Data processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a data processing method and device, electronic equipment and a storage medium. The method comprises the steps that an application service network element sends a data analysis request for a to-be-analyzed target network element to a network data analysis function network element; the network data analysis function network element obtains first feature data of the target network element according to the data analysis request, performs data analysis on the first feature data through a first sub-model of a federated learning model to obtain intermediate analysis information, and sends the intermediate analysis information to an application service network element; and the application service network element obtains second feature data of the target network element, performs data analysis on the intermediate analysis information and the second feature data of the target network element through a second sub-model of the federated learning model to obtain a data analysis result of the target network element, and provides an application service for the target network element according to the data analysis result. According to the technical scheme, the data analysis accuracy and the application service quality can be improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to a data processing method and device, electronic equipment, storage medium, and program product. Background Art

[0002] Network elements that provide application services, such as application function network elements, will perform data analysis on relevant data of the service objects in the process of providing application services to their service objects, so as to provide better application services to the service objects based on the data analysis results.

[0003] In related technologies, the network element providing application services obtains limited data on service objects, which results in low accuracy of data analysis and reduces the quality of application services. Summary of the Invention

[0004] The embodiments of the present application provide a data processing method and device, electronic device, storage medium, and program product, which can improve the accuracy of data analysis and enhance the quality of application services.

[0005] In a first aspect, an embodiment of the present application provides a data processing method, the method comprising:

[0006] Sending a data analysis request for a target network element to be analyzed to a network data analysis function network element, so that the network data analysis function network element obtains first feature data of the target network element according to the data analysis request, and performs data analysis on the first feature data through a first sub-model of a federated learning model to obtain intermediate analysis information;

[0007] Receiving the intermediate analysis information sent by the network data analysis function network element;

[0008] Obtaining second characteristic data of the target network element, and performing data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model to obtain a data analysis result of the target network element;

[0009] Provide application services for the target network element according to the data analysis results.

[0010] In a second aspect, an embodiment of the present application provides a data processing method, the method comprising:

[0011] receiving a data analysis request for a target network element to be analyzed sent by an application service network element, and obtaining first feature data of the target network element according to the data analysis request;

[0012] Performing data analysis on the first feature data using a first sub-model of a federated learning model to obtain intermediate analysis information;

[0013] The intermediate analysis information is sent to the application service network element, so that the application service network element performs data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model, obtains the data analysis result of the target network element, and provides application services for the target network element based on the data analysis result.

[0014] In a third aspect, an embodiment of the present application provides a data processing device, the device comprising:

[0015] a sending module configured to send a data analysis request for a target network element to be analyzed to a network data analysis function network element, so that the network data analysis function network element obtains first feature data of the target network element according to the data analysis request, and performs data analysis on the first feature data through a first sub-model of a federated learning model to obtain intermediate analysis information;

[0016] a receiving module configured to receive the intermediate analysis information sent by the network data analysis function network element;

[0017] an analysis module configured to obtain second characteristic data of the target network element, and perform data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model to obtain a data analysis result of the target network element;

[0018] A service module is configured to provide application services for the target network element according to the data analysis result.

[0019] In a fourth aspect, an embodiment of the present application provides a data processing device, comprising:

[0020] a receiving module configured to receive a data analysis request for a target network element to be analyzed sent by an application service network element, and obtain first feature data of the target network element according to the data analysis request;

[0021] an analysis module configured to perform data analysis on the first feature data using a first sub-model of a federated learning model to obtain intermediate analysis information;

[0022] A sending module is configured to send the intermediate analysis information to the application service network element, so that the application service network element performs data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model, obtains the data analysis result of the target network element, and provides application services for the target network element based on the data analysis result.

[0023] In a fifth aspect, an embodiment of the present application provides an electronic device, including:

[0024] one or more processors;

[0025] The storage device is used to store one or more computer programs, and when the one or more computer programs are executed by the one or more processors, the electronic device implements the data processing method as described above.

[0026] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of an electronic device, the electronic device implements the data processing method as described above.

[0027] In a seventh aspect, an embodiment of the present application provides a computer program product, comprising a computer program, which implements the data processing method as described above when executed by a processor.

[0028] In the technical solution provided in the embodiments of the present application, the application service network element sends a data analysis request for the target network element to be analyzed to the network data analysis function network element; the network data analysis function network element obtains the first characteristic data of the target network element according to the data analysis request, and performs data analysis on the first characteristic data through the first sub-model of the federated learning model to obtain intermediate analysis information, and sends the intermediate analysis information to the application service network element; the application service network element obtains the second characteristic data of the target network element, and performs data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model to obtain the data analysis result of the target network element, so as to provide application services for the target network element based on the data analysis result. Compared with related technologies, it can improve the accuracy of data analysis while ensuring data privacy, thereby improving the quality of application services.

[0029] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a schematic diagram of an implementation environment shown in an exemplary embodiment of the present application;

[0031] Figure 2 is a flow chart of a data processing method shown in an exemplary embodiment of the present application;

[0032] Figure 3 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0033] Figure 4 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0034] Figure 5is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0035] Figure 6 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0036] Figure 7 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0037] Figure 8 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0038] Figure 9 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0039] Figure 10 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0040] Figure 11 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0041] Figure 12 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0042] Figure 13 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0043] Figure 14 is a flow chart of a data processing method shown in another exemplary embodiment of the present application;

[0044] Figure 15 is a schematic diagram of an implementation environment shown in another exemplary embodiment of the present application;

[0045] Figure 16 is a schematic diagram of a data processing device shown in an exemplary embodiment of the present application;

[0046] Figure 17 is a schematic diagram of a data processing device shown in another exemplary embodiment of the present application;

[0047] Figure 18 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0048] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0049] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0050] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0051] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0052] It should also be noted that the term "plurality" used in this application refers to two or more. "And / or" describes the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0053] The following is a detailed introduction to the technical solutions of the embodiments of this application:

[0054] The embodiments of the present application provide a data processing method and device, electronic device, storage medium, and program product, which can improve the accuracy of data analysis while ensuring data privacy, thereby improving the quality of application services.

[0055] See also Figure 1 , Figure 1This is a schematic diagram of an implementation environment involved in this application, which includes an application service network element 110, a network data analysis function network element 120 and a target network element 130.

[0056] Among them, the application service network element 110 refers to a network element that provides application services, including but not limited to at least one of an application function (AF) network element, an over the top server (OTT server) network element, etc. Among them, the application function network element can act as an application server (AS) to implement the control plane function of the third-party application server and interact through the application function network element-network exposure function (NEF) network element-policy control function (PCF) network element method or the application function network element-policy control function network element method; the application function network element can also implement the user plane function of the third-party application server and can interact through the application function network element-Internet Protocol (IP) transmission network-user plane function (UPF) interface; the network exposure function network element is located between the core network and external third-party application function equipment, and is used to manage external network data. External applications need to access the internal data of the core network through the network exposure function network element. The network exposure function network element provides corresponding security guarantees to ensure the security of external applications to the network, and provides functions such as external application quality of service (QoS) customization capability exposure, mobility status event subscription, and application function network element request distribution. The policy control function network element is used to provide control plane policy rules; the user plane function network element is used for packet routing and forwarding, policy implementation, traffic reporting, QoS processing, etc. The network upper layer service network element refers to the network element that provides various application services to users through the Internet.

[0057] The network data analysis function network element 120 is a network element that provides specific network data analysis services to the network.

[0058] The target network element 130 refers to any network element in the network that requires an application service network element to provide application services for it, including but not limited to terminal devices (i.e., user terminals) and servers, wherein terminal devices include but are not limited to mobile phones, tablets, laptops, computers, intelligent voice interaction devices, home appliances, vehicle-mounted terminals, aircraft, remote driving terminals, Extended Reality (XR) devices, etc. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. This section does not limit the specific forms of terminal devices and servers.

[0059] In an exemplary embodiment, the data processing method provided by the embodiment of the present application can be jointly executed by the application service network element 110 and the network data analysis function network element 120. For example, the application service network element 110 can send a data analysis request for the target network element 130 to be analyzed to the network data analysis function network element 120. The network data analysis function network element 120 obtains the first feature data of the target network element 130 according to the data analysis request, and performs data analysis on the first feature data through the first sub-model of the federated learning model to obtain intermediate analysis information, and sends the intermediate analysis information to the application service network element 110; the application service network element 110 obtains the second feature data of the target network element 130, and performs data analysis on the intermediate analysis information and the second feature data of the target network element through the second sub-model in the federated learning model, thereby obtaining the data analysis result of the target network element, and providing application services for the target network element based on the data analysis result. This can improve the accuracy of data analysis while ensuring data privacy, thereby improving the quality of application services.

[0060] Federated learning is a machine learning method used to train models that can learn from data from multiple participants without centralizing the data in a single location. In this embodiment, the federated learning model can be a longitudinal federated learning model. Longitudinal federated learning refers to a model in which multiple participants share the same sample ID but possess different sample characteristics.

[0061] It should be noted that Figure 1 The number of application service network elements 110, network data analysis function network elements 120 and target network elements 130 is only schematic. According to actual needs, there can be any number of application service network elements 110, network data analysis function network elements 120 and target network elements 130.

[0062] The embodiments of this application involve user-related data such as feature data. When the methods of this application are applied to specific products or technologies, they are all subject to user permission or consent, and the extraction, use, and processing of related data comply with local security standards and local laws and regulations. The data processing methods provided in the embodiments of this application can be applied to application service scenarios in networks such as 5G networks.

[0063] See also Figure 2 , Figure 2 This is a flow chart of a data processing method shown in an exemplary embodiment of the present application. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The application service network element 110 in the illustrated implementation environment is executed.

[0064] like Figure 2 As shown, in an exemplary embodiment, the data processing method may include S210-S240, which are described in detail as follows:

[0065] S210, sending a data analysis request for the target network element to be analyzed to the network data analysis function network element, so that the network data analysis function network element obtains the first characteristic data of the target network element according to the data analysis request, and performs data analysis on the first characteristic data through the first sub-model of the federated learning model to obtain intermediate analysis information.

[0066] It should be noted that the target network element refers to any network element in the network that requires an application service network element to provide application services for it, including but not limited to mobile phones, tablets, laptops, computers, intelligent voice interaction devices, home appliances, vehicle-mounted terminals, aircraft, remote driving terminals and other terminal devices, as well as independent physical servers, cloud servers, etc. The characteristic data of the target network element refers to any data related to the target network element, including but not limited to at least one of the network parameters, QoS parameters, application service parameters, etc. of the target network element, wherein the network parameters refer to parameters related to the network quality, including but not limited to Channel Quality Indicator (CQI), Reference Signal Received Power (RSRQ), Received Signal Strength Indicator (RSSI), Reference Signal Received Quality (RSRP), Cell Identity document (cell id), etc.; QoS parameters refer to parameters related to QoS, including but not limited to at least one of end-to-end delay (for example, transmission delay, propagation delay, queuing delay, etc.), delay jitter, packet loss rate, throughput, etc.; application service parameters refer to parameters related to application services, which are used to characterize the quality and status of application services. Different application services have different application service parameters. For example, for video playback services, application service parameters include video decoding rate, video encoding rate, frame rate, etc.; for remote driving services, application service parameters include the position, moving speed, moving direction, surrounding environment, road conditions, etc. of the remote driving vehicle.

[0067] Both the application service network element and the network data analysis function network element can obtain the characteristic data of the target network element. The characteristic data of the target network element obtained by them are not exactly the same. The characteristic data on the network data analysis function network element side is recorded as the first characteristic data, and the characteristic data on the application service network element side is recorded as the second characteristic data. In order to obtain as much characteristic data of the target network element as possible for data analysis, thereby obtaining the data analysis results of the target network element, and better providing application services for the target network element based on the data analysis results, a federated learning model is constructed based on the application service network element and the network data analysis function network element. The federated learning model includes multiple sub-models, wherein the sub-model deployed in the network data analysis function network element is recorded as the first sub-model, and the sub-model deployed in the application service network element is recorded as the second sub-model. The first sub-model is used to perform data analysis on the first characteristic data to obtain intermediate analysis information, and the second sub-model is used to perform data analysis on the second characteristic data and the intermediate analysis information. It should be understood that the "first" and "second" in the first characteristic data and the second characteristic data are only used to characterize that the network elements corresponding to the characteristic data are different, and are not used to limit the order, quantity, etc. of the characteristic data. Similarly, the "first" and "second" in the first sub-model and the second sub-model are only used to characterize that the network elements deployed by the sub-models are different, and are not used to limit the order, quantity, etc. of the sub-models.

[0068] When data analysis is required for a target network element, the application service network element may generate a data analysis request and send the data analysis request to the network data analysis function network element. The data analysis request is used to request the network data analysis function network element to perform data analysis on the target network element, and may include identification information of the target network element, so that the network data analysis function network element determines the network element that needs to be analyzed based on the identification information. The identification information of the network element includes but is not limited to at least one of the network element's IP address, physical address (Media Access Control Address, MAC), and identification number (Identity document, ID).

[0069] After the network data analysis function network element receives the data analysis request, it can determine the target network element according to the data analysis request and obtain the characteristic data of the target network element, thereby obtaining the first characteristic data of the target network element. Then, the first characteristic data of the target network element is input into the first sub-model, so that the first sub-model performs data analysis based on the first characteristic data of the target network element, thereby obtaining the data output by the first sub-model based on the data analysis results, that is, the intermediate analysis information.

[0070] Optionally, the application service network element and the network data analysis function network element can communicate through a trusted third-party network element. The trusted third-party network element includes but is not limited to a control plane network element, such as a network open function network element. Correspondingly, when the application service network element sends a data analysis request to the network data analysis function network element, the data analysis request can be first sent to the third-party network element, and the third-party network element sends the data analysis request to the network data analysis function network element. In subsequent records, intermediate analysis information, model update parameters, identification ciphertext sets, etc. that need to be transmitted between the application service network element and the network data analysis function network element can all be transmitted using this transmission method.

[0071] S220: Receive intermediate analysis information sent by the network data analysis function network element.

[0072] After the network data analysis function network element obtains the intermediate analysis information, it can send the intermediate analysis information to the application service network element.

[0073] Optionally, the network data analysis function network element may send the intermediate analysis information to a third-party network element, which then sends the intermediate analysis information to the application service network element. Correspondingly, the application service network element receives the intermediate analysis information sent by the third-party network element.

[0074] S230, obtaining the second characteristic data of the target network element, and performing data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model to obtain a data analysis result of the target network element.

[0075] When data analysis is required on the target network element, the application service network element can obtain the characteristic data of the target network element to obtain the second characteristic data of the target network element, and then input the second characteristic data of the target network element and the intermediate analysis information into the second sub-model, so that the second sub-model performs data analysis on the intermediate analysis information and the second characteristic data of the target network element to obtain the data analysis results of the target network element.

[0076] The data analysis result is used to provide application services for the target network element. It is the result of data analysis on the characteristic data of the target network element. For example, the application service policy for the target network element can be adjusted according to the data analysis result. Different data analysis purposes result in different data analysis results. In an optional example, the data analysis purpose may be to determine the control policy of the target network element. Correspondingly, the data analysis result is the control policy of the target network element, including but not limited to the application service control policy, network parameter configuration policy, QoS parameter configuration policy, network resource configuration policy, etc. for the target network element. For example, if the target network element is a remote-driven vehicle, the data analysis result may be the driving policy of the remote-driven vehicle at the current moment or in the future, obtained by performing data analysis on the characteristic data of the remote-driven vehicle obtained by the application service network element and the network data analysis function network element respectively, so as to control the remote-driven vehicle according to the driving policy. In another optional example, the purpose of data analysis may be to detect the status of the target network element. Correspondingly, the data analysis result may be the status of the target network element, including but not limited to the status of the target network element at historical moments, current moments, or future moments. For example, if the target network element is a mobile phone, the data analysis result may be the current network resource utilization of the mobile phone obtained by performing data analysis on the characteristic data of the mobile phone obtained by the application service network element and the network data analysis function network element respectively.

[0077] Optionally, the application service network element may first send the data analysis request to the network data analysis function network element, and then obtain the second characteristic data of the target network element, or may first obtain the second characteristic data of the target network element, and then send the data analysis request to the network data analysis function network element, or may obtain the second characteristic data of the target network element and send the data analysis request at the same time. In this embodiment, there is no restriction on the order of execution of obtaining the second characteristic data of the target network element and sending the data analysis request.

[0078] S240: Provide application services to the target network element according to the data analysis result.

[0079] After obtaining the data analysis results, application services can be provided to the target network element based on the data analysis results, thereby improving the quality of application services. For example, the data transmission rate between the application service network element and the target network element can be adjusted according to the data analysis results.

[0080] exist Figure 2In the illustrated embodiment, on the one hand, data analysis is performed based on the characteristic data of the target network element obtained respectively by the application service network element and the network data analysis function network element, which enriches the data volume of the data analysis and improves the accuracy of the data analysis. Application services are provided to the target network element based on the data analysis results, which can improve the quality of application services. On the other hand, combined with federated learning technology, the network data analysis function network element performs data analysis on the characteristic data of the target network element obtained by itself based on the first sub-model in the federated learning model contained in itself, and obtains intermediate analysis information. The application service network element performs data analysis on the characteristic data of the target network element obtained by itself and the intermediate analysis information from the network data analysis function network element based on the second sub-model in the federated learning model contained in itself, and obtains data analysis results. Without exposing the characteristic data of the target network element obtained by the network data analysis function network element, the application service network element can use the characteristic data of the target network element obtained by the network data analysis function network element to perform data analysis, thereby ensuring data privacy and improving data analysis security.

[0081] In an exemplary embodiment, see Figure 3 , Figure 3 is Figure 2 A data processing method is proposed based on the above. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The application service network element 110 in the illustrated implementation environment is executed.

[0082] like Figure 3 As shown, the method may further include S310-S340, which are described in detail as follows:

[0083] S310, receiving a first model update parameter sent by the network data analysis function network element; wherein the first model update parameter is obtained by the network data analysis function network element by training the first sub-model according to the first feature data of the training sample.

[0084] During the training process of the federated learning model, or after the training of the federated learning model is completed, the federated learning model can be trained to optimize the model parameters of the federated learning model. During each training process, the network data analysis function network element can obtain the feature data of the training sample, obtain the first feature data of the training sample, and train the first sub-model based on the first feature data of the training sample to obtain the model update parameter, and record the model update parameter as the first model update parameter. The training sample can refer to the network element used as a sample for model training, such as a mobile phone, tablet, laptop, computer, intelligent voice interaction device, home appliance, vehicle terminal, aircraft, remote driving terminal and other terminal devices, as well as independent physical servers, cloud servers, etc. In order to improve the accuracy of subsequent data analysis of the target network element based on the federated learning model, the type of the training sample can match the type of the target network element. The model update parameters can include parameters such as the gradient and weight of the model.

[0085] The application service network element may receive the first model update parameter sent by the network data analysis function network element.

[0086] S320, obtaining the second feature data and the data analysis result label of the training sample, and training the second sub-model according to the second feature data and the data analysis result label of the training sample to obtain the second model update parameter.

[0087] The data analysis result label is used to represent the expected data analysis result after data analysis based on the characteristic data of the training sample. It can be regarded as the real data analysis result. The label can be manually marked for the training sample.

[0088] The application service network element can also obtain the characteristic data of the training sample, obtain the second characteristic data of the training sample, and obtain the data analysis result label corresponding to the training sample, so as to train the second sub-model based on the second characteristic data of the training sample and the data analysis result label, obtain the model update parameters, and record the model update parameters as the second model update parameters.

[0089] S330: Update the second sub-model according to the first model update parameter and the second model update parameter.

[0090] After obtaining the first model update parameter and the second model update parameter, the application service network element may update the second sub-model by integrating the first model update parameter and the second model update parameter.

[0091] S340: Send the second model update parameter to the network data analysis function network element, so that the network data analysis function network element updates the first sub-model according to the first model update parameter and the second model update parameter.

[0092] After obtaining the second model update parameters, the application service network element can send the second model update parameters to the network data analysis function network element, so that the network data analysis function network element can also integrate the first model update parameters and the second model update parameters to update the first sub-model, thereby realizing the update of the vertical federated learning model.

[0093] It should be noted that Figure 3 The specific implementation details of S210-S240 shown can be referred to Figure 2 S210-S240 shown are not described here in detail.

[0094] exist Figure 3 In the embodiment shown, during the model update process, only the model update parameters obtained by training based on the feature data of the training samples obtained by each party will be transmitted between the network data analysis function network element and the application service network element, and the feature data of the training samples will not be transmitted, thereby protecting data privacy and improving data security.

[0095] In an exemplary embodiment, see Figure 4 , Figure 4 is Figure 3 A data processing method is proposed based on the above. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The application service network element 110 in the illustrated implementation environment is executed.

[0096] like Figure 4 As shown, S310 includes S410-S420, which are described in detail as follows:

[0097] S410, sending an information subscription request to the network data analysis function network element, so that the network data analysis function network element obtains the first feature data of the training sample according to the information subscription request, and trains the first sub-model according to the first feature data to obtain the first model update parameter.

[0098] To obtain data related to the federated learning model, such as model update parameters, from the network data analysis function element, the application service element can send an information subscription request to the network data analysis function element. The information subscription request is used to subscribe to data related to the federated learning model. After receiving the information subscription request, the network data analysis function element can obtain the first feature data of the training sample based on the information subscription request, thereby training the first sub-model and obtaining the first model update parameters.

[0099] Optionally, after receiving the information subscription request, the network data analysis function network element may also send a subscription success notification message to the application service network element to notify the application service that the subscription is successful.

[0100] S420: Obtain a first model update parameter from the network data analysis function network element.

[0101] After subscription, the network data analysis function network element obtains the first model update parameter and sends the first model update parameter to the application service network element, and the application service network element receives the first model update parameter from the network data analysis function network element.

[0102] It should be noted that Figure 4 The specific implementation details of S210-S240 shown can be referred to Figure 2 S210-S240 shown, Figure 4 The specific implementation details of S320-S340 shown can be referred to Figure 3 S320-S340 shown are not described here in detail.

[0103] exist Figure 4 In the illustrated embodiment, the network data analysis function network element acquires characteristic data of training samples and performs subsequent training based on information subscription requests from the application service network element, which can save resources and improve data security.

[0104] In an exemplary embodiment, see Figure 5 , Figure 5 is Figure 4 A data processing method is proposed based on the above. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The application service network element 110 in the illustrated implementation environment is executed.

[0105] like Figure 5 As shown, S410 includes S510-S520, which are described in detail as follows:

[0106] S510 , sending an information subscription request to a control plane network element, so that the control plane network element sends the information subscription request to a network data analysis function network element; wherein the control plane network element includes a network open function network element.

[0107] In this embodiment, the application service network element and the network data analysis function network element communicate through a third-party network element, which is a control plane network element; wherein the control plane network element includes at least one of a network open function network element and the like.

[0108] During the information subscription process, the application service network element can send an information subscription request to the control plane network element, which in turn sends the information subscription request to the network data analysis function network element. Optionally, after receiving the information subscription request, the control plane network element can also verify whether the application service network element has permission to access the network data analysis function network element. If so, the information subscription request is sent to the network data analysis function network element; if not, the information subscription request is rejected.

[0109] S520: Receive a subscription success notification message sent by the network data analysis function network element through the control plane network element.

[0110] After the information subscription request reaches the network data analysis function network element, the network data analysis function network element can send a subscription success notification message to the control plane network element, and the control plane network element sends the subscription success notification message to the application service network element; after the application service network element receives the subscription success notification message, it indicates that the subscription is successful. Subsequently, after the control plane network element receives data related to the federated learning model from the network data analysis function network element, it can send the data to the application service network element.

[0111] Optionally, the application service network element can also send a cancellation request to the control plane network element, and the control plane network element sends the cancellation request to the network data analysis function network element. The network data analysis function network element sends a cancellation success notification to the control plane network element, so that the control plane network element sends the cancellation success notification to the application service network element, indicating that the subscription cancellation is successful. Subsequently, after the control plane network element receives data related to the federated learning model from the network data analysis function network element, it will not send the data to the application service network element.

[0112] It should be noted that Figure 5 The specific implementation details of S210-S240 shown can be referred to Figure 2 S210-S240 shown, Figure 5 The specific implementation details of S320-S340 shown can be referred to Figure 3 S320-S340 shown, Figure 5 The specific implementation details of S420 shown can be referred to Figure 4 The S420 shown is not described here in detail.

[0113] exist Figure 5 In the illustrated embodiment, information subscription requests are transmitted between the network data analysis function network element and the application service network element based on the control plane network element, which can improve the security and stability of data transmission.

[0114] In an exemplary embodiment, see Figure 6 , Figure 6 is Figure 4 A data processing method is proposed based on the above. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The application service network element 110 in the illustrated implementation environment is executed.

[0115] like Figure 6 As shown, S410 includes S610-S620, which are described in detail as follows:

[0116] S610, obtain the performance parameters corresponding to multiple network data analysis function network elements, and select the network data analysis function network elements participating in the federated learning model from the multiple network data analysis function network elements based on the performance parameters corresponding to the multiple network data analysis function network elements.

[0117] In order to improve the training speed of the federated learning model and the subsequent data analysis speed, the performance parameters corresponding to the multiple network data analysis function network elements contained in the network can be obtained first, where the performance parameters of the network data analysis function network elements include but are not limited to at least one of the idle resources of the network data analysis function network elements, the computing speed, the number of federated learning models being trained, etc.

[0118] Then, based on the performance parameters corresponding to the multiple network data analysis function network elements, the network data analysis function network elements that participate in the federated learning model are screened from the multiple network data analysis function network elements, that is, the network data analysis function network elements that serve as participants in the federated learning model are screened. The performance of the network data analysis function network element is positively correlated with the probability of the network data analysis function network element serving as a participant in the federated learning model. In other words, the better the performance of the network data analysis function network element, the higher the probability that the network data analysis function network element serves as a participant in the federated learning model.

[0119] S620: Send an information subscription request to the filtered network data analysis function network elements.

[0120] An information subscription request is sent to the screened network data analysis function network elements, so that the network data analysis function network elements that receive the information subscription request serve as participants of the federated learning model and participate in the training of the federated learning model and subsequent data analysis.

[0121] It should be noted that Figure 6 The specific implementation details of S210-S240 shown can be referred to Figure 2 S210-S240 shown, Figure 6 The specific implementation details of S320-S340 shown can be referred to Figure 3 S320-S340 shown, Figure 6 The specific implementation details of S420 shown can be referred to Figure 4 The S420 shown is not described here in detail.

[0122] exist Figure 6 In the embodiment shown, the network data analysis function network elements participating in the federated learning model are screened out based on the performance parameters of the network data analysis function network elements, which can improve the training speed of the federated learning model and the subsequent data analysis speed.

[0123] In an exemplary embodiment, see Figure 7 , Figure 7 is Figure 6 A data processing method is proposed based on the above. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The application service network element 110 in the illustrated implementation environment is executed.

[0124] like Figure 7 As shown, S610 includes S710-S740, which are described in detail as follows:

[0125] S710: Obtain performance parameters corresponding to a plurality of network data analysis function network elements.

[0126] Optionally, the application service network element may send a performance parameter acquisition request to each network data analysis function network element, and receive response information sent by each network data analysis function network element, wherein the response information includes the performance parameters of the network data analysis function network element.

[0127] S720 , obtaining the number of historical information subscription requests received by each network data analysis function network element and the amount of idle resources of each network data analysis function network element from the performance parameters of each network data analysis function network element.

[0128] The performance parameters of the network data analysis function network element may include the amount of idle resources of the network data analysis function network element and the number of historical information subscription requests received by the network data analysis function network element; wherein, the historical information subscription request refers to an information subscription request whose reception time is earlier than the current time.

[0129] Optionally, for the purpose of increasing the subscription success rate, the number of historical information subscription requests received by the network data analysis function network element may be the number of historical information subscription requests received by the network data analysis function network element and successfully subscribed to.

[0130] S730, calculate the quality score of each network data analysis function network element based on the number of historical information subscription requests received by each network data analysis function network element and the amount of idle resources of each network data analysis function network element; wherein the quality score is positively correlated with the amount of idle resources and positively correlated with the number of historical information subscription requests.

[0131] For each network data analysis function network element, its quality score can be calculated based on the number of historical information subscription requests it receives and the amount of idle resources. Among them, since the more idle resources a network data analysis function network element has, the more resources the network data analysis function network element can use for the federated learning model. Therefore, the quality score is set to be positively correlated with the amount of idle resources, that is, the more idle resources, the higher the quality score; the more historical information subscription requests a network data analysis function network element receives, the more application service network elements select the network data analysis function network element as a participant in its federated learning model, and the more reliable the network data analysis function network element is. Therefore, the number of historical information subscription requests received is set to be positively correlated with the quality score, that is, the more historical information subscription requests received, the higher the quality score.

[0132] S740 , selecting a set number of network data analysis function network elements from the plurality of network data analysis function network elements in descending order of the corresponding quality scores.

[0133] After calculating the quality score of each network data analysis function network element, the application service network element can select a set number of network data analysis function network elements from multiple network data analysis function network elements in order of the corresponding quality scores from high to low, and use the selected set number of network data analysis function network elements as participants in the federated learning model, and send information subscription requests to the set number of network data analysis function network elements respectively.

[0134] The specific value of the set quantity can be flexibly set according to actual needs, for example, it can be set to 1, 2, 3, etc.

[0135] It should be noted that Figure 7 The specific implementation details of S210-S240 shown can be referred to Figure 2 S210-S240 shown, Figure 7 The specific implementation details of S320-S340 shown can be referred to Figure 3 S320-S340 shown, Figure 7 The specific implementation details of S420 shown can be referred to Figure 4 The S420 shown is not described here any more. Figure 7 The specific implementation details of S620 shown can be referred to Figure 6 The S620 shown is not described here in detail.

[0136] exist Figure 7In the embodiment shown, network data analysis function network elements participating in the federated learning model are screened out based on the number of historical information subscription requests received by the network data analysis function network element and the amount of idle resources. This can improve the training speed of the federated learning model and the subsequent data analysis speed, improve the success rate of information subscription, and thereby improve the success rate of model training.

[0137] In an exemplary embodiment, see Figure 8 , Figure 8 is Figure 3 A data processing method is proposed based on the above. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The application service network element 110 in the illustrated implementation environment is executed.

[0138] like Figure 8 As shown, the method further includes S810-S830, which are described in detail as follows:

[0139] S810, receiving a first identification ciphertext set sent by a network data analysis function network element, wherein the first identification ciphertext set includes the identification information ciphertext of each sample network element in the first sample set, and the identification information ciphertext of each sample network element is obtained by encrypting the identification information of each sample network element by the network data analysis function network element.

[0140] The network data analysis function network element contains feature data corresponding to multiple sample network elements, which are combined into a first sample set. The application service network element contains feature data corresponding to multiple sample network elements, which are combined into a second sample set. The sample network element refers to the network element used as a sample, and the identification information of the network element includes, but is not limited to, at least one of the network element's IP address, MAC address, and ID.

[0141] In order to find common sample network elements (i.e., network elements included in both the first sample set and the second sample set) from the first sample set and the second sample set while ensuring data security for sample alignment, the network data analysis function network element may encrypt the identification information of each sample network element in the first sample set to obtain the identification information ciphertext of each sample network element, and construct a first identification ciphertext set based on the identification information ciphertexts corresponding to the multiple sample network elements in the first sample set, and send the first identification ciphertext set to the application service network element. Optionally, the network data analysis function network element may obtain the first identification ciphertext set from the network data analysis function network element when the application service network element receives the information from the application service network element.

[0142] The encryption algorithm for the identification information of the sample network element includes, but is not limited to, a homomorphic encryption algorithm, wherein processing the homomorphically encrypted data yields an output, and decrypting this output yields the same output as the output obtained by using the same method on the unencrypted original data. Therefore, using a homomorphic encryption algorithm to encrypt the identification information enables the application service network element to find the shared sample network element based on the identification information in the ciphertext state sent by the network data analysis function network element, thereby preventing the application service network element from obtaining the identification information of the sample network element contained in the network data analysis function network element, thereby improving data security. The homomorphic encryption algorithm includes, but is not limited to, the RSA algorithm, which is an asymmetric encryption algorithm.

[0143] S820: Encrypt the identification information of each sample network element in the second sample set to obtain a ciphertext of the identification information of each sample network element in the second sample set to construct a second identification ciphertext set; wherein the encryption method of the identification information ciphertext included in the first identification ciphertext set matches the encryption method of the identification information ciphertext included in the second identification ciphertext set.

[0144] The application service network element may encrypt the identification information of each sample network element included in the second sample set, thereby obtaining the identification information ciphertext of each sample network element in the second sample set, and thereby construct a second identification ciphertext set based on the identification information ciphertexts corresponding to the multiple sample network elements in the second sample set. The encryption method of the identification information ciphertexts included in the first identification ciphertext set matches (e.g., is the same as) the encryption method of the identification information ciphertexts included in the second identification ciphertext set, such that the identification information ciphertexts of the shared sample network elements are the same in the first identification ciphertext set and the second identification ciphertext set.

[0145] S830: Search for shared identification information ciphertext from the first identification ciphertext set and the second identification ciphertext set, and use the sample network element corresponding to the shared identification information ciphertext as a training sample.

[0146] After obtaining the first identification ciphertext set and the second identification ciphertext set, the application service network element can search for the identification information ciphertext shared by the first identification ciphertext set and the second identification ciphertext set to obtain the shared identification information ciphertext, that is, obtain the intersection of the first identification ciphertext set and the second identification ciphertext set, use the identification information ciphertext in the intersection as the shared identification information ciphertext, and use the sample network element corresponding to the shared identification information ciphertext as the shared sample network element, and use the shared sample network element as the training sample. Optionally, the application service network element can also send the shared identification information ciphertext to the network data analysis function network element, so that the network data analysis function network element can determine the training sample based on the shared identification information ciphertext to achieve sample alignment.

[0147] In an optional example, during the sample alignment process, the network data analysis function network element can generate an asymmetric key pair, and use the private key therein to encrypt the identification information of each sample network element in the first sample set to obtain the identification information ciphertext of each sample network element in the first sample set to construct a first identification ciphertext set; the first identification ciphertext set and the public key in the asymmetric key pair are sent to the application service network element, the application service network element generates disturbance information (for example, a random number) for each sample network element in the second sample set, and uses the public key to encrypt the disturbance information of each sample network element to obtain disturbance information ciphertext, and then generates the disturbance identification information ciphertext of each sample network element based on the disturbance information ciphertext of each sample network element and the identification information of each sample network element to construct a first ciphertext set, and sends the first ciphertext set to the network data analysis function network element. The network data analysis function network element decrypts the disturbance identification information ciphertext of each sample network element in the second sample set contained in the first ciphertext set using a private key, obtains the intermediate identification information ciphertext of each sample network element in the second sample set, to construct a second ciphertext set, and sends the second ciphertext set to the application service network element; after receiving the second ciphertext set, the application service network element removes the disturbance on the intermediate identification information ciphertext of each sample network element in the first sample set according to the disturbance information of each sample network element in the first sample set, thereby obtaining the identification information ciphertext obtained by encrypting the identification information of each sample network element in the second sample set based on the private key, to construct a second identification ciphertext set, searches out the common identification information ciphertext from the first identification ciphertext set and the second identification ciphertext set, and uses the sample network element corresponding to the common identification information ciphertext as the common sample network element; the application service network element can also send the common identification information ciphertext to the network data analysis function network element, so that the network data analysis function network element searches out the common sample network element from the first sample set according to the common identification information ciphertext. In this process, the network data analysis function network element is the party that owns the private key, and the application service network element is the party that uses the public key. In other embodiments, during the sample alignment process, the network data analysis function network element can also perform corresponding operations as the party that owns the public key, and the application service network element can also perform corresponding operations as the party that owns the private key.

[0148] It should be noted that Figure 8 In the embodiment shown, the application service network element searches for the shared identification information ciphertext. In other embodiments, the network data analysis function network element may also search for the shared identification information ciphertext. Correspondingly, the network data analysis function network element may receive the second identification ciphertext set sent by the application service network element, and search for the shared identification information ciphertext from the first identification ciphertext set and the second identification ciphertext set. Figure 8 The specific implementation details of S210-S240 shown can be referred to Figure 2 S210-S240 shown, Figure 8The specific implementation details of S310-S340 shown can be referred to Figure 3 S310-S340 shown are not described here in detail.

[0149] exist Figure 8 In the illustrated embodiment, sample alignment is performed based on the ciphertext of the identification information of the samples, which can improve data security.

[0150] See also Figure 9 , Figure 9 This is a flow chart of a data processing method shown in an exemplary embodiment of the present application. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The network data analysis function in the illustrated implementation environment is executed by the network element 120 .

[0151] like Figure 9 As shown, in an exemplary embodiment, the data processing method may include S910-S930, which are described in detail as follows:

[0152] S910: Receive a data analysis request for a target network element to be analyzed, sent by an application service network element, and obtain first feature data of the target network element according to the data analysis request.

[0153] The network data analysis function network element can receive a data analysis request sent by the application service network element, thereby obtaining characteristic data of the target network element based on the data analysis request, thereby obtaining first characteristic data of the target network element. For an introduction to the network data analysis function network element, the application service network element, and the target network element, please refer to the description of the aforementioned embodiment, which will not be repeated here.

[0154] Optionally, the application service network element may obtain characteristic data of the target network element from network elements such as a radio access network (RAN) network element and an operation, administration and maintenance (OAM) network element.

[0155] S920: Perform data analysis on the first feature data using the first sub-model of the federated learning model to obtain intermediate analysis information.

[0156] After acquiring the first characteristic data of the target network element, the network data analysis function network element inputs the first characteristic data into the first sub-model to obtain the intermediate analysis information of the target network element output by the first sub-model.

[0157] Optionally, an Analytics logical function (AnLF) may be deployed in the network data analysis function NE to provide external network data analysis function NE service interfaces, such as the Nwd af_AnalyticsSubscription and Nwdaf_AnalyticsInfo interfaces, to generate analysis results based on requests from consumer NEs. The network data analysis function NE may call the data analysis logical function so that the data analysis logical function performs data analysis on the first feature data through the first sub-model of the federated learning model to obtain intermediate analysis information.

[0158] S930, sending the intermediate analysis information to the application service network element, so that the application service network element performs data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model, obtains the data analysis result of the target network element, and provides application services for the target network element based on the data analysis result.

[0159] The network data analysis function network element sends the intermediate analysis information of the target network element to the application service network element; the application service network element performs data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model to obtain the data analysis results of the target network element, thereby providing application services for the target network element based on the data analysis results. The specific process can be found in the records of the aforementioned embodiments and will not be repeated here.

[0160] Optionally, the network data analysis function network element and the application service network element can communicate through a trusted third-party network element. Under this condition, the network data analysis function network element can send intermediate analysis information to the third-party network element, and the third-party network element will then send the intermediate analysis information to the application service network element.

[0161] exist Figure 9In the illustrated embodiment, on the one hand, data analysis is performed based on the characteristic data of the target network element obtained respectively by the application service network element and the network data analysis function network element, which enriches the data volume of the data analysis and improves the accuracy of the data analysis. Application services are provided to the target network element based on the data analysis results, which can improve the quality of application services. On the other hand, combined with federated learning technology, the network data analysis function network element performs data analysis on the characteristic data of the target network element obtained by itself based on the first sub-model in the federated learning model contained in itself, and obtains intermediate analysis information. The application service network element performs data analysis on the characteristic data of the target network element obtained by itself and the intermediate analysis information from the network data analysis function network element based on the second sub-model in the federated learning model contained in itself, and obtains data analysis results. Without exposing the characteristic data of the target network element obtained by the network data analysis function network element, the application service network element can use the characteristic data of the target network element obtained by the network data analysis function network element to perform data analysis, thereby ensuring data privacy and improving data analysis security.

[0162] In an exemplary embodiment, see Figure 10 , Figure 10 is Figure 9 A data processing method is proposed based on the above. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The network data analysis function in the illustrated implementation environment is executed by the network element 120 .

[0163] like Figure 10 As shown, the method further includes S1010-S1030, which are described in detail as follows:

[0164] S1010: Train the first sub-model according to the first feature data of the training sample to obtain a first model update parameter.

[0165] During the training process of the federated learning model, or after the training of the federated learning model is completed, the federated learning model can be trained to optimize the model parameters of the federated learning model. During each training process, the network data analysis function element can obtain feature data of the training samples to obtain first feature data of the training samples, train the first sub-model based on the first feature data of the training samples, obtain model update parameters, and record the model update parameters as first model update parameters. For a detailed description of the training samples and model update parameters, please refer to the description of the aforementioned embodiment and will not be repeated here.

[0166] Optionally, the application service network element may obtain feature data of training samples from network elements such as wireless access network elements, operation management and maintenance network elements, etc.

[0167] S1020, sending the first model update parameter to the application service network element, so that the application service network element updates the second sub-model according to the first model update parameter and the second model update parameter; wherein, the second model update parameter is obtained by the application service network element through training the second sub-model based on the second feature data of the training sample and the data analysis result label.

[0168] The network data analysis function network element sends the first model update parameter to the application service network element, and the application service network element updates the second sub-model according to the first model update parameter and the second model update parameter.

[0169] S1030: Receive the second model update parameter sent by the application service network element, and update the first sub-model according to the first model update parameter and the second model update parameter.

[0170] The network data analysis function network element may receive the second model update parameter from the application service network element, thereby updating the first sub-model according to the first model update parameter and the second model update parameter.

[0171] Optionally, a model training logic function (MTLF) is deployed in the network data analysis function element for model training. The network data analysis function element can call the model training logic function to train and update the first sub-model. The model training logic function can provide the trained first sub-model to the data analysis logic function, so that the data analysis logic function can perform data analysis based on the first sub-model.

[0172] It should be noted that Figure 10 The specific implementation details of S910-S930 shown can be referred to Figure 9 S910-S930 shown are not described here in detail.

[0173] exist Figure 10 In the embodiment shown, during the model update process, only the model update parameters obtained by training based on the feature data of the training samples obtained by each party will be transmitted between the network data analysis function network element and the application service network element, and the feature data of the training samples will not be transmitted, thereby protecting data privacy and improving data security.

[0174] In an exemplary embodiment, see Figure 11 , Figure 11 is Figure 9 A data processing method is proposed based on the above. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1The network data analysis function in the illustrated implementation environment is executed by the network element 120 .

[0175] like Figure 11 As shown, S910 includes S1110-S1130, which are described in detail as follows:

[0176] S1110: Receive a data analysis request for a target network element to be analyzed, sent by an application service network element.

[0177] The network data analysis function network element can receive data analysis requests sent by the application service network element.

[0178] S1120 , obtain network parameters of the target network element from the operation management and maintenance network element; wherein the network parameters include a channel quality indicator.

[0179] After receiving a data analysis request, characteristic data of the target network element can be obtained to analyze data for the target network element. The operation, management, and maintenance network element includes network parameters such as channel quality indicators. Therefore, the network parameters of the target network element can be obtained from the operation, management, and maintenance network element. For example, parameters such as channel quality indicators can be obtained. Channel quality indicators can help dynamically adjust modem parameters between base stations and terminal devices to maximize communication quality and data transmission rates. By analyzing and providing these parameters to application function network elements, better services can be provided to terminal devices, allowing services to better adapt to complex network changes.

[0180] S1130: Add the network parameters of the target network element to the first characteristic data of the target network element.

[0181] After the network parameters of the target network element are obtained, the network parameters may be added to the first characteristic data of the target network element. That is, the first characteristic data of the target network element includes the network parameters of the target network element obtained from the operation, management and maintenance network element.

[0182] It should be noted that Figure 11 The specific implementation details of S920-S930 shown can be referred to Figure 9 S920-S930 shown are not described here in detail.

[0183] exist Figure 11 In the illustrated embodiment, network parameters of a target network element are obtained from an operation management and maintenance network element for use in data analysis, which can enrich the amount of data analyzed and improve the accuracy of data analysis.

[0184] In an exemplary embodiment, see Figure 12 , Figure 12 is Figure 9 A data processing method is proposed based on the above. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The network data analysis function in the illustrated implementation environment is executed by the network element 120 .

[0185] like Figure 12 As shown, S910 includes S1210-S1230, which are described in detail as follows:

[0186] S1210: Receive a data analysis request for a target network element to be analyzed, sent by an application service network element.

[0187] The network data analysis function network element can receive data analysis requests sent by the application service network element.

[0188] S1220, according to the data analysis request, perform permission verification on the application service network element and obtain a verification result; wherein the application service network element includes the application function network element and the network upper layer service network element.

[0189] After receiving the data analysis request for the target network element, the network data analysis function network element can verify whether the application service network element has the authority to obtain the intermediate analysis information of the target network element, thereby obtaining a verification result.

[0190] The specific verification method can be flexibly set according to actual needs. For example, in an optional example, it can be determined whether the application service network element is providing application services for the target network element. If so, it is determined that the application service network element has the authority to obtain the intermediate analysis information of the target network element. If not, it is determined that the application service network element does not have the authority to obtain the intermediate analysis information of the target network element. The specific method for determining whether the application service network element is providing application services for the target network element can be flexibly set according to actual needs. In an optional example, if a session is established between the target network element and the application service network element, it is largely indicated that the application service network element is providing application services for the target network element. Therefore, whether the application service network element is providing application services for the target network element can be determined based on whether a session is established between the target network element and the application service network element. In another optional example, it can be verified whether the application service network element is abnormal. If the application service network element is in an abnormal state, such as being attacked, it is determined that the application service network element does not have the authority to obtain the intermediate analysis information of the target network element. If the application service network element is in a normal state, it is determined that the application service network element has the authority to obtain the intermediate analysis information of the target network element. In another optional example, it is also possible to verify whether the security level of the application service network element is higher than the set level threshold. If so, it has the authority; if not, it does not have the authority. The security level can be determined based on whether the application service network element has security management software and hardware equipment such as firewalls, whether it has a trusted execution environment, etc.

[0191] S1230: If the verification result indicates that the application service network element has the authority to obtain the intermediate analysis information of the target network element, first feature data of the target network element is obtained.

[0192] If the verification result indicates that the application service network element has the authority to obtain the intermediate analysis information of the target network element, the first feature data of the target network element is obtained for subsequent data analysis to obtain the intermediate analysis information.

[0193] Optionally, if the verification result indicates that the application service network element does not have the authority to obtain the intermediate analysis information of the target network element, the data analysis request is rejected.

[0194] It should be noted that Figure 12 The specific implementation details of S920-S930 shown can be referred to Figure 9 S920-S930 shown are not described here in detail.

[0195] exist Figure 12 In the embodiment shown, the application service network element is subject to permission verification, and only after the verification result shows that the application service network element has the permission to obtain the intermediate analysis information of the target network element, the first characteristic data of the target network element is obtained for data analysis, which can ensure data security.

[0196] In an exemplary embodiment, see Figure 13 , Figure 13 is Figure 12 A data processing method is proposed based on the above. This method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The network data analysis function in the illustrated implementation environment is executed by the network element 130 .

[0197] like Figure 13 As shown, S1220 includes S1310-S1320, which are described in detail as follows:

[0198] S1310 , selecting a target authority verification method from a plurality of authority verification methods according to the attribute data of the application service network element and the type of the target network element; wherein different authority verification methods have different verification completeness.

[0199] In this embodiment, the application service network element can be verified from multiple dimensions, such as whether a session is established between the application service network element and the target network element, whether the status of the application service network element is abnormal, and the security level of the application service network element. Application service network elements have different attributes, different target network elements have different types, and different data security requirements. Therefore, multiple permission verification methods are pre-set, wherein different permission verification methods correspond to different verification completeness, that is, different permission verification methods include different numbers of verification dimensions. For example, permission verification method 1 includes one permission verification dimension, which is based on whether a session is established between the application service network element and the target network element; permission verification method 2 includes two permission verification dimensions, which are based on whether a session is established between the application service network element and the target network element, and based on whether the status of the application service network element is abnormal; permission verification method 3 includes three permission verification dimensions, which are based on whether a session is established between the application service network element and the target network element, based on whether the status of the application service network element is abnormal, and based on the security level of the application service network element.

[0200] Based on the attribute data of the application service network element and the type of the target network element, a target permission verification method can be selected from a variety of permission verification methods. Among them, the specific selection method can be flexibly set according to actual needs. For example, if the type of the target network element indicates that it has low security requirements, then a permission verification method with lower verification integrity can be selected as the target permission verification method. If the attribute data of the application service network element indicates that the application network element is trustworthy, or if the application service network element has obtained intermediate analysis information of the target network element in the recent period, then a permission verification method with lower verification integrity can be selected as the target permission verification method.

[0201] S1320: Perform permission verification on the application service network element according to the target permission verification method to obtain a verification result.

[0202] After selecting the target authority verification method, the application service network element is verified based on the target authority verification method.

[0203] Optionally, if the target permission verification method includes at least two verification dimensions, the final verification result can be determined to be permission granted when the verification results corresponding to the at least two verification dimensions are permission granted.

[0204] It should be noted that Figure 13 The specific implementation details of S920-S930 shown can be referred to Figure 9 S920-S930 shown, Figure 13The specific implementation details of S1210 and S1230 shown can be referred to Figure 12 S1210 and S1230 shown are not described again here.

[0205] exist Figure 13 In the illustrated embodiment, the attribute data of the application service network element is different, the type of the target network element is different, and the verification completeness of the application service network element is different, thereby saving processing resources while ensuring data security.

[0206] In an exemplary embodiment, see Figure 14 , the implementation environment includes application service network elements, network open function network elements, network data analysis function network elements, operation management and maintenance network elements as an example for explanation, among which application service network elements are application function network elements or network upper layer service network elements. Figure 14 As shown, the data processing method includes S1401-S1411, which are described in detail as follows:

[0207] S1401: The application service network element sends an information subscription request to the network open function network element.

[0208] The application service network element can send an information subscription request to the network open function network element to subscribe to data related to the federated learning model from the network data analysis function network element, for example, including but not limited to data in the sample alignment process (for example, identification ciphertext, public key, etc.), data in the federated learning model training process (for example, model update parameters), data in the federated learning model data analysis process (for example, intermediate analysis information), etc.

[0209] Optionally, the application service NE can call the Nnef_AnalyticsExposure_Subscribe service of the network exposure function NE to initiate a subscription, and call the Nnef_AnalyticsExposure_Unsubscribe service to cancel a subscription.

[0210] S1402: The network open function network element sends an information subscription request to the network data analysis function network element.

[0211] After the network open function network element sends the information subscription request to the network data analysis function network element, it can send the information subscription request to the network data analysis function network element to subscribe to data related to the federated learning model from the network data analysis function network element.

[0212] Optionally, after receiving the information subscription request, the network open function NE can verify whether the application service NE has permission to access the network data analysis function NE. If so, it can authorize the application service NE, agree to the subscription, and send the information subscription request to the network data analysis function NE, thereby initiating a subscription with the network data analysis function NE. Optionally, the network open function NE can call the Nnwdaf_AnalyticsSubscription_Subscribe service to initiate a subscription, or call the Nwdaf_AnalyticsSubscription_Unsubscribe service to cancel a subscription.

[0213] In the network data analysis function element, analysis IDs are used to identify corresponding analysis data. Therefore, after agreeing to the subscription, the network openness function element can also map the identification information of the application service element and the analysis ID corresponding to the data related to the federated learning model, and open this mapping relationship. Subsequently, after receiving data related to the federated learning model, the data can be sent to the application service element based on the corresponding analysis ID and this mapping relationship.

[0214] S1403: The network openness function network element receives a subscription success notification message from the network data analysis function network element.

[0215] After receiving the information subscription request, the network data analysis function network element may send a subscription success notification message to the network open function network element to indicate that it agrees to the subscription.

[0216] If the subscription fails, the network data analysis function NE may send a subscription success notification message to the network open function NE. Optionally, the network data analysis function NE may call the Nnwdaf_AnalyticsSubscription_Notify service to send a subscription success notification message, a subscription failure notification message, etc. to the network open function NE.

[0217] S1404: The network open function network element sends a subscription success notification message to the application service network element.

[0218] After receiving the subscription success notification message, the network open function network element sends the message to the application service network element to indicate successful subscription.

[0219] If the network open function NE receives a subscription failure notification message, it sends a subscription failure notification message to the application service NE. Optionally, the network open function NE can call the Nnef_AnalyticsSubscription_Notify service to send a subscription success notification message or a subscription failure notification message to the application service NE.

[0220] S1405: The network open function network element sends an information acquisition request to the network data analysis function network element.

[0221] Information retrieval requests are used to request data related to federated learning models.

[0222] Optionally, the network open function NE may call the Nnwdaf_AnalyticsInfo_Reqest service operation to initiate an information acquisition request.

[0223] S1406 , the network data analysis function network element obtains characteristic data of the sample network element from the operation management and maintenance network element.

[0224] After receiving the information acquisition request, the network data analysis function network element collects characteristic data (for example, network parameters) of the sample network elements from the operation management and maintenance network elements for subsequent training of the federated learning model.

[0225] S1407: The application service network element and the network data analysis function network element perform sample alignment to obtain training samples.

[0226] The specific method of sample alignment can be found in the description of the aforementioned embodiment and will not be repeated here.

[0227] S1408, the application service network element and the network data analysis function network element train the federated learning model to obtain a trained federated learning model.

[0228] The application service network element trains the second sub-model in the federated learning model based on the characteristic data of the training samples obtained by itself (for example, application service parameters) and the data analysis result labels. The network data analysis function network element trains the first sub-model in the federated learning model based on the characteristic data of the training samples obtained by itself. During the training process, the application service network element and the network data analysis function network element interact with the model to update the parameters, thereby obtaining a trained federated learning model.

[0229] S1409: The application service network element sends a data analysis request for the target network element to the network data analysis function network element.

[0230] The data analysis request is used to request the network data analysis function network element to obtain characteristic data (for example, network parameters) of the target network element, and based on the characteristic data, call the first sub-model to perform data analysis to obtain intermediate analysis information.

[0231] S1410, the network data analysis function network element sends the intermediate analysis information of the target network element to the application service network element.

[0232] The specific process of obtaining the intermediate analysis information can be found in the above records and will not be repeated here.

[0233] S1411, the application service network element determines the data analysis result of the target network element based on the intermediate analysis information.

[0234] The application service network element obtains the characteristic data of the target network element (for example, application service parameters), and inputs the characteristic data and intermediate analysis information into the second sub-model of the trained federated learning model to obtain the data analysis results output by the second sub-model.

[0235] After obtaining the data analysis results, the application service network element can also provide application services to the target network element based on the data analysis results. In an optional example, the target network element can be a user terminal, see Figure 15 As shown, the application function network element can obtain the characteristic data of the user terminal, and the network data analysis function network element can obtain the characteristic data of the user terminal from the operation management and maintenance network element. The network data analysis function network element contains data analysis logic functions and model training logic functions. It participates in the training of the federated learning model through the model training logic function and participates in the data analysis of federated learning through the data analysis logic function. The network data analysis function network element can input the characteristic data of the user terminal obtained from the operation management and maintenance network element into the sub-model of the federated learning model it owns, obtain the intermediate analysis information output by the sub-model, and send the intermediate analysis information to the application function network element through the network open function network element. The application function network element inputs the intermediate analysis information and the characteristic data of the user terminal obtained by itself into the sub-model of the federated learning model it owns, obtains the data analysis results output by the sub-model, and controls the user terminal based on the data analysis results.

[0236] It should be noted that the data processing method in this embodiment can be applied to various scenarios that require data analysis. For example, with the purpose of optimizing the network resource utilization of the target network element, the federated learning model outputs data analysis results containing network resource configuration policies, so that the application service network element configures the network resources of the target network element based on the network resource configuration policy.

[0237] Figure 14 The specific implementation method of S1410-S1411 shown has been described in detail in the above embodiments and will not be repeated here.

[0238] exist Figure 14 In the embodiment shown, data silos caused by data privacy between application service network elements and network data analysis function network elements can be avoided, and joint data modeling and analysis can be achieved while ensuring data privacy, which can improve the accuracy of data analysis. Application services can be provided based on the data analysis results, which can improve the quality of application services.

[0239] See also Figure 16 , Figure 16FIG. 1 is a block diagram of a data processing device according to an exemplary embodiment of the present invention. Figure 16 As shown, the device includes:

[0240] The sending module 1601 is configured to send a data analysis request for a target network element to be analyzed to the network data analysis function network element, so that the network data analysis function network element obtains first feature data of the target network element according to the data analysis request, and performs data analysis on the first feature data using the first sub-model of the federated learning model to obtain intermediate analysis information;

[0241] The receiving module 1602 is configured to receive the intermediate analysis information sent by the network data analysis function network element;

[0242] The analysis module 1603 is configured to obtain second characteristic data of the target network element, and perform data analysis on the intermediate analysis information and the second characteristic data of the target network element using the second sub-model of the federated learning model to obtain a data analysis result of the target network element;

[0243] The service module 1604 is configured to provide application services to the target network element according to the data analysis results.

[0244] In an exemplary embodiment, based on the above solution, the apparatus further includes an updating module configured to:

[0245] Receiving a first model update parameter sent by the network data analysis function network element; wherein the first model update parameter is obtained by the network data analysis function network element by training the first sub-model according to the first feature data of the training sample;

[0246] Obtaining second feature data and data analysis result labels of the training samples, and training the second sub-model based on the second feature data and data analysis result labels of the training samples to obtain second model update parameters;

[0247] updating the second sub-model according to the first model update parameter and the second model update parameter;

[0248] The second model update parameter is sent to the network data analysis function network element, so that the network data analysis function network element updates the first sub-model according to the first model update parameter and the second model update parameter.

[0249] In an exemplary embodiment, based on the above solution, the update module is specifically configured as follows:

[0250] Sending an information subscription request to the network data analysis function network element, so that the network data analysis function network element obtains the first feature data of the training sample according to the information subscription request, and trains the first sub-model according to the first feature data to obtain the first model update parameter;

[0251] A first model update parameter is obtained from the network data analysis function network element.

[0252] In an exemplary embodiment, based on the above solution, the update module is specifically configured as follows:

[0253] Sending an information subscription request to a control plane network element, so that the control plane network element sends the information subscription request to a network data analysis function network element; wherein the control plane network element includes a network open function network element;

[0254] Receive the subscription success notification message sent by the network data analysis function network element through the control plane network element.

[0255] In an exemplary embodiment, based on the above solution, the update module is specifically configured as follows:

[0256] Obtaining performance parameters corresponding to a plurality of network data analysis function network elements, and selecting a network data analysis function network element that participates in a federated learning model from the plurality of network data analysis function network elements based on the performance parameters corresponding to the plurality of network data analysis function network elements;

[0257] Send an information subscription request to the filtered network data analysis function network elements.

[0258] In an exemplary embodiment, based on the above solution, the update module is specifically configured as follows:

[0259] Obtaining, from the performance parameters of each network data analysis function network element, the number of historical information subscription requests received by each network data analysis function network element and the amount of idle resources of each network data analysis function network element;

[0260] Calculate the quality score of each network data analysis function network element based on the number of historical information subscription requests received by each network data analysis function network element and the amount of idle resources of each network data analysis function network element; wherein the quality score is positively correlated with the amount of idle resources and positively correlated with the number of historical information subscription requests;

[0261] A set number of network data analysis function network elements are selected from the plurality of network data analysis function network elements in descending order of the corresponding quality scores.

[0262] In an exemplary embodiment, based on the above solution, the device further includes an alignment module configured to:

[0263] Receiving a first identification ciphertext set sent by the network data analysis function network element, wherein the first identification ciphertext set includes the identification information ciphertext of each sample network element in the first sample set, and the identification information ciphertext of each sample network element is obtained by encrypting the identification information of each sample network element by the network data analysis function network element;

[0264] Encrypting the identification information of each sample network element in the second sample set to obtain a ciphertext of the identification information of each sample network element in the second sample set, so as to construct a second ciphertext set of identification information; wherein the encryption method of the ciphertext of the identification information included in the first ciphertext set of identification information matches the encryption method of the ciphertext of the identification information included in the second ciphertext set of identification information;

[0265] The shared identification information ciphertext is searched from the first identification ciphertext set and the second identification ciphertext set, and the sample network element corresponding to the shared identification information ciphertext is used as a training sample.

[0266] It should be noted that Figure 16 The data processing device provided and the data processing method corresponding to the application service network element provided in the above embodiment belong to the same concept, and the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here.

[0267] See also Figure 17 , Figure 17 FIG. 4 is a block diagram of a data processing device according to an exemplary embodiment of the present application.

[0268] like Figure 17 As shown, the device includes:

[0269] The receiving module 1701 is configured to receive a data analysis request for a target network element to be analyzed sent by an application service network element, and obtain first feature data of the target network element according to the data analysis request;

[0270] An analysis module 1702 is configured to perform data analysis on the first feature data using a first sub-model of the federated learning model to obtain intermediate analysis information;

[0271] The sending module 1703 is configured to send the intermediate analysis information to the application service network element, so that the application service network element performs data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model, obtains the data analysis result of the target network element, and provides application services for the target network element based on the data analysis result.

[0272] In an exemplary embodiment, based on the above solution, the apparatus further includes an updating module configured to:

[0273] Training the first sub-model according to the first feature data of the training sample to obtain a first model update parameter;

[0274] Sending the first model update parameter to the application service network element, so that the application service network element updates the second sub-model according to the first model update parameter and the second model update parameter; wherein the second model update parameter is obtained by the application service network element through training the second sub-model according to the second feature data of the training sample and the data analysis result label;

[0275] Receive the second model update parameter sent by the application service network element, and update the first sub-model according to the first model update parameter and the second model update parameter.

[0276] In an exemplary embodiment, based on the above solution, the receiving module 1701 is specifically configured as follows:

[0277] Obtaining network parameters of the target network element from the operation management and maintenance network element; wherein the network parameters include a channel quality indicator;

[0278] The network parameter of the target network element is added to the first characteristic data of the target network element.

[0279] In an exemplary embodiment, based on the above solution, the receiving module 1701 is specifically configured as follows:

[0280] According to the data analysis request, the application service network element is authenticated and the authentication result is obtained; the application service network element includes the application function network element and the network upper layer service network element;

[0281] If the verification result indicates that the application service network element has the authority to obtain the intermediate analysis information of the target network element, the first feature data of the target network element is obtained.

[0282] In an exemplary embodiment, based on the above solution, the receiving module 1701 is specifically configured as follows:

[0283] Select a target permission verification method from a variety of permission verification methods based on the attribute data of the application service network element and the type of the target network element; wherein different permission verification methods have different verification completeness;

[0284] According to the target authority verification method, the application service network element is verified for authority and a verification result is obtained.

[0285] It should be noted that Figure 17 The data processing device provided and the data processing method corresponding to the network data analysis function network element provided in the above embodiment belong to the same concept, and the specific way in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here.

[0286] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more computer programs, wherein when the one or more computer programs are executed by one or more processors, the electronic device implements the data processing method provided in the above-mentioned embodiments.

[0287] Figure 18 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown.

[0288] It should be noted that Figure 18 The computer system 1800 of the electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present application.

[0289] like Figure 18 As shown, the computer system 1800 includes a central processing unit (CPU) 1801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1802 or a computer program loaded from a storage portion 1808 into a random access memory (RAM) 1803, such as executing the data processing method in the above embodiment. Various computer programs and data required for system operation are also stored in the RAM 1803. The CPU 1801, ROM 1802, and RAM 1803 are connected to each other via a bus 1804. An input / output (I / O) interface 1805 is also connected to the bus 1804.

[0290] In some embodiments, the following components are connected to the I / O interface 1805: an input section 1806 including a keyboard, a mouse, and the like; an output section 1807 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 1808 including a hard disk; and a communication section 1809 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 1809 performs communication processing via a network such as the Internet. A drive 1810 is also connected to the I / O interface 1805 as needed. Removable media 1811, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 1810 as needed, so that computer programs read from the removable media can be installed in the storage section 1808 as needed.

[0291] In particular, according to an embodiment of the present application, a computer program that implements the data processing method can be carried on a computer-readable medium, and the computer program can be downloaded and installed from the network through the communication part 1809 and / or installed from the removable medium 1811.

[0292] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. Computer-readable storage medium can be, for example, a system, device or component of electricity, magnetism, light, electromagnetic, infrared or semiconductor, or any combination of the above. More specific examples of computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium containing or storing a computer program, which can be used by an instruction execution system, a device or a device or used in combination with it. A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer program readable by a computer. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer program embodied in a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0293] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and a computer program.

[0294] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0295] Another aspect of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of an electronic device, the electronic device implements the aforementioned data processing method. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device.

[0296] Another aspect of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, implements the data processing method provided in each of the above embodiments. The computer program can be stored in a computer-readable storage medium.

[0297] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. Ordinary technicians in this field can easily make corresponding changes or modifications based on the main ideas and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.

Claims

1. A data processing method, characterized in that: The method comprises: Sending a data analysis request for a target network element to be analyzed to a network data analysis function network element, so that the network data analysis function network element obtains first feature data of the target network element according to the data analysis request, and performs data analysis on the first feature data through a first sub-model of a federated learning model to obtain intermediate analysis information; Receiving the intermediate analysis information sent by the network data analysis function network element; Obtaining second characteristic data of the target network element, and performing data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model to obtain a data analysis result of the target network element; Provide application services for the target network element according to the data analysis results.

2. The method according to claim 1, wherein The method further comprises: Receiving a first model update parameter sent by the network data analysis function network element; wherein the first model update parameter is obtained by the network data analysis function network element by training the first sub-model according to the first feature data of the training sample; Obtaining the second feature data and the data analysis result label of the training sample, and training the second sub-model according to the second feature data and the data analysis result label of the training sample to obtain the second model update parameter; updating the second sub-model according to the first model update parameter and the second model update parameter; The second model update parameter is sent to the network data analysis function network element, so that the network data analysis function network element updates the first sub-model according to the first model update parameter and the second model update parameter.

3. The method according to claim 2, wherein The receiving the first model update parameter sent by the network data analysis function network element includes: Sending an information subscription request to the network data analysis function network element, so that the network data analysis function network element obtains the first feature data of the training sample according to the information subscription request, and trains the first sub-model according to the first feature data to obtain the first model update parameter; The first model update parameter is obtained from the network data analysis function network element.

4. The method according to claim 3, wherein The sending of the information subscription request to the network data analysis function network element includes: Sending the information subscription request to a control plane network element, so that the control plane network element sends the information subscription request to the network data analysis function network element; wherein the control plane network element includes a network open function network element; Receive a subscription success notification message sent by the network data analysis function network element through the control plane network element.

5. The method according to claim 3, wherein The sending of the information subscription request to the network data analysis function network element includes: Obtaining performance parameters respectively corresponding to a plurality of network data analysis function network elements, and screening out network data analysis function network elements participating in the federated learning model from the plurality of network data analysis function network elements based on the performance parameters respectively corresponding to the plurality of network data analysis function network elements; Send an information subscription request to the filtered network data analysis function network elements.

6. The method according to claim 5, wherein The selecting, from the plurality of network data analysis function network elements, a network data analysis function network element that participates in the federated learning model according to the performance parameters respectively corresponding to the plurality of network data analysis function network elements, includes: Obtaining, from the performance parameters of each network data analysis function network element, the number of historical information subscription requests received by each network data analysis function network element and the amount of idle resources of each network data analysis function network element; Calculating a quality score of each network data analysis function network element based on the number of historical information subscription requests received by each network data analysis function network element and the amount of idle resources of each network data analysis function network element; wherein the quality score is positively correlated with the amount of idle resources and positively correlated with the number of historical information subscription requests; A set number of network data analysis function network elements are screened out from the plurality of network data analysis function network elements in descending order of the corresponding quality scores.

7. The method according to claim 2, wherein The method further comprises: Receive a first identification ciphertext set sent by the network data analysis function network element, wherein the first identification ciphertext set includes the identification information ciphertext of each sample network element in the first sample set, and the identification information ciphertext of each sample network element is obtained by encrypting the identification information of each sample network element by the network data analysis function network element; Encrypting the identification information of each sample network element in the second sample set to obtain a ciphertext of the identification information of each sample network element in the second sample set, so as to construct a second set of ciphertext identification information; wherein the encryption method of the ciphertext identification information included in the first set of ciphertext identification information matches the encryption method of the ciphertext identification information included in the second set of ciphertext identification information; The common identification information ciphertext is searched from the first identification ciphertext set and the second identification ciphertext set, and the sample network element corresponding to the common identification information ciphertext is used as the training sample.

8. A data processing method, characterized in that: The method comprises: receiving a data analysis request for a target network element to be analyzed sent by an application service network element, and obtaining first feature data of the target network element according to the data analysis request; Performing data analysis on the first feature data using a first sub-model of a federated learning model to obtain intermediate analysis information; The intermediate analysis information is sent to the application service network element, so that the application service network element performs data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model, obtains the data analysis result of the target network element, and provides application services for the target network element based on the data analysis result.

9. The method according to claim 8, wherein The method further comprises: Training the first sub-model according to the first feature data of the training sample to obtain a first model update parameter; Sending the first model update parameter to the application service network element, so that the application service network element updates the second sub-model according to the first model update parameter and the second model update parameter; wherein the second model update parameter is obtained by the application service network element through training the second sub-model according to the second feature data of the training sample and the data analysis result label; Receive the second model update parameter sent by the application service network element, and update the first sub-model according to the first model update parameter and the second model update parameter.

10. The method according to claim 8, wherein The acquiring the first characteristic data of the target network element according to the data analysis request includes: Acquire network parameters of the target network element from an operation management and maintenance network element; wherein the network parameters include a channel quality indicator; The network parameter of the target network element is added to the first characteristic data of the target network element.

11. The method according to claim 8, wherein The acquiring the first characteristic data of the target network element according to the data analysis request includes: According to the data analysis request, the application service network element is authenticated to obtain a verification result; wherein the application service network element includes an application function network element and a network upper layer service network element; If the verification result indicates that the application service network element has the authority to obtain the intermediate analysis information of the target network element, the first feature data of the target network element is obtained.

12. The method according to claim 11, wherein The performing permission verification on the application service network element according to the data analysis request to obtain a verification result includes: selecting a target authority verification method from a plurality of authority verification methods according to the attribute data of the application service network element and the type of the target network element; wherein different authority verification methods have different verification completeness; According to the target authority verification method, the application service network element is verified for authority to obtain the verification result.

13. A data processing device, characterized in that: The device comprises: a sending module configured to send a data analysis request for a target network element to be analyzed to a network data analysis function network element, so that the network data analysis function network element obtains first feature data of the target network element according to the data analysis request, and performs data analysis on the first feature data through a first sub-model of a federated learning model to obtain intermediate analysis information; a receiving module configured to receive the intermediate analysis information sent by the network data analysis function network element; an analysis module configured to obtain second characteristic data of the target network element, and perform data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model to obtain a data analysis result of the target network element; A service module is configured to provide application services for the target network element according to the data analysis result.

14. A data processing device, characterized in that: The device comprises: a receiving module configured to receive a data analysis request for a target network element to be analyzed sent by an application service network element, and obtain first feature data of the target network element according to the data analysis request; an analysis module configured to perform data analysis on the first feature data using a first sub-model of a federated learning model to obtain intermediate analysis information; A sending module is configured to send the intermediate analysis information to the application service network element, so that the application service network element performs data analysis on the intermediate analysis information and the second characteristic data of the target network element through the second sub-model of the federated learning model, obtains the data analysis result of the target network element, and provides application services for the target network element based on the data analysis result.

15. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more computer programs, which, when executed by the one or more processors, enables the electronic device to implement the method according to any one of claims 1 to 12.

16. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor of an electronic device, the electronic device is enabled to implement the method according to any one of claims 1 to 12.

17. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 12 when being executed by a processor.

Images