID of the first network element.

[0194] For ease of description, the embodiment of the present application assumes that other verifications of retrieving / obtaining the model from the first network element (such as ADRF) have passed. The following mainly focuses on: whether the NF instance ID carried by the above-mentioned second request is in the allowedNFc list of the above-mentioned model A.

[0195] In a possible implementation, if the NF instance ID carried in the second request is in the allowed NFc list, the first network element may send a second response to the second network element. It is understandable that the model ID or Storage Transaction ID carried in the second request may be used to index model A.

[0196] It can be understood that after step S103, if a third network element (such as NWDAF containing AnLF) wants to retrieve / obtain the model from the first network element (such as ADRF), the third network element may also send a second request to the first network element. The model ID or Storage Transaction ID of model A carried in the second request may be obtained from the second network element (such as NWDAF containing MTLF), and the method of obtaining the model ID or Storage Transaction ID of model A is not limited in the embodiment of the present application. After receiving the second request, the first network element still verifies whether the NF instance ID carried in the second request is in the allowed NFc list of model A. Because the NF instance ID carried in the second request sent by the third network element is not in the allowed NFc list of model A, and model A is not authorized to be obtained by other network elements, the verification fails. If the verification fails, the first network element may reject the second request.

[0197] It can be seen from this that the embodiment of the present application does not carry the allowed NFc list of the model when storing the model. When retrieving / obtaining the model, the model will not be returned to other network elements except the model producer (i.e., the second network element). The judgment logic of ADRF during model authorization check is clarified, which can not only reduce the risk of model leakage caused by the non-existence of the allowed NFc list and the sending of the model to unauthorized network elements by ADRF assumining that the model has no permission restrictions, but also improve security; it can also solve the problem that due to the non-existence of the allowed NFc list, ADRF considers that all network elements cannot obtain the model and rejects all retrieval requests, resulting in the model producer (i.e., the second network element) being unable to obtain the model.

[0198] In a possible implementation, after step S103, if the second network element (such as NWDAF containing MTLF) wants to update or delete the model stored in the first network element (such as ADRF), the above Figure 3 The information interaction method shown may also include but is not limited to the following steps:

[0199] S107, the second network element (such as NWDAF containing MTLF) sends a fourth request to the first network element (such as ADRF), where the fourth request is used to request to update or delete the above-mentioned model A. The fourth request includes the NF instance ID, and the fourth request also includes the model ID or storage transaction ID of model A.

[0200] S108: If the NF instance ID carried by the fourth request is the NF instance ID of the second network element, the first network element (such as ADRF) processes model A according to the fourth request.

[0201] In a possible implementation, the fourth request may be used to request to update or delete the model A stored in the first network element. The fourth request may include the NF instance ID, and the fourth request may also include the model ID or StorageTransaction ID of model A. The model ID or Storage Transaction ID may be used to index the model, and may also be used to index the NF instance ID of the second network element. It is understandable that if the fourth request is used to request to update the model A stored in the first network element, the fourth request also includes: the address of the updated model in the second network element, and the updated model ID; optionally, the allowed NFc list of the updated model.

[0202] In a possible implementation, before the second network element sends the fourth request to the first network element, the second network element may request an access token from the NRF network element, which will not be described in detail here. Accordingly, the fourth request also includes the token.

[0203] In a possible implementation, after receiving the fourth request, the first network element can verify whether the NF instance ID carried in the fourth request is the NFinstance ID of the second network element corresponding to the model ID or the Storage Transaction ID. In the case where the fourth request carries an access token, the first network element can also verify the validity of the token. If the verification is successful, the first network element processes model A according to the fourth request. The following embodiments of the present application assume that the token verification is successful.

[0204] If the NF instance ID carried by the fourth request is the NF instance ID of the second network element, it means that the network element requesting to update / delete the model is the same network element as the network element requesting to store the model, so the first network element can process the model A corresponding to the model ID or storage transaction ID according to the fourth request. It can be understood that if the fourth request is used to request to update the model A stored in the first network element, the first network element updates the model A according to the information in the fourth request. If the fourth request is used to request to delete the model A stored in the first network element, the first network element deletes the model A corresponding to the model ID or StorageTransaction ID in the fourth request.

[0205] It is understood that the embodiment of the present application does not limit the execution order between step S107-step S108 and step S105-step S106. For example, step S107-step S108 can be executed after step S105-step S106, or before step S105-step S106, and the embodiment of the present application does not limit it.

[0206] It can be understood that if the above-mentioned fourth request is used to request the deletion of model A stored in the first network element, then steps S107-step S108 need to be executed after steps S105-step S106; if steps S107-step S108 are executed before steps S105-step S106, the second network element (such as NWDAF containing MTLF) cannot obtain model A from the first network element (such as ADRF), so steps S105-step S106 are not necessary to execute. If the above-mentioned fourth request is used to request the update of model A stored in the first network element, steps S107-step S108 can be executed after steps S105-step S106, or before steps S105-step S106. If steps S107-step S108 are executed before steps S105-step S106, the second response returned by step S106 includes the address of the updated model in the first network element.

[0207] In the embodiment of the present application, when the storage request (i.e., the first request mentioned above) does not carry the allowed NFc list of the model, ADRF generates an allowed NFc list for the model, and the allowed NFc list includes the NFinstance ID of the second network element. The storage scheme of the model is improved, and when retrieving / obtaining the model, the model will not be returned to other network elements except the model producer (i.e., the second network element). The judgment logic of ADRF during the model authorization check is clarified, and the model acquisition permissions at both ends of the first network element and the second network element are aligned (or synchronized). Furthermore, the risk of model leakage can be reduced and the security of model acquisition can be improved.

[0208] Embodiment 2

[0209] Embodiment 2 of the present application mainly introduces the processing logic of ADRF when a storage request does not carry an allowed NFc list, indicating that the model producer (such as NWDAF containing MTLF) has not authorized other network elements to obtain the model, or other network elements (other network elements except the model producer) are not allowed to obtain the model.

[0210] The "obtaining model" in the embodiment of the present application can be understood as: downloading (or obtaining) the model from ADRF to the local, and can also be understood as "retrieve model" or "access model" or "query model" and so on.

[0211] See also Figure 4 , Figure 4 This is a second flow chart of the information interaction method provided in the embodiment of the application. In this method, the first network element may be an ADRF, and the second network element may be an NWDAF including an MTLF. Of course, the second network element may also be an NWDAF including an MTLF and an AnLF, and this embodiment of the application does not limit this.

[0212] like Figure 4 As shown, the information interaction method includes but is not limited to the following steps:

[0213] S201, a second network element (such as NWDAF containing MTLF) sends a first request to a first network element (such as ADRF), where the first request is used to request to store model A in the first network element, and the first request includes: a model ID of model A, and an NF instance ID of the second network element, and the first request does not include an allowed NFc list corresponding to model A.

[0214] Correspondingly, the first network element (such as ADRF) receives the first request.

[0215] In a possible implementation manner, the specific implementation manner of the first request can refer to the description of step S101 in the aforementioned embodiment 1, which will not be repeated here.

[0216] S202, the first network element (such as ADRF) stores the NF instance ID and model ID of the second network element.

[0217] In a possible implementation, after receiving the above-mentioned first request, the first network element can obtain (for example, download) the model A from the second network element according to the address of the model A in the second network element (such as URL1) and store it locally. Then, the first network element can store the NF instance ID of the second network element and the model ID of the model A, thereby recording the corresponding relationship between them. Alternatively, if the first network element generates a storage transaction identifier (Storage Transaction ID) for all models stored in the above-mentioned first request, the first network element can also store the Storage Transaction ID, thereby recording the corresponding relationship between the NF instance ID of the second network element, the model ID of the model A, and the Storage Transaction ID. Among them, the Storage Transaction ID can be understood as a credential for one-time storage, which can be used to index the stored model; however, because one or more models may be stored at a time, one Storage Transaction ID may index one or more models.

[0218] In one possible implementation, the above-mentioned first request also includes first indication information, which can be used to indicate that: the second network element has not authorized other network elements to obtain model A, or model A is not allowed to be obtained by other network elements (i.e., other network elements except the second network element), or the second network element has not authorized any network element to obtain model A.

[0219] In a possible implementation, after the first network element receives the above-mentioned first request, the information interaction method may also include: the first network element determines that the second network element has not authorized other network elements to obtain the model A, or determines that the model A is not allowed to be obtained by other network elements (other network elements except the second network element), or the second network element has not authorized any network element to obtain the model A. Among them, the specific determination method can refer to the description of step S102 in the above-mentioned embodiment 1, which is not repeated here. It can be understood that the "other network elements" in the embodiment of the present application may refer to other NWDAF network elements, or may refer to any network element in the network except the second network element, and the embodiment of the present application does not limit it. Similarly, the "any network element" in the embodiment of the present application may refer to any NWDAF network element, or may refer to any network element in the network.

[0220] In a possible implementation, since the first request does not carry the allowed NFclist corresponding to the model A, after receiving the first request, the first network element may generate an allowed NFc list for the model A, and the allowed NFc list is empty. Then, the first network element may also store the generated allowed NFc list, thereby recording the correspondence between the NF instance ID of the second network element, the model ID of the model A, and the allowed NFc list, or recording the correspondence between the NF instance ID of the second network element, the model ID of the model A, the allowed NFc list, and the StorageTransaction ID.

[0221] S203: The first network element (such as ADRF) sends a first response to the second network element (such as NWDAF containing MTLF), where the first response includes the model ID of model A, or the first response includes the model ID of model A and a storage transaction ID.

[0222] Correspondingly, the second network element (such as NWDAF containing MTLF) receives the first response.

[0223] In a possible implementation manner, the specific implementation manner of the first response can refer to the description of step S103 in the aforementioned embodiment 1, which is not repeated here.

[0224] S204, the second network element (such as NWDAF containing MTLF) sends a second request to the first network element (such as ADRF), where the second request is used to request to obtain model A, and the second request includes the NF instance ID, and the second request also includes the model ID or storage transaction ID of model A.

[0225] Correspondingly, the first network element (such as ADRF) receives the second request.

[0226] In a possible implementation, the implementation of step S204 of the embodiment of the present application can refer to the implementation of step S104 in the aforementioned embodiment 1, which will not be repeated here.

[0227] S205, the first network element (such as ADRF) verifies whether the NF instance ID carried in the second request is the NF instance ID of the second network element stored above.

[0228] S206: If the NF instance ID carried in the second request is the NF instance ID of the second network element stored in the second network element, the first network element (such as ADRF) sends a second response to the second network element (such as NWDAF containing MTLF), and the second response carries the information of model A stored in the first network element.

[0229] Correspondingly, the second network element (such as NWDAF containing MTLF) receives the second response.

[0230] In a possible implementation, after receiving the second request, the first network element can verify whether the NF instance ID carried by the second request is the NF instance ID of the second network element stored in step S202, or verify whether the NF instance ID carried by the second request is the same as the NF instance ID of the second network element. In the case where the second request carries an access token, the first network element can also verify the validity of the token. It can be understood that the first network element may also need to verify other information, which is not listed one by one in the embodiments of the present application. If the verification is passed, the first network element sends a second response to the second network element, and the second response may include information about model A stored by the first network element. For example, the second response includes one or more of the following: the storage address of model A in the first network element (such as URL2), and the model file of model A. Optionally, the second response also includes the ID of the first network element.

[0231] For ease of description, the embodiment of the present application assumes that other verifications of retrieving / obtaining the model from the first network element (such as ADRF) have been passed. The following mainly focuses on: whether the NF instance ID carried by the above-mentioned second request is the NF instance ID of the second network element stored in step S202.

[0232] In a possible implementation, if the NF instance ID carried by the second request is the NFinstance ID of the second network element, or the NF instance ID carried by the second request is the same as the NF instance ID of the second network element, the first network element may send a second response to the second network element. It can be understood that the model ID or StorageTransaction ID carried in the above second request can be used to index the model, and can also be used to index the NF instance ID of the second network element (this is because the first network element establishes a corresponding relationship between them in step S202).

[0233] It can be understood that after step S203, if a third network element (such as NWDAF containing AnLF) wants to retrieve / obtain the model from the first network element (such as ADRF), the third network element may also send a second request to the first network element. The model ID or Storage Transaction ID of model A carried in the second request may be obtained from the second network element (such as NWDAF containing MTLF), and the method of obtaining the model ID or Storage Transaction ID of model A is not limited in the implementation of this application. After receiving the second request, the first network element still verifies whether the NF instance ID carried in the second request is the NF instance ID of the second network element stored in step S202. Because the NF instance ID carried in the second request sent by the third network element is not the NF instance ID of the second network element, and model A is not authorized to other network elements for acquisition, the verification fails. If the verification fails, the first network element may reject the second request.

[0234] It can be seen from this that in the embodiment of the present application, when the storage request (i.e., the first request mentioned above) does not carry the allowedNFc list of the model, it means that the model producer (such as NWDAF containing MTLF) has not authorized other network elements to obtain this model, which can improve the storage solution of the model and align (or synchronize) the model acquisition permissions at both ends of the first network element and the second network element. When retrieving / acquiring the model, ADRF will not return the model to other network elements except the model producer (i.e., the second network element), which clarifies the judgment logic of ADRF during the model authorization check. It can not only reduce the risk of model leakage caused by the non-existence of the allowed NFc list and the sending of the model to unauthorized network elements by ADRF as it believes that the model has no permission restrictions, but also improve security; it can also solve the problem that because the allowed NFc list does not exist, ADRF believes that all network elements cannot access the model and rejects all retrieval requests, resulting in the model producer (i.e., the second network element) also being unable to access the model.

[0235] In a possible implementation, after step S203, if the second network element (such as NWDAF containing MTLF) wants to update or delete the model stored in the first network element (such as ADRF), the above Figure 4 The information interaction method shown may also include but is not limited to the following steps:

[0236] S207, the second network element (such as NWDAF containing MTLF) sends a fourth request to the first network element (such as ADRF), where the fourth request is used to request to update or delete the above-mentioned model A. The fourth request includes the NF instance ID, and the fourth request also includes the model ID or storage transaction ID of model A.

[0237] S208: If the NF instance ID carried by the fourth request is the NF instance ID of the second network element, the first network element (such as ADRF) processes model A according to the fourth request.

[0238] In a possible implementation, the implementation of step S207 and step S208 in the embodiment of the present application can refer to the implementation of step S107 and step S108 in the aforementioned embodiment 1, which will not be repeated here.

[0239] It is understood that the embodiment of the present application does not limit the execution order between step S207-step S208 and step S206-step S206. For example, step S207-step S208 can be executed after step S205-step S206, or before step S205-step S206. For details, please refer to the relevant description of the above embodiment 1, which will not be repeated here.

[0240] Embodiment 3

[0241] Embodiment 3 of the present application mainly introduces carrying indication information in a storage request to indicate authorization for all network elements to obtain the model, and the processing logic of ADRF.

[0242] See also Figure 5 , Figure 5 This is a third flow chart of the information interaction method provided in the embodiment of the application. In this method, the first network element may be an ADRF, the second network element may be an NWDAF including an MTLF, and of course the second network element may also be an NWDAF including an MTLF and an AnLF, which is not limited in the embodiment of the application. The third network element may be an NWDAF including an AnLF.

[0243] like Figure 5 As shown, the information interaction method includes but is not limited to the following steps:

[0244] S301, the second network element (such as NWDAF containing MTLF) sends a first request to the first network element (such as ADRF), where the first request is used to request the storage of model A, and the first request includes: a model ID of model A, and indication information, where the indication information is used to indicate that the second network element authorizes all network elements to obtain model A.

[0245] Correspondingly, the first network element (such as ADRF) receives the first request.

[0246] In a possible implementation, the above-mentioned first request may be used to request to store one or more models in the first network element. Exemplarily, the first request may be Nadrf_MLModelManagement_StorageRequest. The first request may include, but is not limited to: the NF instance ID of the second network element, the model identifier (i.e., model ID) of each model in the one or more models, and the address of each model in the second network element (expressed by URL). Optionally, the first request also includes one or more indication information. For the convenience of description in the embodiment of the present application, the following takes the storage of model A in the first network element as an example. Then the first request may include, but is not limited to: the NF instance ID of the second network element, the model ID of model A, the address of model A in the second network element (such as URL1), and the indication information corresponding to model A. The indication information may be used to indicate that the second network element authorizes all network elements to obtain model A, or to indicate that model A is allowed to be obtained by all network elements. "All network elements" in the embodiment of the present application may be all NWDAF network elements, or any network element in the network, and the embodiment of the present application is not limited. That is to say, for model A, when acquiring or retrieving the model, ADRF does not need to verify NFc's model acquisition authority. As long as NFc provides a model acquisition index (such as a model ID or a storage transaction ID), the corresponding model can be acquired.

[0247] In one possible implementation, the first request may further include the allowed NFclist corresponding to model A. In one possible implementation, the indication information may be carried in the allowed NFc list corresponding to model A. In order to reduce overhead, the allowed NFc list may not include the NF instance ID. In another possible implementation, the indication information may be a separate information element. In order to reduce overhead, the first request may not include the allowed NFc list corresponding to model A.

[0248] S302: The first network element (such as ADRF) stores the model ID of model A and the above indication information.

[0249] In a possible implementation, after receiving the first request, the first network element may obtain (e.g., download) the model A from the second network element according to the address of the model A in the second network element (e.g., URL1) and store it locally. Then, the first network element may store the model ID of the model A and the above-mentioned indication information, thereby recording the corresponding relationship between them. Alternatively, if the above-mentioned indication information is carried in the allowed NFc list corresponding to the model A, the first network element may store the model ID corresponding to the model A and the allowed NFc list. If the first network element generates a storage transaction identifier (Storage Transaction ID) for all models requested to be stored in the first request, the first network element may also store the Storage Transaction ID, thereby recording the corresponding relationship between the model ID of the model A, the Storage Transaction ID, and the above-mentioned indication information (or allowed NFclist). The first network element storing the indication information may be understood as the first network element storing the content indicated by the indication information carried by the first request, that is, the storage indication information of the first network element may not be the information element carrying the indication information in the first request, but the content actually indicated by the indication information.

[0250] In one possible implementation, the first network element may also store the NF instance ID of the second network element, thereby recording the correspondence between the NF instance ID of the second network element, the model ID of model A, and the above indication information, or recording the correspondence between the NF instance ID of the second network element, the model ID of model A, the Storage Transaction ID, and the above indication information; for subsequent use.

[0251] S303: The first network element (such as ADRF) sends a first response to the second network element (such as NWDAF containing MTLF), where the first response includes the model ID of model A, or the first response includes the model ID of model A and a storage transaction ID.

[0252] In a possible implementation manner, the specific implementation manner of the first response can refer to the description of step S103 in the aforementioned embodiment 1, which will not be repeated here.

[0253] The embodiment of the present application carries the indication information of the model in the storage request (i.e., the first request mentioned above) to indicate that all network elements can obtain the model, thereby improving the storage solution of the model and aligning (or synchronizing) the model acquisition permissions at both ends of the first network element and the second network element.

[0254] In a possible implementation, after step S303, if the third network element wants to retrieve / acquire the model from the first network element (such as ADRF), the above Figure 5 The information interaction method shown may also include but is not limited to the following steps:

[0255] S304 : The third network element (eg NWDAF containingAnLF) sends a model providing request to the second network element (eg NWDAF containingMTLF). The model providing request includes the analysis ID of model A. The model providing request is used to request the second network element to provide modelA.

[0256] Correspondingly, the second network element (such as NWDAF containing MTLF) receives the model providing request.

[0257] S305: The second network element (such as NWDAF containing MTLF) sends a model provision response to the third network element (such as NWDAF containing AnLF), where the model provision response includes a model ID or a storage transaction ID.

[0258] Correspondingly, the third network element (such as NWDAF containingAnLF) receives the model and provides a response.

[0259] In a possible implementation, the model provision request may include but is not limited to the analysis ID of model A, and may optionally include a vendor ID and / or an acquisition token of a third network element. The model provision request may be used to request the second network element to provide model A. Exemplarily, the model provision request may be Nnwdaf_MLModelProvisionRequest.

[0260] In a possible implementation, after receiving the above model providing request, the second network element can determine which model IDs of the models to authorize to the third network element based on the model providing request and internal logic, and then return a model providing response to the third network element. The model providing response may include a model ID or a storage transaction ID, and optionally also includes the ID of the first network element.

[0261] Exemplarily, the second network element first determines the model authorized to be acquired by the third network element in the (one or more) models corresponding to the analysis ID carried in the above-mentioned model provision request, and then checks whether the model authorized to be acquired by the third network element has a storage transaction ID. If there is a storage transaction ID, it is determined whether the (one or more) models corresponding to the storage transaction ID are all authorized to be acquired by the third network element; if the (one or more) models corresponding to the storage transaction ID are all authorized to be acquired by the third network element, the storage transaction ID can be carried in the model provision response. Optionally, the model provision response also includes the ID of the model authorized to be acquired by the third network element in the (one or more) models corresponding to the analysis ID. In other cases, the model ID is carried in the model provision response. For example, if the (one or more) models corresponding to the storage transaction ID include models that are not authorized to be acquired by the third network element, the ID of the model authorized to be acquired by the third network element in the (one or more) models corresponding to the analysis ID can be carried in the model provision response.

[0262] It can be understood that although the above model provision request carries the analysis ID of model A, since the analysis ID is used to identify the function of the model, and there may be multiple models with the same function, the analysis ID carried in the above model provision request may correspond to one or more models, and these one or more models include model A. In addition, a storage transaction ID can be understood as a credential for one storage, and one or more models can be stored at one time, so a storage transaction ID can index one or more models.

[0263] For example, assume that the analysis ID carried in the above model provision request corresponds to three models, namely model A, model B, and model C; assume that the second network element determines based on internal logic that model A and model B are authorized to be obtained by the third network element, and model A corresponds to storage transaction ID 1, and model B corresponds to storage transaction ID 2. Assume that storage transaction ID 1 only corresponds to model A, and storage transaction ID 2 corresponds to model B and model D. Since model A can be obtained by all network elements, storage transaction ID 1 can be carried in the model provision response; if both model B and model D are authorized to be obtained by the third network element, storage transaction ID 2 can also be carried in the model provision response; that is, the model provision response includes storage transaction ID 1 and storage transaction ID 2. However, if model D is not authorized to be obtained by the third network element, the model provision response should carry the model ID of model B and storage transaction ID 1, or the model provision response should carry the model IDs of model A and model B.

[0264] S306: The third network element (such as NWDAF containingAnLF) sends a second request to the first network element (such as ADRF). The second request is used to request to obtain model A. The second request includes the model ID of model A or the storage transaction ID.

[0265] Correspondingly, the first network element (such as ADRF) receives the second request.

[0266] In a possible implementation, the implementation of step S306 of the embodiment of the present application can refer to the implementation of step S104 in the aforementioned embodiment 1, which will not be repeated here.

[0267] S307, if the model ID or storage transaction ID carried in the above-mentioned second request corresponds to the above-mentioned indication information stored, the first network element (such as ADRF) sends a second response to the third network element (such as NWDAF containingAnLF), and the second response carries the information of model A stored in the first network element.

[0268] Correspondingly, the third network element (such as NWDAF containingAnLF) receives the second response.

[0269] In one possible implementation, after receiving the second request, the first network element may verify whether the model ID or storage transaction ID carried in the second request corresponds to the indication information according to the content stored in step S202. If the model ID or storage transaction ID carried in the second request corresponds to the stored indication information, because the indication information indicates that all network elements can obtain model A, the first network element may send a second response to the third network element. In another possible implementation, if the indication information is carried in the allowed NFc list corresponding to model A, after receiving the second request, the first network element may verify the Allowed NFclist corresponding to the model ID or storage transaction ID carried in the second request. If the Allowed NFc list contains the indication information, the first network element may send a second response to the third network element. For the implementation of the second response, please refer to the description in the first embodiment, which will not be repeated here.

[0270] It can be understood that the model ID or storage transaction ID carried in the above second request can be used to index the model, and can also be used to index the indication information (this is because the first network element establishes a corresponding relationship between them in step S302).

[0271] It can also be understood that, in the case where the second request carries an access token, the first network element can also verify the validity of the token. If the verification is successful, the first network element sends a second response to the second network element.

[0272] It can be understood that if the third network element and the second network element are the same network element, the above steps S304 and S305 may not be performed.

[0273] The embodiment of the present application carries indication information in the storage request (i.e., the first request mentioned above) to indicate that all network elements can obtain the model. When searching, the permission of the model is determined. If the permission of the model allows all network elements to obtain it, the model is returned. The judgment logic of the first network element during the model authorization check is clarified, the storage scheme of the model is improved, and the model acquisition permissions of the first network element and the second network element are aligned (or synchronized).

[0274] In a possible implementation, after step S303, if the second network element (such as NWDAF containing MTLF) wants to update or delete the model stored in the first network element (such as ADRF), the above Figure 5 The information interaction method shown may also include but is not limited to the following steps:

[0275] S308, the second network element (such as NWDAF containing MTLF) sends a fourth request to the first network element (such as ADRF), where the fourth request is used to request to update or delete the above-mentioned model A. The fourth request includes the NF instance ID, and the fourth request also includes the model ID or storage transaction ID of model A.

[0276] Correspondingly, the first network element (such as ADRF) receives the fourth request.

[0277] S309: If the NF instance ID carried by the fourth request is the NF instance ID of the second network element, the first network element (such as ADRF) processes model A according to the fourth request.

[0278] In a possible implementation, the implementation of step S308 and step S309 in the embodiment of the present application can refer to the implementation of step S107 and step S108 in the aforementioned embodiment 1, which will not be repeated here.

[0279] It is understood that the embodiment of the present application does not limit the execution order between step S308-step S309 and step S304-step S307. For example, step S308-step S309 can be executed after step S304-step S307, or before step S304-step S307. For details, please refer to the relevant description of the above embodiment 1, which will not be repeated here.

[0280] Embodiment 4

[0281] Embodiment 4 of the present application mainly introduces the processing logic of ADRF when a storage request does not carry an allowed NFc list, indicating that the model producer (such as NWDAF containing MTLF) authorizes all network elements to obtain the model.

[0282] The "obtaining model" in the embodiment of the present application can be understood as: downloading (or obtaining) the model from ADRF to the local, and can also be understood as "retrieve model" or "access model".

[0283] See also Figure 6 , Figure 6 This is a fourth flow chart of the information interaction method provided in the application embodiment. In this method, the first network element may be an ADRF, the second network element may be an NWDAF including an MTLF, and of course the second network element may also be an NWDAF including an MTLF and an AnLF, which is not limited in the present application embodiment. The third network element may be an NWDAF including an AnLF.

[0284] like Figure 6 As shown, the information interaction method includes but is not limited to the following steps:

[0285] S401, the second network element (such as NWDAF containing MTLF) sends a first request to the first network element (such as ADRF), where the first request is used to request storage of model A, and the first request includes: a model ID of model A, and an NF instance ID of the second network element, and the first request does not include an allowed NFc list corresponding to model A.

[0286] Correspondingly, the first network element (such as ADRF) receives the first request.

[0287] In a possible implementation method, the implementation method of step S401 in the embodiment of the present application can refer to the implementation method of step S101 in the aforementioned embodiment 1, which is not repeated here.

[0288] S402, the first network element (such as ADRF) determines that the second network element authorizes all network elements to obtain the model A according to the fact that the first request does not include the allowed NFclist corresponding to the model A.

[0289] In a possible implementation, before step S401, for example, in the network element registration process, the first network element (such as ADRF) sends a third request to the network storage function (NRF) network element. The third request can be used to notify or register the NF configuration file of the first network element to the NRF network element. The third request may include indication information a, which is used to indicate that when the allowedNFc list corresponding to the model does not exist, all network elements can obtain the model. In other words, the indication information a is used to indicate that when the first network element receives the model management storage request, if the model management storage request does not include the allowed NFclist corresponding to the model, the model authorization logic of the first network element is that the model producer (such as NWDAF containing MTLF) authorizes all network elements to obtain the model, or the model is allowed to be obtained by all network elements. The second network element discovers the first network element according to the network element discovery process, and can obtain the model authorization logic of the first network element when the allowed NFc list does not exist from the NRF network element. Then the second network element decides to store the model in the first network element according to the model authorization logic of the first network element and its own storage policy, that is, executes step S101. Therefore, after the first network element receives the above-mentioned first request, it can be determined that the second network element authorizes all network elements to obtain model A, or that model A is allowed to be obtained by all network elements, based on the fact that the first request does not include the allowed NFc list corresponding to model A and the locally preconfigured model authorization logic.

[0290] Alternatively, before step S401, for example, in the network element registration process, the second network element (such as NWDAF containing MTLF) sends a third request to the network storage function (NRF) network element. The third request can be used to notify or register the NF configuration file of the second network element to the NRF network element. The third request may include indication information a, which is used to indicate that when the allowedNFc list corresponding to the model does not exist, all network elements can obtain the model. In other words, the indication information a is used to indicate that when the allowedNFc list corresponding to the model does not exist in the model management storage request, the model authorization logic of the second network element is that the model producer (such as NWDAF containing MTLF) authorizes all network elements to obtain the model, or the model is allowed to be obtained by all network elements. The first network element discovers the second network element according to the network element discovery process, and can obtain the model authorization logic of the second network element from the NRF network element when the allowedNFc list does not exist. Then, after the first network element receives the above-mentioned first request, according to the fact that the first request does not include the allowed NFc list corresponding to model A and the model authorization logic of the second network element, it can be determined that the second network element authorizes all network elements to obtain model A, or that model A is allowed to be accessed by all network elements.

[0291] In another possible implementation, when the allowed NFc list corresponding to the predefined model in the standard protocol does not exist, it means that the model producer (such as NWDAF containing MTLF) authorizes all network elements to obtain the model, or the model is allowed to be obtained by all network elements. Then, when the above-mentioned first request does not include the allowed NFc list corresponding to model A, it can be used to indicate that the second network element authorizes all network elements to obtain model A. Therefore, after the first network element receives the above-mentioned first request, it can be determined that the second network element authorizes all network elements to obtain model A, or that model A is allowed to be obtained by all network elements, based on the fact that the first request does not include the allowed NFc list corresponding to model A.

[0292] It can be understood that the "all network elements" in the embodiment of the present application can be all NWDAF network elements, or any network element in the network, and the embodiment of the present application does not limit it. That is to say, for model A, when acquiring or retrieving the model, ADRF does not need to verify the model acquisition authority of NFc, as long as NFc provides the model acquisition index (such as model ID or storage transaction ID), it can acquire the corresponding model.

[0293] S403: The first network element (such as ADRF) stores the model ID.

[0294] In a possible implementation, after receiving the first request, the first network element may obtain (e.g., download) the model A from the second network element according to the address of the model A in the second network element (e.g., URL1) and store it locally. Then, the first network element may store the model ID of the model A. If the first network element generates a storage transaction identifier (Storage Transaction ID) for all models requested to be stored in the first request, the first network element may also store the Storage TransactionID, thereby recording the corresponding relationship between the model ID of the model A and the Storage Transaction ID.

[0295] In one possible implementation, the first network element can also store the NF instance ID of the second network element, thereby recording the correspondence between the NF instance ID of the second network element and the model ID of model A, or recording the correspondence between the NF instance ID of the second network element, the model ID of model A, and the Storage Transaction ID; for subsequent use.

[0296] S404: The first network element (such as ADRF) sends a first response to the second network element (such as NWDAF containing MTLF), where the first response includes the model ID of model A, or the first response includes the model ID of model A and a storage transaction ID.

[0297] In a possible implementation method, the implementation method of step S404 of the embodiment of the present application can refer to the implementation method of step S103 in the aforementioned embodiment 1, which is not repeated here.

[0298] In the embodiment of the present application, when the storage request (i.e., the first request mentioned above) does not carry the allowed NFc list of the model, it indicates that the model producer (such as NWDAF containing MTLF) authorizes all network elements to obtain this model, thereby improving the storage solution of the model and aligning (or synchronizing) the model acquisition permissions at both ends of the first network element and the second network element.

[0299] In a possible implementation, after step S404, if the model is to be retrieved / acquired from the first network element (such as ADRF), the above Figure 6 The information interaction method shown may also include but is not limited to the following steps:

[0300] S405 : The third network element (eg NWDAF containingAnLF) sends a model providing request to the second network element (eg NWDAF containingMTLF). The model providing request includes the analysis ID of model A. The model providing request is used to request the second network element to provide model A.

[0301] Correspondingly, the second network element (such as NWDAF containing MTLF) receives the model providing request.

[0302] S406: The second network element (such as NWDAF containing MTLF) sends a model provision response to the third network element (such as NWDAF containing AnLF), where the model provision response includes a model ID or a storage transaction ID.

[0303] Correspondingly, the third network element (such as NWDAF containingAnLF) receives the model and provides a response.

[0304] In a possible implementation method, the implementation method of step S405-step S406 of the embodiment of the present application can refer to the implementation method of step S304-step S305 in the aforementioned embodiment 3, which will not be repeated here.

[0305] S407: The third network element (such as NWDAF containingAnLF) sends a second request to the first network element (such as ADRF). The second request is used to request to obtain model A. The second request includes the model ID of model A or the storage transaction ID.

[0306] Correspondingly, the first network element (such as ADRF) receives the second request.

[0307] In a possible implementation, the implementation of step S407 of the embodiment of the present application can refer to the implementation of step S104 in the aforementioned embodiment 1, which will not be repeated here.

[0308] S408, if the model ID or storage transaction ID carried in the second request does not have a corresponding allowed NFclist, the first network element (such as ADRF) sends a second response to the third network element (such as NWDAF containingAnLF), and the second response carries the information of model A stored in the first network element.

[0309] Correspondingly, the third network element (such as NWDAF containingAnLF) receives the second response.

[0310] In one possible implementation, after receiving the second request, the first network element may verify whether the allowed NFc list corresponding to the model ID or storage transaction ID carried in the second request is stored locally. If the model ID or storage transaction ID carried in the second request does not have a corresponding allowed NFc list, it means that the model A corresponding to the model ID or storage transaction ID is authorized to be acquired by all network elements, and the first network element may send a second response to the third network element. For the implementation of the second response, please refer to the description in the aforementioned embodiment 1, which will not be repeated here. It can be understood that the first network element may also need to verify other information. If all verifications are passed, the first network element returns a second response to the third network element, which is not limited in the embodiments of the present application.

[0311] It can be understood that if the third network element and the second network element are the same network element, the above steps S405 and S406 may not be performed.

[0312] In the embodiment of the present application, when the storage request (i.e., the first request mentioned above) does not carry the allowed NFc list of the model, it indicates that the model producer (such as NWDAF containing MTLF) authorizes all network elements to obtain the model, thus improving the storage scheme of the model; when searching, the first network element determines the authority of the model, and if the authority of the model allows all network elements to obtain it, the model is returned. The judgment logic of the first network element during the model authorization check is clarified, the storage scheme of the model is improved, and the model acquisition authority of the first network element and the second network element is aligned (or synchronized).

[0313] In a possible implementation, after step S404, if the second network element (such as NWDAF containing MTLF) wants to update or delete the model stored in the first network element (such as ADRF), the above Figure 6 The information interaction method shown may also include but is not limited to the following steps:

[0314] S409, the second network element (such as NWDAF containing MTLF) sends a fourth request to the first network element (such as ADRF), where the fourth request is used to request to update or delete the above-mentioned model A. The fourth request includes the NF instance ID, and the fourth request also includes the model ID or storage transaction ID of model A.

[0315] Correspondingly, the first network element (such as ADRF) receives the fourth request.

[0316] S410: If the NF instance ID carried by the fourth request is the NF instance ID of the second network element, the first network element (such as ADRF) processes model A according to the fourth request.

[0317] In a possible implementation, the implementation of step S409 and step S410 in the embodiment of the present application can refer to the implementation of step S107 and step S108 in the aforementioned embodiment 1, which will not be repeated here.

[0318] It is understandable that NWDAF containing MTLF can retrain the model or generate a new model according to its internal logic. However, when the model is retrained or generated and stored in ADRF, how to set the access permission of this model remains to be solved.

[0319] Embodiment 5

[0320] Embodiment 5 of the present application mainly introduces how to set the access permission of the model after NWDAF containing MTLF retrains or generates a new model.

[0321] It can be understood that the fifth embodiment of the present application can be implemented in combination with any of the aforementioned embodiments one to four, or can be implemented alone, and the present application does not limit this.

[0322] See also Figure 7 , Figure 7 This is a fifth flow chart of the information interaction method provided in the application embodiment. In this method, the first network element may be an ADRF, and the second network element may be an NWDAF including an MTLF. Of course, the second network element may also be an NWDAF including an MTLF and an AnLF, which is not limited in the embodiment of the application.

[0323] like Figure 7 As shown, the information interaction method includes but is not limited to the following steps:

[0324] S501: A second network element (such as NWDAF containing MTLF) determines a second model based on the first model.

[0325] S502, the second network element (such as NWDAF containing MTLF) sends a storage request to the first network element (such as ADRF), where the storage request is used to request to store the second model in the first network element, and the storage request includes: an allowed NFc list corresponding to the second model; wherein the allowed NFc list corresponding to the second model is determined based on the allowedNFc list corresponding to the first model.

[0326] Correspondingly, the first network element (such as ADRF) receives the storage request.

[0327] In a possible implementation, the second network element re-provides the second model based on the accuracy of the first model. Exemplarily, the second network element finds that the accuracy of the first model is lower than a preset threshold according to its internal logic, or the first model can no longer meet the requirements of the model consumer (such as NWDAF containingAnLF), and can retrain the first model to obtain the second model, or regenerate a new model, i.e., the second model. For example: Model M1 is the model initially trained by the second network element for the third network element (such as NWDAF containingAnLF). Subsequently, when the second network element detects that in some special cases, such as special time periods, holidays, morning rush hours, etc., which are significantly different from general scenarios, the second network element additionally trains a new model M2 for such cases, or retrains model M1 to obtain model M2. However, model M1 is not completely deactivated, so in general, the third network element can use model M1, and model M2 in special cases, so that the third network element can obtain better model performance.

[0328] In a possible implementation, after the second network element obtains the second model, the second network element may send a storage request 1 to the first network element, and the storage request 1 may be used to request to store the second model in the first network element. The storage request 1 may include, but is not limited to: the NF instance ID of the second network element, the model ID of the second model, the address of the second model in the second network element, and the allowed NFc list corresponding to the second model. Accordingly, the first network element may return a storage response 1 to the second network element. Among them, the allowed NFc list corresponding to the second model is determined based on the allowed NFc list corresponding to the first model. For example, the allowed NFc list corresponding to the second model is the same as the allowed NFc list corresponding to the first model. In other words, when the second network element determines that the model consumers of the first model and the second model are consistent, the second network element can use the allowed NF consumer list corresponding to the first model as the allowed NF consumer list corresponding to the second model. For another example, the second network element determines that the AllowedNFclist corresponding to the first model is AllowedNFclist1, and AllowedNFclist1 includes all consumer network elements of the current first model. Subsequently, the second network element generates the second model according to the internal logic. At this time, due to changes in network configuration or business relationships, the new model (i.e., the second model) generated by the second network element no longer provides services to certain network elements. At this time, the AllowedNFclist corresponding to the second model can be a subset of the AllowedNFclist corresponding to the first model. Alternatively, the new model (i.e., the second model) generated by the second network element has newly added several consumer network elements, and the AllowedNFclist corresponding to the second model can include the AllowedNFclist corresponding to the first model and the newly added consumer network elements.

[0329] In a possible implementation, before the second network element sends a storage request to the first network element, the second network element may also store the first model to the first network element. Exemplarily, the second network element sends a storage request 2 to the first network element, and the storage request 2 may be used to request the first model to be stored in the first network element. The storage request 2 may include, but is not limited to: the NFinstance ID of the second network element, the model ID of the first model, and the address of the first model in the second network element. Accordingly, the first network element may return a storage response 2 to the second network element. Optionally, the storage request 2 also includes an allowed NFclist corresponding to the first model. It can be understood that if the storage request 2 does not include the allowed NFc list corresponding to the first model, after the second network element stores the first model to the first network element, the second network element may add the allowedNFc list corresponding to the first model in the first network element through a model management storage update operation (such as sending a Nadrf_MLModelManagement_Storage Update message).

[0330] In an embodiment of the present application, when the access permissions of two models (such as the first model and the second model) are the same, the allowed NFc list of the previously stored model (i.e., the first model) is used to replace the allowed NFc list of the latest generated model (i.e., the second model), thereby clarifying / improving the setting method of model access permissions in the retraining scenario.

[0331] At present, in the prior art, when NFc (such as NWDAF containing AnLF) requests NFp (NWDAF containing MTLF) to provide a model, NFp (NWDAF containing MTLF) can return Storage transaction ID or model ID. However, the processing logic of NFp (NWDAF containing MTLF) returning Storage transaction ID or model ID is unclear.

[0332] Embodiment 6

[0333] Embodiment 6 of the present application mainly introduces the processing logic of the NFp (NWDAF containing MTLF) side returning the Storagetransaction ID or model ID.

[0334] It can be understood that the sixth embodiment of the present application can be implemented in combination with any of the aforementioned embodiments one to four, and can also be implemented in combination with the aforementioned embodiment five, and of course can also be implemented alone, and the present application does not limit this.

[0335] See also Figure 8 , Figure 8 This is a sixth flow chart of the information interaction method provided in the application embodiment. In this method, the second network element may be a NWDAF containing MTLF, and of course the second network element may also be a NWDAF containing MTLF and AnLF, which is not limited in the embodiment of the application. The third network element may be a NWDAF containingAnLF.

[0336] like Figure 8 As shown, the information interaction method includes but is not limited to the following steps:

[0337] S601, a third network element (such as NWDAF containingAnLF) sends a model providing request to a second network element (such as NWDAF containingMTLF), where the model providing request includes an analysis ID and is used to request the second network element to provide a model corresponding to the analysis ID.

[0338] Correspondingly, the second network element (such as NWDAF containing MTLF) receives the model providing request.

[0339] S602: The second network element (such as NWDAF containing MTLF) sends a model provision response to a third network element (such as NWDAF containing AnLF), where the model provision response includes a model ID or a storage transaction ID.

[0340] Correspondingly, the third network element (such as NWDAF containingAnLF) receives the model and provides a response.

[0341] In a possible implementation, the model provision request may include but is not limited to an analysis ID, and may optionally include a vendor ID and / or an access token of a third network element. The model provision request may be used to request the second network element to provide a model corresponding to the analysis ID. Exemplarily, the model provision request may be Nnwdaf_MLModelProvision Request.

[0342] In one possible implementation, the above-mentioned analysis ID may correspond to one or more storage transaction identifiers. It can be understood that the analysis identifier can be used to identify the function / role of the model, and there may be multiple models used to implement the same function. Therefore, one analysis identifier may correspond to one or more models. A storage transaction identifier can be understood as a credential for one storage, and one or more models can be stored at a time, so a storage transaction identifier can index one or more models. Therefore, the analysis identifier and the storage transaction identifier can generate a corresponding relationship through the model. For example, one analysis identifier can correspond to one or more storage transaction identifiers.

[0343] In a possible implementation, after receiving the above model provision request, the second network element can determine which models in the model corresponding to the analysis ID are authorized to be obtained by the third network element according to the model provision request and internal logic, and then return a model provision response to the third network element. The model provision response may include a model ID or a storage transaction ID, and optionally also includes the ID of the first network element (such as ADRF).

[0344] Exemplarily, the second network element first determines the model authorized to be acquired by the third network element in the (one or more) models corresponding to the analysis ID carried in the above-mentioned model provision request, and then checks whether the model authorized to be acquired by the third network element has a storage transaction ID. If there is a storage transaction ID, it is determined whether the (one or more) models corresponding to the storage transaction ID are all authorized to be acquired by the third network element; if the (one or more) models corresponding to the storage transaction ID are all authorized to be acquired by the third network element, the storage transaction ID can be carried in the model provision response; in other cases, the model ID can be carried in the model provision response. For example, if the (one or more) models corresponding to the storage transaction ID include models that are not authorized to be acquired by the third network element, the ID of the model authorized to be acquired by the third network element in the (one or more) models corresponding to the analysis ID can be carried in the model provision response. For another example, if the models authorized to be acquired by the third network element in the (one or more) models corresponding to the analysis ID do not have a storage transaction ID, the ID of the model authorized to be acquired by the third network element in the (one or more) models corresponding to the analysis ID can be carried in the model provision response.

[0345] In the embodiment of the present application, when all the models corresponding to the storage transaction ID of a certain model authorized to be obtained by the third network element in the model corresponding to the analysis ID are authorized to be obtained by the third network element, the storage transaction ID is returned to the third network element; otherwise, the model ID authorized to be obtained by the third network element in the model corresponding to the analysis ID is returned to the third network element. This not only clarifies the processing logic of the second network element returning the Storage transaction ID or model ID, but also reduces the risk of the third network element unauthorizedly obtaining the model from the first network element (such as ADRF) through the Storage transaction ID.

[0346] This is because in the prior art, when the model corresponding to the analysis ID has a storage transaction ID that is authorized to be obtained by the third network element, the second network element returns the storage transaction ID to the third network element, but the storage transaction ID may index multiple models, and there are models among these multiple models that are not authorized to the third network element. In this case, when the third network element uses the storage transaction ID obtained from the second network element to retrieve / obtain the model, the first network element (such as ADRF) may return all models corresponding to the storage transaction ID to the third network element. For example, the second network element stores model M1, model M2, and model M3 to the first network element (such as ADRF), and the storage transaction IDs of these three models are all Storage Transaction ID1; the analysis IDs of model M1 and model M2 are analysis ID1, and the analysis ID of model M3 is analysis ID2, and when stored, the allowed NFclist of model M3 does not exist. Assuming that the allowed NFclist does not exist, the judgment logic of the first network element during the model authorization check is that other network elements can obtain it. In the prior art, the third network element uses analysis ID1 to request the second network element to provide the model corresponding to analysis ID1. Assuming that both model M1 and model M2 are authorized to be obtained by the third network element, since model M1 and model M2 correspond to storage transaction IDs, the second network element will return Storage Transaction ID1 to the third network element. Then when the third network element uses StorageTransaction ID1 to retrieve / obtain the model from the first network element, the first network element will return model M1, model M2 and model M3 to the third network element. But in fact, the second network element did not authorize the third network element to obtain model M3. Therefore, the third network element obtained model M3 beyond its authority, which poses a risk of model leakage.

[0347] When the second network element of the embodiment of the present application has not fully authorized the third network element to obtain the model corresponding to the storage transaction ID, it will not return the storage transaction ID to the third network element, thereby reducing the risk of model leakage.

[0348] Currently, the existing technology allows NFc (such as NWDAF containingAnLF) to use Storage transactionID to retrieve / obtain the model, but the processing logic after the ADRF side receives the Storage transaction ID is unclear.

[0349] Embodiment 7

[0350] Embodiment 7 of the present application mainly introduces the processing logic after the ADRF side receives the Storage transaction ID when NFc (such as NWDAF containing AnLF) uses the Storage transaction ID to retrieve / acquire the model.

[0351] It can be understood that the embodiment of the present application can be implemented in combination with the aforementioned embodiment 6, or can be implemented alone, and the present application does not limit it. When the embodiment of the present application is implemented in combination with the aforementioned embodiment 6, the embodiment of the present application is executed after the aforementioned embodiment 6. In other words, in the embodiment of the present application, the third network element can obtain the storage transaction identifier from the second network element according to the method provided in the aforementioned embodiment 6, or can obtain the storage transaction identifier from the second network element in other ways, and the present application does not limit it.

[0352] See also Fig. 9 , Fig. 9 This is a sixth flow chart of the information interaction method provided in the application embodiment. In this method, the first network element may be an ADRF, and the third network element may be an NWDAF containingAnLF.

[0353] like Fig. 9 As shown, the information interaction method includes but is not limited to the following steps:

[0354] S701, a third network element (such as NWDAF containingAnLF) sends a second request to a first network element (such as ADRF), where the second request is used to request to obtain a model from the first network element, and the second request includes a storage transaction ID.

[0355] Correspondingly, the first network element (such as ADRF) receives the second request.

[0356] S702: The first network element (such as ADRF) sends a second response to the third network element (such as NWDAF containing AnLF). Correspondingly, the third network element (such as NWDAF containing AnLF) receives the second response.

[0357] In a possible implementation, the second request may be used to request to obtain a model from the first network element. Exemplarily, the second request may be a Nadrf_MLModelManagement_Retrieval Request. The second request may include, but is not limited to, a storage transaction ID. Among them, the storage transaction ID may be obtained by the third network element from the second network element (such as NWDAF containing MTLF) through a model provision request (for example, Nnwdaf_MLModelProvision Request). The specific acquisition method is not limited in the embodiments of the present application. For example, you may refer to the aforementioned embodiment five, which will not be repeated here. Of course, other methods may also be used.

[0358] In a possible implementation, after receiving the second request, the first network element may return a second response to the third network element. If the model corresponding to the storage transaction ID carried by the second request contains a model that is authorized to be obtained by the third network element, the second response may include the model that is authorized to be obtained by the third network element and / or the address of the model in the first network element in the model corresponding to the storage transaction ID. Alternatively, if not all models corresponding to the storage transaction ID carried by the second request are authorized to be obtained by the third network element, the second response may be used to reject the second request.

[0359] When the third network element in the embodiment of the present application uses the Storage transaction ID to retrieve / acquire the model, after receiving the Storage transaction ID, the first network element returns only the model corresponding to the Storage transaction ID that is authorized for the third network element to obtain to the third network element; or, if not all the models corresponding to the Storage transaction ID are authorized for the third network element to obtain, the request of the third network element is rejected. The processing logic after the ADRF side receives the Storage transaction ID is clarified, and the solution is improved.

[0360] The above content elaborates on the method of the present application in detail. In order to facilitate better implementation of the above scheme of the embodiment of the present application, the embodiment of the present application also provides corresponding devices or equipment.

[0361] The embodiment of the present application can divide the functional modules of each network element of the present application according to the above method example, and also divide the functional modules of the above network elements according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic, which is only a logical functional division. There may be other division methods in actual implementation. The following will be combined with Figures 10 to 12 The communication device according to the embodiment of the present application is described in detail.

[0362] See also Fig.10 , Fig.10 Schematic diagram of a communication device provided in an embodiment of the present application. Fig.10 As shown, the communication device includes a transceiver unit 10 and a processing unit 20. Optionally, the communication device also includes a storage unit 30. The transceiver unit 10 can implement corresponding communication functions, the processing unit 20 is used for data processing, and the storage unit 30 is used for storing information or data. For example, the transceiver unit 10 can also be called a communication interface or a communication unit.

[0363] In some embodiments of the present application, the communication device may be the first network element shown above. Fig.10 The communication device shown can be used to execute the steps or functions performed by the first network element in the above method embodiment. Exemplarily, the communication device can be the first network element or a chip or functional module configured in the first network element, etc., which is not limited in the embodiments of the present application. The transceiver unit 10 is used to execute the operations related to the first network element transceiver in the above method embodiment, the processing unit 20 is used to execute the operations related to the first network element processing in the above method embodiment, and the storage unit 30 is used to execute the operations related to the first network element storage in the above method embodiment.

[0364] Exemplarily, the transceiver unit 10 is used to receive a first request from a second network element, where the first request is used to request a storage model, the first request includes an NF instance identifier of the second network element, and the first request does not include an allowed NFc list corresponding to the model; the processing unit 20 is used to generate an allowed NFc list for the model, where the allowedNFc list includes the NF instance identifier of the second network element, and the NF instance identifier of the second network element included in the allowed NFc list is used to authorize the model; the transceiver unit 10 is also used to send a first response to the first request to the second network element.

[0365] Exemplarily, the first request further includes the model identifier of the model. The storage unit 30 is configured to store the NF instance identifier of the second network element, the allowed NFc list generated by the processing unit 20, and the model identifier.

[0366] Exemplarily, the transceiver unit 10 is further used to: receive a second request, the second request being used to request acquisition of the above-mentioned model; and when the NF instance identifier carried by the second request is in the above-mentioned allowed NFc list, send a second response to the second request, the second response carrying information of the model stored in the first network element.

[0367] Exemplarily, the processing unit 20 is further used to: reject the second request if the NF instance identifier carried in the second request is not in the above-mentioned allowed NFc list.

[0368] Exemplarily, the first request further includes first indication information, where the first indication information is used to indicate that the second network element has not authorized other network elements to obtain the model.

[0369] Exemplarily, the processing unit 20 is further configured to: determine, according to the first request not including the allowedNFc list corresponding to the model, that the second network element does not authorize other network elements to obtain the model.

[0370] Exemplarily, the transceiver unit 10 is also used to: send a third request to the NRF network element, the third request is used to notify or register the NF configuration file of the first network element to the NRF network element, the third request includes second indication information, and the second indication information is used to indicate that when the allowed NFc list corresponding to the model does not exist, other network elements cannot obtain the above model.

[0371] Exemplarily, the first request does not include an allowed NFc list corresponding to the model, which is used to indicate that the second network element does not authorize other network elements to obtain the model.

[0372] Exemplarily, the transceiver unit 10 is further used to receive a fourth request, where the fourth request is used to request to update or delete the above-mentioned model, and the fourth request includes an NF instance identifier; the processing unit 20 is further used to process the model according to the fourth request when the NF instance identifier carried by the fourth request is the NF instance identifier of the second network element.

[0373] In the embodiment of the present application, the specific description of the first request, the first response, the second request, the second response, the third request, the fourth request, and each network element, etc. can be referred to the method embodiment 1 shown above, and will not be described in detail here.

[0374] It is understandable that the specific description of the transceiver unit and the processing unit shown in the embodiment of the present application is only an example. For the specific functions or execution steps of the transceiver unit and the processing unit, reference can be made to the above-mentioned method embodiment 1, which will not be described in detail here. In addition, the technical effects of the embodiment of the present application refer to the technical effects in the above-mentioned method embodiment 1, and for the sake of brevity, they will not be repeated here.

[0375] Exemplarily, the transceiver unit 10 is used to receive a first request from the second network element, the first request is used to request the storage of the model, the first request includes: a model identifier of the model, and an NF instance identifier of the second network element, and the first request does not include an allowed NFc list corresponding to the model; the storage unit 30 is used to store the NF instance identifier of the second network element and the model identifier; the transceiver unit 10 is also used to send a first response to the first request to the second network element; the transceiver unit 10 is also used to receive a second request, the second request is used to request to obtain the model; the transceiver unit 10 is also used to send a second response to the second request when the NF instance identifier carried by the second request is the stored NF instance identifier of the second network element, the second response carries information of the model stored by the first network element.

[0376] Exemplarily, the processing unit 20 is configured to generate a first response and a second response.

[0377] Exemplarily, the processing unit 20 is further used to reject the second request if the NF instance identifier carried by the second request is not the NF instance identifier of the stored second network element.

[0378] Exemplarily, the processing unit 20 is further configured to generate an allowed NFc list for the model, wherein the allowedNFc list is empty.

[0379] Exemplarily, the first request further includes first indication information, where the first indication information is used to indicate that the second network element has not authorized other network elements to obtain the model.

[0380] Exemplarily, the processing unit 20 is further configured to determine, based on the fact that the first request does not include an allowed NFclist corresponding to the model, that the second network element does not authorize other network elements to obtain the model.

[0381] Exemplarily, the transceiver unit 10 is also used to send a third request to the NRF network element, where the third request is used to notify or register the NF configuration file of the first network element to the NRF network element, and the third request includes second indication information, where the second indication information is used to indicate that when the allowed NFc list corresponding to the model does not exist, other network elements cannot obtain the model.

[0382] Exemplarily, the first request does not include an allowed NFc list corresponding to the model, which is used to indicate that the second network element does not authorize other network elements to obtain the model.

[0383] Exemplarily, the transceiver unit 10 is further used to receive a fourth request, where the fourth request is used to request to update or delete the model, and the fourth request includes an NF instance identifier; the processing unit 20 is further used to process the model according to the fourth request when the NF instance identifier carried by the fourth request is the NF instance identifier of the second network element.

[0384] In the embodiment of the present application, the specific description of the first request, the first response, the second request, the second response, the third request, the fourth request, and each network element, etc. can be referred to the method embodiment 2 shown above, and will not be described in detail here.

[0385] It is understandable that the specific description of the transceiver unit and the processing unit shown in the embodiment of the present application is only an example. For the specific functions or execution steps of the transceiver unit and the processing unit, reference can be made to the above-mentioned method embodiment 2, which will not be described in detail here. In addition, the technical effects of the embodiment of the present application refer to the technical effects in the above-mentioned method embodiment 2, and for the sake of brevity, they will not be repeated here.

[0386] Exemplarily, the transceiver unit 10 is used to receive a first request from a second network element, the first request being used to request storage of a model, the first request comprising: a model identifier of the model, and indication information, the indication information being used to indicate that the second network element authorizes all network elements to obtain the model; the transceiver unit 10 is also used to send a first response to the first request to the second network element; the transceiver unit 10 is also used to receive a second request from a third network element, the second request being used to request acquisition of the model; the transceiver unit 10 is also used to send a second response to the second request to the third network element according to the indication information, the second response carrying information of the model stored by the first network element.

[0387] Exemplarily, the processing unit 20 is configured to generate a first response and a second response.

[0388] Exemplarily, the storage unit 30 is used to store the model identifier and the indication information.

[0389] Exemplarily, the transceiver unit 10 is specifically configured to send a second response to the second request to the third network element when the model identifier or the storage transaction identifier carried in the second request corresponds to the stored indication information.

[0390] Exemplarily, the first request further includes an allowed NFc list corresponding to the model, and the indication information is located in the allowed NFc list.

[0391] Exemplarily, the first request also includes a network function NF instance identifier of the second network element. The transceiver unit 10 is further configured to receive a fourth request from the second network element, the fourth request being used to request to update or delete the model, the fourth request including the NF instance identifier; the processing unit 20 is further configured to process the model according to the fourth request when the NF instance identifier carried by the fourth request is the NF instance identifier of the second network element.

[0392] In the embodiment of the present application, the specific description of the first request, the first response, the second request, the second response, the fourth request, and each network element, etc. can be referred to the method embodiment three shown above, and will not be described in detail here.

[0393] It is understandable that the specific description of the transceiver unit and the processing unit shown in the embodiment of the present application is only an example. For the specific functions or execution steps of the transceiver unit and the processing unit, reference can be made to the above-mentioned method embodiment 3, which will not be described in detail here. In addition, the technical effects of the embodiment of the present application refer to the technical effects in the above-mentioned method embodiment 3, and for the sake of brevity, they will not be repeated here.

[0394] Exemplarily, the transceiver unit 10 is used to receive a first request sent by the second network element, the first request is used to request the storage of the model, and the first request includes: the model ID of the model, and the NF instance ID of the second network element; the processing unit 20 is used to determine that the second network element authorizes all network elements to obtain the model based on the fact that the first request does not include the allowed NFc list corresponding to model A; the transceiver unit 10 is also used to send a first response to the second network element, the first response includes the model ID of the model, or the first response includes the model ID and storage transaction ID of the model.

[0395] Exemplarily, the transceiver unit 10 is further used to receive a second request, where the second request is used to request to obtain the above-mentioned model, and the second request includes the model ID or storage transaction ID of the above-mentioned model; the transceiver unit 10 is also used to send a second response to the third network element when the model ID or storage transaction ID carried in the second request does not have a corresponding allowed NFc list, and the second response carries information about the above-mentioned model stored in the first network element.

[0396] Exemplarily, the transceiver unit 10 is further used to receive a fourth request from the second network element, where the fourth request is used to request to update or delete the model, and the fourth request includes an NF instance identifier; the processing unit 20 is further used to process the model according to the fourth request when the NF instance identifier carried by the fourth request is the NF instance identifier of the second network element.

[0397] In the embodiment of the present application, the specific description of the first request, the first response, the second request, the second response, the fourth request, and each network element, etc. can be referred to the method embodiment 4 shown above, and will not be described in detail here.

[0398] It is understandable that the specific description of the transceiver unit and the processing unit shown in the embodiment of the present application is only an example. For the specific functions or execution steps of the transceiver unit and the processing unit, reference can be made to the above-mentioned method embodiment 4, which will not be described in detail here. In addition, the technical effects of the embodiment of the present application refer to the technical effects in the above-mentioned method embodiment 4, which will not be repeated here for the sake of brevity.

[0399] Exemplarily, the transceiver unit 10 is used to receive a second request, where the second request is used to request to obtain a model, and the second request includes a storage transaction ID of the model; the transceiver unit 10 is used to send a second response to the third network element.

[0400] Among them, if there is a model authorized to be obtained by the third network element in the model corresponding to the storage transaction ID carried by the second request, the second response may include the model authorized to be obtained by the third network element and / or the address of the model in the first network element in the model corresponding to the storage transaction ID. In other cases, the second response is used to reject the above-mentioned second request. For example: if the model corresponding to the storage transaction ID carried by the second request is not fully authorized to be obtained by the third network element, the second response can be used to reject the second request.

[0401] In the embodiment of the present application, the specific description of the second request, the second response, and each network element, etc. can be referred to the method embodiment 7 shown above, and will not be described in detail here.

[0402] It is understandable that the specific description of the transceiver unit and the processing unit shown in the embodiment of the present application is only an example. For the specific functions or execution steps of the transceiver unit and the processing unit, reference can be made to the above-mentioned method embodiment VII, which will not be described in detail here. In addition, the technical effects of the embodiment of the present application refer to the technical effects in the above-mentioned method embodiment VII, which will not be repeated here for the sake of brevity.

[0403] Reuse Fig.10 In some other embodiments of the present application, the communication device may be the second network element shown above. Fig.10 The communication device shown can be used to execute the steps or functions performed by the second network element in the above method embodiment. Exemplarily, the communication device can be the second network element or a chip or functional module configured in the second network element, etc., which is not limited in the present embodiment. The transceiver unit 10 is used to execute the operations related to the second network element transceiver in the above method embodiment, and the processing unit 20 is used to execute the operations related to the second network element processing in the above method embodiment.

[0404] Exemplarily, the processing unit 20 is used to determine the second model based on the first model; the transceiver unit 10 is used to send a storage request to the first network element, the storage request is used to request to store the second model in the first network element, and the storage request includes: an allowed NFc list corresponding to the second model; wherein the allowed NFc list corresponding to the second model is determined based on the allowed NFc list corresponding to the first model.

[0405] Exemplarily, the processing unit 20 is specifically configured to re-provide the second model based on the accuracy of the first model.

[0406] Exemplarily, the processing unit 20 is specifically configured to obtain the second model by retraining the first model.

[0407] Exemplarily, the allowed NF consumer list corresponding to the second model is the same as the allowed NF consumer list corresponding to the first model.

[0408] In the embodiment of the present application, the specific description of the first storage request, the second storage request, and each network element, etc. can be referred to the method embodiment 5 shown above, and will not be described in detail here.

[0409] It is understandable that the specific description of the transceiver unit and the processing unit shown in the embodiment of the present application is only an example. For the specific functions or execution steps of the transceiver unit and the processing unit, reference can be made to the above-mentioned method embodiment 5, which will not be described in detail here. In addition, the technical effects of the embodiment of the present application refer to the technical effects in the above-mentioned method embodiment 5, and for the sake of brevity, they will not be repeated here.

[0410] Exemplarily, the transceiver unit 10 is used to receive a model provision request from a third network element, the model provision request includes an analysis identifier, and the model provision request is used to request the second network element to provide the model corresponding to the analysis identifier; the transceiver unit 10 is also used to send a model provision response to the third network element. Wherein, when the model authorized to be acquired by the third network element in the model corresponding to the analysis identifier has a storage transaction identifier, and all the models corresponding to the storage transaction identifier are authorized to be acquired by the third network element, the model provision response includes the storage transaction identifier. Or, when the model authorized to be acquired by the third network element in the model corresponding to the analysis identifier has a storage transaction identifier, and the model corresponding to the storage transaction identifier contains a model that is not authorized to be acquired by the third network element, the model provision response includes the identifier of the model authorized to be acquired by the third network element in the model corresponding to the analysis identifier.

[0411] Exemplarily, the processing unit 20 is used to generate a model provision response. In another exemplary embodiment, the processing unit 20 is used to control the transceiver unit 10 to receive a model provision request and send a model provision response.

[0412] In the embodiment of the present application, the specific description of the model providing request, the model providing response, and each network element, etc. can be referred to the method embodiment 6 shown above, and will not be described in detail here.

[0413] It is understandable that the specific description of the transceiver unit and the processing unit shown in the embodiment of the present application is only an example. For the specific functions or execution steps of the transceiver unit and the processing unit, reference can be made to the above-mentioned method embodiment 6, which will not be described in detail here. In addition, the technical effects of the embodiment of the present application refer to the technical effects in the above-mentioned method embodiment 6, which will not be repeated here for the sake of brevity.

[0414] Exemplarily, the transceiver unit 10 is used to send a first request to the first network element, where the first request is used to request the storage of a model, and the first request includes: a model identifier of the model, and indication information, where the indication information is used to instruct the second network element to authorize all network elements to obtain the model; the transceiver unit 10 is also used to receive a first response from the first network element.

[0415] Exemplarily, the first response includes the model identifier and a storage transaction identifier corresponding to the model.

[0416] Exemplarily, the transceiver unit 10 is used to receive a model provision request from a third network element, the model provision request includes an analysis identifier of the model, and the model provision request is used to request the second network element to provide the model; the transceiver unit 10 is also used to send a model provision response to the third network element. Wherein, when the model authorized to be acquired by the third network element in the model corresponding to the analysis identifier has a storage transaction identifier, and all the models corresponding to the storage transaction identifier are authorized to be acquired by the third network element, the model provision response includes the storage transaction identifier. Or, when the model authorized to be acquired by the third network element in the model corresponding to the analysis identifier has a storage transaction identifier, and the model corresponding to the storage transaction identifier contains a model that is not authorized to be acquired by the third network element, the model provision response includes the model identifier of the model.

[0417] Exemplarily, the processing unit 20 is used to generate a first request and a model providing request.

[0418] Exemplarily, the first request further includes an allowed NFc list corresponding to the model, and the indication information is located in the allowed NFc list.

[0419] In the embodiment of the present application, the specific description of the first request, the first response, the model providing request, the model providing response, and each network element, etc. can be referred to the method embodiment three shown above, and will not be described in detail here.

[0420] It is understandable that the specific description of the transceiver unit and the processing unit shown in the embodiment of the present application is only an example. For the specific functions or execution steps of the transceiver unit and the processing unit, reference can be made to the above-mentioned method embodiment 3, which will not be described in detail here. In addition, the technical effects of the embodiment of the present application refer to the technical effects in the above-mentioned method embodiment 3, and for the sake of brevity, they will not be repeated here.

[0421] The above describes the communication device of the embodiment of the present application, and the following describes possible product forms of the communication device. It should be understood that any device having the above Fig.10 Any form of product with the functions of the communication device described above falls within the protection scope of the embodiments of the present application. It should also be understood that the following description is only an example and does not limit the product form of the communication device of the embodiments of the present application to this.

[0422] In one possible implementation, Fig.10 In the communication device shown, the processing unit 20 may be one or more processors, the transceiver unit 10 may be a transceiver, or the transceiver unit 10 may also be a sending unit and a receiving unit, the sending unit may be a transmitter, the receiving unit may be a receiver, and the sending unit and the receiving unit are integrated into one device, such as a transceiver. In the embodiment of the present application, the processor and the transceiver may be coupled, etc., and the embodiment of the present application does not limit the connection mode of the processor and the transceiver. In the process of executing the above method, the process of sending information in the above method can be understood as the process of outputting the above information by the processor. When outputting the above information, the processor outputs the above information to the transceiver so that it is transmitted by the transceiver. After the above information is output by the processor, it may also need to be processed in other ways before it reaches the transceiver. Similarly, the process of receiving information in the above method can be understood as the process of the processor receiving the input 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 be processed in other ways before it is input into the processor.

[0423] See also Fig.11 , Fig.11 is another structural diagram of the communication device provided in the embodiment of the present application. Fig.11 As shown, the communication device provided in the embodiment of the present application can be used to implement the method described in the above method embodiment, and reference can be made to the description in the above method embodiment. The communication device can be the aforementioned first network element or second network element, or a chip or circuit therein. Exemplarily, the communication device includes one or more processors 1001 and a transceiver 1002. The communication device may further include a memory 1003. In one implementation, the communication device also includes an input and output device (not shown in the figure).

[0424] The processor 1001 is mainly used to process the communication protocol and communication data, and to control the entire communication device, execute the software program, and process the data of the software program. The memory 1003 is mainly used to store the software program and data. The transceiver 1002 may include a control circuit and an antenna. The control circuit is mainly used to convert the baseband signal and the radio frequency signal and process the radio frequency signal. The antenna is mainly used to send and receive radio frequency signals in the form of electromagnetic waves. The input and output devices, such as a touch screen, a display screen, a keyboard, etc., are mainly used to receive data input by the user and output data to the user.

[0425] When the communication device is turned 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 sent wirelessly, the processor 1001 performs baseband processing on the data to be sent, and outputs the baseband signal to the radio frequency circuit. The radio frequency circuit performs radio frequency processing on the baseband signal and then sends the radio frequency signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency 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.

[0426] In another implementation, the RF circuit and antenna may be arranged independently of the processor performing baseband processing. For example, in a distributed scenario, the RF circuit and antenna may be arranged remotely from the communication device.

[0427] The processor 1001 , the transceiver 1002 , and the memory 1003 may be connected via a communication bus.

[0428] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the first network element in the first embodiment of the above method, the processor 1001 may be used to execute Figure 3 Step S102, step S105 and step S108 in, and / or other processes for performing the technology described herein; the transceiver 1002 can be used to perform Figure 3 Steps S103 and S106 in, and / or other processes for the technology described herein.

[0429] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the second network element in the first embodiment of the method, the processor 1001 may be used to generate a first request, a second request, and a fourth request, and / or other processes for executing the technology described herein; the transceiver 1002 may be used to execute Figure 3 Steps S101, S104, and S107 in, and / or other processes for the technology described herein.

[0430] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the first network element in the second embodiment of the above method, the processor 1001 may be used to execute Figure 4 Steps S205 and S208 in, and / or other processes for performing the techniques described herein; the transceiver 1002 may be used to perform Figure 4 Step S203 and step S206 in, and / or other processes for the technology described herein; memory 1003 can be used to execute Figure 4Step S202 in , and / or other processes for performing the techniques described herein.

[0431] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the second network element in the second embodiment of the above method, the processor 1001 can be used to generate a first request, a second request, and a fourth request, and / or other processes for executing the technology described herein; the transceiver 1002 can be used to execute Figure 4 Steps S201, S204, and S207 in, and / or other processes for the technology described herein.

[0432] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the first network element in the third embodiment of the above method, the processor 1001 may be used to execute Figure 5 Step S309 in, and / or other processes for performing the techniques described herein; the transceiver 1002 may be used to perform Figure 5 Step S303 and step S307 in, and / or other processes for the technology described herein; memory 1003 can be used to execute Figure 4 Step S302 in , and / or other processes for performing the techniques described herein.

[0433] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the second network element in the third embodiment of the above method, the processor 1001 can be used to generate a first request, a fourth request, and a model to provide a response, and / or other processes for executing the technology described herein; the transceiver 1002 can be used to execute Figure 5 Steps S301, S305, and S308 in, and / or other processes for the technology described herein.

[0434] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the third network element in the third embodiment of the above method, the processor 1001 can be used to generate a model provision request, a second request, and / or other processes for executing the technology described herein; the transceiver 1002 can be used to execute Figure 5 Steps S304 and S306 in, and / or other processes for the technology described herein.

[0435] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the first network element in the fourth embodiment of the above method, the processor 1001 may be used to execute Figure 6 Steps S402 and S410 in, and / or other processes for performing the techniques described herein; the transceiver 1002 may be used to perform Figure 6Step S404 and step S408 in, and / or other processes for the technology described herein; memory 1003 can be used to execute Figure 4 Step S403 in , and / or other processes for performing the techniques described herein.

[0436] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the second network element in the fourth embodiment of the above method, the processor 1001 can be used to generate a first request, a fourth request, and a model to provide a response, and / or other processes for executing the technology described herein; the transceiver 1002 can be used to execute Figure 6 Steps S401, S406, and S409 in, and / or other processes for the technology described herein.

[0437] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the third network element in the fourth embodiment of the above method, the processor 1001 can be used to generate a model provision request, a second request, and / or other processes for executing the technology described herein; the transceiver 1002 can be used to execute Figure 6 Steps S405 and S407 in, and / or other processes for the technology described herein.

[0438] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the second network element in the fifth embodiment of the method, the processor 1001 may be used to execute Figure 7 Step S501 in, and / or other processes for performing the techniques described herein; the transceiver 1002 may be used to perform Figure 7 Step S502 in, and / or other processes for the technology described herein.

[0439] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the second network element in the sixth embodiment of the above method, the processor 1001 can be used to generate a model to provide a response, and / or to execute other processes of the technology described herein; the transceiver 1002 can be used to execute Figure 8 Step S602 in, and / or other processes for the technology described herein.

[0440] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the third network element in the sixth embodiment of the above method, the processor 1001 can be used to generate a model provision request, and / or to execute other processes of the technology described herein; the transceiver 1002 can be used to execute Figure 8 Step S601 in, and / or other processes for the technology described herein.

[0441] Exemplarily, when the communication device is used to execute the steps, methods or functions performed by the first network element in the seventh embodiment of the above method, the processor 1001 can be used to generate a second response, and / or to perform other processes of the technology described herein; the transceiver 1002 can be used to perform Fig. 9 Step S702 in, and / or other processes for the technology described herein.

[0442] Exemplarily, when the communication device is used to execute the steps, methods or functions executed by the third network element in the seventh embodiment of the method, the processor 1001 may be used to generate a second request, and / or to execute other processes of the technology described herein; the transceiver 1002 may be used to execute Figure 8 Step S701 in, and / or other processes for the technology described herein.

[0443] In any of the above implementations, the processor 1001 may include a transceiver for implementing the receiving and sending functions. For example, the transceiver may be a transceiver circuit, or an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing the receiving and sending functions may be separate or integrated. The above transceiver circuit, interface, or interface circuit may be used for reading and writing code / data, or the above transceiver circuit, interface, or interface circuit may be used for transmitting or delivering signals.

[0444] In any of the above implementations, the processor 1001 may store instructions, which may be computer programs. The computer programs run on the processor 1001, and may enable the communication device to perform the method described in the above method embodiment. The computer program may be fixed in the processor 1001, in which case the processor 1001 may be implemented by hardware.

[0445] In one implementation, the communication device may include a circuit that can implement the functions of sending or receiving or communicating in the aforementioned method embodiment. The processor and transceiver described in the present application can be implemented in an integrated circuit (IC), an analog IC, a radio frequency integrated circuit (RFIC), a mixed signal IC, an application specific integrated circuit (ASIC), a printed circuit board (PCB), an electronic device, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (nMetal-oxide-semiconductor, NMOS), P-channel metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (bipolar junction transistor, BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.

[0446] It is understandable that the communication device shown in the embodiment of the present application may also have Fig.11 The embodiments of the present application do not limit the number of components and the like. The methods executed by the processor and transceiver shown above are only examples, and the specific steps executed by the processor and transceiver can refer to the introduction of the above method embodiments.

[0447] In another possible implementation, Fig.10 In the communication device shown, the processing unit 20 may be one or more logic circuits, and the transceiver unit 10 may be an input / output interface, or a communication interface, or an interface circuit, or an interface, etc. Alternatively, the transceiver unit 10 may be a sending unit and a receiving unit, the sending unit may be an output interface, the receiving unit may be an input interface, and the sending unit and the receiving unit may be integrated into one unit, such as an input / output interface. Fig.12 , Fig.12 is another structural diagram of a communication device provided in an embodiment of the present application. Fig.12 As shown, Fig.12The communication device shown includes a logic circuit 901 and an interface 902. That is, the processing unit 20 can be implemented by the logic circuit 901, and the transceiver unit 10 can be implemented by the interface 902. The logic circuit 901 can be a chip, a processing circuit, an integrated circuit or a system on chip (SoC) chip, etc., and the interface 902 can be a communication interface, an input / output interface, a pin, etc. For example, Fig.12 The above communication device is taken as an example of a chip, and the chip includes a logic circuit 901 and an interface 902 .

[0448] In the embodiment of the present application, the logic circuit and the interface may also be coupled to each other. The embodiment of the present application does not limit the specific connection method between the logic circuit and the interface.

[0449] For example, Fig.12 The communication device shown can be used to implement the method described in the above method embodiment, and reference can be made to the description in the above method embodiment. The communication device can be any one of the above-mentioned first network element, second network element, or third network element.

[0450] It can be understood that the communication device shown in the embodiment of the present application can implement the method provided in the embodiment of the present application in the form of hardware, or can implement the method provided in the embodiment of the present application in the form of software, etc., and the embodiment of the present application is not limited to this.

[0451] for Fig.12 The specific implementation methods of the various embodiments shown can also refer to the above embodiments, which will not be described in detail here.

[0452] An embodiment of the present application also provides a communication system, which includes at least two of a first network element, a second network element, and a third network element. At least two of the first network element, the second network element, and the third network element can be used to execute the method in the aforementioned method embodiment.

[0453] In addition, the present application also provides a computer program, which is used to implement the operations and / or processing performed by the first network element in the method provided by the present application.

[0454] The present application also provides a computer program, which is used to implement the operations and / or processing performed by the second network element in the method provided by the present application.

[0455] The present application also provides a computer program, which is used to implement the operations and / or processing performed by the third network element in the method provided by the present application.

[0456] The present application also provides a computer-readable storage medium, in which computer code is stored. When the computer code is executed on a computer, the computer executes the operations and / or processing performed by the first network element in the method provided in the present application.

[0457] The present application also provides a computer-readable storage medium, in which computer code is stored. When the computer code runs on a computer, the computer executes the operations and / or processing performed by the second network element in the method provided in the present application.

[0458] The present application also provides a computer-readable storage medium, in which computer code is stored. When the computer code runs on a computer, the computer executes the operations and / or processing performed by the third network element in the method provided by the present application.

[0459] The present application also provides a computer program product, which includes a computer code or a computer program. When the computer code or the computer program runs on a computer, the operations and / or processing performed by the first network element in the method provided by the present application are executed.

[0460] The present application also provides a computer program product, which includes a computer code or a computer program. When the computer code or the computer program runs on a computer, the operations and / or processing performed by the second network element in the method provided by the present application are executed.

[0461] The present application also provides a computer program product, which includes a computer code or a computer program. When the computer code or the computer program runs on a computer, the operations and / or processing performed by the third network element in the method provided by the present application are executed.

[0462] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0463] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the technical effects of the solutions provided in the embodiments of the present application.

[0464] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0465] If the integrated unit is implemented in the form of 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 the present application is essentially or partly contributed to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a readable storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned readable storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0466] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An information interaction method, characterized in that: include: A first network element receives a first request from a second network element, where the first request is used to request a storage model, the first request includes a network function NF instance identifier of the second network element, and the first request does not include an allowed NF consumer list corresponding to the model; The first network element generates an allowed NF consumer list for the model, wherein the allowed NF consumer list includes the NF instance identifier of the second network element, and the NF instance identifier of the second network element included in the allowed NF consumer list is used to authorize the model; The first network element sends a first response to the first request to the second network element.

2. The method according to claim 1, characterized in that The first request also includes a model identifier of the model; The method also includes: the first network element storing the NF instance identifier of the second network element, the allowed NF consumer list, and the model identifier.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: The first network element receives a second request, where the second request is used to request to obtain the model; In a case where the NF instance identifier carried in the second request is in the allowed NF consumer list, the first network element sends a second response to the second request, where the second response carries information about the model.

4. The method according to claim 3, characterized in that The method also includes: if the NF instance identifier carried by the second request is not in the allowed NF consumer list, the first network element rejects the second request.

5. The method according to any one of claims 1 to 4, characterized in that The first request also includes first indication information, where the first indication information is used to indicate that the second network element has not authorized other network elements to obtain the model.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: The first network element determines that the second network element has not authorized other network elements to obtain the model based on the fact that the first request does not include the allowed NF consumer list corresponding to the model.

7. The method according to claim 6, characterized in that Before the first network element receives the first request from the second network element, the method further includes: The first network element sends a third request to the network storage function NRF network element, and the third request is used to notify the NRF network element of the NF configuration file of the first network element. The third request includes second indication information, and the second indication information is used to indicate that when the allowed network function NF consumer list corresponding to the model does not exist, other network elements cannot obtain the model.

8. The method according to claim 6, characterized in that The first request does not include the allowed NF consumer list corresponding to the model, which is used to indicate that the second network element does not authorize other network elements to obtain the model.

9. The method according to any one of claims 1 to 8, characterized in that After the first network element sends a first response to the first request to the second network element, the method further includes: The first network element receives a fourth request, where the fourth request is used to request to update or delete the model, and the fourth request includes an NF instance identifier; If the NF instance identifier carried by the fourth request is the NF instance identifier of the second network element, the first network element processes the model according to the fourth request.

10. The method according to any one of claims 1 to 9, characterized in that The first network element is an analysis data storage function ADRF network element, and the second network element is a network data analysis function NWDAF network element including a model training logic function MTLF.

11. An information interaction method, characterized in that: include: The second network element receives a model providing request from a third network element, the model providing request including an analysis identifier, the model providing request being used to request providing a first model corresponding to the analysis identifier, the analysis identifier corresponding to a storage transaction identifier; The second network element sends a model providing response to the third network element; Wherein, when the second model corresponding to the storage transaction identifier is authorized to be acquired by the third network element, the model provides a response including the storage transaction identifier; or, When the second model corresponding to the storage transaction identifier is not authorized to be acquired by the third network element, the response provided by the model does not include the storage transaction identifier.

12. The method according to claim 11, characterized in that The analysis identifier corresponds to a storage transaction identifier, including: a model in the first model corresponding to the analysis identifier and authorized to be acquired by the third network element has a storage transaction identifier.

13. The method according to claim 11 or 12, characterized in that: The second network element is a network data analysis function NWDAF network element including a model training logic function MTLF, and the third network element is a NWDAF network element including an analysis logic function ANLF.

14. A communication device, characterized in that: The method comprises a unit or a module for executing the method according to any one of claims 1 to 13.

15. A readable storage medium, characterized in that: The readable storage medium stores program instructions, and when the program instructions are executed on a communication device, the communication device executes the method according to any one of claims 1 to 13.

16. A communication system, characterized in that: include: A first network element and a second network element for executing the method according to any one of claims 1 to 10; Or the communication system includes: a second network element for executing the method described in any one of claims 11 to 13, and a third network element.

Images