Data service method and system, communication system, storage medium and program product

Abstract

The invention provides a data service method and system, a communication system, a storage medium and a computer program product. The method comprises the steps that a data service network element receives an artificial intelligence data service request sent by service demand equipment; and the data service network element executes corresponding processing operation according to the artificial intelligence data service request, and returns an execution result to the service demand equipment. According to the technical scheme, the service demand equipment requests the network side to complete the artificial intelligence data service, the artificial intelligence data is provided in a servitization form, and the service demand equipment can utilize the artificial intelligence data service; diversified artificial intelligence data services can be provided for service demand equipment, the efficiency of service processing such as artificial intelligence model training and reasoning can be improved, and the quality of the artificial intelligence data services is improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a data service method, system, communication system, storage medium and computer program product. Background Art

[0002] At present, six major application scenarios have been proposed for communication network systems such as 6G: immersive communication, ultra-large-scale connection, extremely high reliability and low latency, integration of artificial intelligence (AI) and communication, integration of perception and communication, and ubiquitous connection; among them, the last three application scenarios are emerging scenarios for integrated innovation, and perception and AI are clearly defined as new capabilities. The huge amount of data generated by perception capabilities can be used by AI technology to make autonomous judgments and decisions, which can improve network performance or directly support upper-layer applications. The application of AI algorithms will greatly enhance the overall performance of the network, improve user experience and optimize efficiency. With the advancement of communication systems, more diverse AI model data and training data will appear, which need to be efficiently circulated and shared between different network architectures and network element nodes. In future communication networks, data processing based on data service system architecture has become a trend. However, the existing relevant communication protocols do not provide solutions for how terminals request the network side to complete AI model training and reasoning and other processing. Therefore, it is necessary to provide relevant technical solutions for data services. Summary of the invention

[0003] The present disclosure provides a data service method, system, communication system, storage medium and computer program product.

[0004] According to a first aspect of the present disclosure, a data service method is provided, including: a data service network element receives an artificial intelligence data service request sent by a service demand device; the data service network element performs corresponding processing operations according to the artificial intelligence data service request, and returns the execution result to the service demand device.

[0005] Optionally, the data service network element includes a data service management function network element; the data service network element receiving the artificial intelligence data service request sent by the terminal includes: the data service management function network element receiving the artificial intelligence data service request.

[0006] Optionally, the data service network element includes an execution network element; the data service management function network element and the data service network element perform corresponding processing operations according to the artificial intelligence data service request, including: the data service management function network element determines the execution network element corresponding to the artificial intelligence data service request, and controls the execution network element to perform the processing operation.

[0007] Optionally, the artificial intelligence data service request includes the artificial intelligence model training request; the execution network element includes a first data plane functional network element and a first data storage functional network element; and controlling the execution network element to perform the processing operation includes: the data service management functional network element generates a training task for model training, and controls the first data plane functional network element and the first data storage functional network element to perform model training processing according to the training task.

[0008] Optionally, the training task includes a data storage task and a first data processing task; and controlling the first data plane functional network element and the first data storage functional network element to perform model training processing according to the training task includes: the data service management functional network element assigns the first data processing task to the first data plane functional network element, so that the first data plane functional network element performs model training based on sample data, obtains the model training results and sends them to the first data storage functional network element; the data service management functional network element sends the data storage task to the first data storage functional network element, so that the first data storage functional network element stores the model training results.

[0009] Optionally, the data service management function network element sends the first data collection task to the wireless access network, so that the wireless access network collects the sample data and sends it to the first data plane function network element.

[0010] Optionally, the data service management function network element sends a data request to the service demand device, so that the service demand device sends the sample data to the first data plane function network element.

[0011] Optionally, the execution result includes model training completion information; and returning the execution result to the service demand device includes: the data service management function network element returns the model training completion information to the service demand device.

[0012] Optionally, the artificial intelligence data service request includes the artificial intelligence reasoning processing request; the execution network element includes a second data plane functional network element and a second data storage functional network element; the data service management functional network element determines the execution network element corresponding to the artificial intelligence data service request, and controls the execution network element to perform the processing operation, including: the data service management functional network element generates an inference task for performing artificial intelligence reasoning, and controls the second data plane functional network element and the second data storage functional network element to perform inference processing according to the inference task.

[0013] Optionally, the reasoning task includes a second data collection task and a second data processing task; and controlling the second data plane functional network element and the second data storage functional network element to perform reasoning processing according to the reasoning task includes: the data service management functional network element assigns the second data processing task to the second data plane functional network element, so that the second data plane functional network element uses the artificial intelligence model stored in the second data storage functional network element to perform reasoning processing on the sample data to be reasoned and obtain an reasoning result; the data service management functional network element sends the second data collection task to the second data storage functional network element, so that the second data storage functional network element returns the artificial intelligence model to the second data plane functional network element when it receives the model request sent by the second data plane functional network element.

[0014] Optionally, the data service management function network element sends the address of the second data storage function network element to the service demand device, so that the service demand device sends the sample data to be inferred to the second data plane function network element.

[0015] Optionally, the execution result includes reasoning result information; and returning the execution result to the service demand device includes: the second data plane function network element returns the reasoning result information to the service demand device.

[0016] Optionally, the data service management function network element determines the execution network element corresponding to the artificial intelligence data service request, including: the data service management function network element sends a service discovery request message to a network registration center according to the artificial intelligence data service request; the data service management function network element receives a service discovery response message returned by the network registration center, and determines the execution network element from the artificial intelligence data service network element carried by the service discovery response message.

[0017] Optionally, the information carried by the artificial intelligence data service request includes: one or more of: request type, request node location information, artificial intelligence task identifier, artificial intelligence data service type, data service capability type, and an identifier that the service request device carries sample data.

[0018] According to a second aspect of the present disclosure, a data service system is provided, including: a data service network element, used to receive an artificial intelligence data service request sent by a service demand device; according to the artificial intelligence data service request, perform corresponding processing operations, and return the execution result to the service demand device.

[0019] Optionally, the data service network element includes a data service management function network element; the data service management function network element is used to receive the artificial intelligence data service request.

[0020] Optionally, the data service network element includes an execution network element; the data service management function network element is used to determine the execution network element corresponding to the artificial intelligence data service request, and control the execution network element to perform the processing operation.

[0021] Optionally, the artificial intelligence data service request includes the artificial intelligence model training request; the execution network element includes a first data plane functional network element and a first data storage functional network element; the data service management functional network element is used to generate a training task for model training, and control the first data plane functional network element and the first data storage functional network element to perform model training processing according to the training task.

[0022] Optionally, the training task includes a data storage task and a first data processing task; the data service management functional network element is used to assign the first data processing task to the first data plane functional network element; the data storage task is sent to the first data storage functional network element; the first data plane functional network element is used to perform model training based on sample data, obtain model training results and send them to the first data storage functional network element; the first data storage functional network element is used to store the model training results.

[0023] Optionally, the data service management function network element is used to send a first data collection task to a wireless access network, so that the wireless access network collects the sample data and sends it to the first data plane function network element.

[0024] Optionally, the data service management function network element is used to send a data request to the service demand device, so that the service demand device sends the sample data to the first data plane function network element.

[0025] Optionally, the execution result includes model training completion information; the data service management function network element is used to return the model training completion information to the service demand device.

[0026] Optionally, the artificial intelligence data service request includes the artificial intelligence reasoning processing request; the execution network element includes a second data plane functional network element and a second data storage functional network element; the data service management functional network element is used to generate an inference task for performing artificial intelligence reasoning, and control the second data plane functional network element and the second data storage functional network element to perform reasoning processing according to the inference task.

[0027] Optionally, the reasoning task includes a second data collection task and a second data processing task; the data service management functional network element is used to assign the second data processing task to the second data plane functional network element, and send the second data collection task to the second data storage functional network element; the second data plane functional network element is used to use the artificial intelligence model stored in the second data storage functional network element to perform reasoning processing on the sample data to be inferred to obtain an reasoning result; the second data storage functional network element is used to return the artificial intelligence model to the second data plane functional network element upon receiving a model request sent by the second data plane functional network element.

[0028] Optionally, the data service management function network element is used to send the address of the second data storage function network element to the service demand device, so that the service demand device sends the sample data to be inferred to the second data plane function network element.

[0029] Optionally, the execution result includes reasoning result information; and the second data plane functional network element is used to return the reasoning result information to the service demand device.

[0030] Optionally, the data service management function network element is used to send a service discovery request message to a network registration center according to the artificial intelligence data service request; receive a service discovery response message returned by the network registration center, and determine the execution network element from the artificial intelligence data service network element carried by the service discovery response message.

[0031] According to a third aspect of the present disclosure, a communication system is provided, comprising: the data service system as described above.

[0032] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are executed by a processor as described above.

[0033] According to a fifth aspect of the present disclosure, a computer program product is provided, wherein the computer program product stores computer instructions, and the computer instructions are executed by a processor according to the method described above.

[0034] The data service method, system, communication system, storage medium and computer program product disclosed in the present invention receive artificial intelligence data service requests sent by service demand devices through data service network elements and perform corresponding processing operations; a technical solution is proposed for service demand devices to request the network side to complete artificial intelligence data services, and artificial intelligence data is provided in a service-oriented form, so that service demand devices can use artificial intelligence data services; it can provide diversified artificial intelligence data services for service demand devices, improve the efficiency of service processing such as artificial intelligence model training and reasoning, and improve the quality of artificial intelligence data services. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] By describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present disclosure will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. The above and other purposes and advantages of the present disclosure will be further described below in conjunction with specific embodiments and with reference to the accompanying drawings. In the accompanying drawings, the same or corresponding technical features or components will be represented by the same or corresponding figure marks.

[0036] Figure 1 is a flowchart of some embodiments of the data service method according to the present disclosure;

[0037] Figure 2 A schematic diagram of a flow chart of a control execution network element executing a processing operation in some embodiments of the data service method disclosed herein;

[0038] Figure 3 A schematic diagram of a process for performing artificial intelligence model training in some embodiments of the data service method disclosed herein;

[0039] Figure 4 A schematic diagram of a process for performing artificial intelligence model training in other embodiments of the data service method according to the present disclosure;

[0040] Figure 5 A schematic diagram of a process for performing artificial intelligence model training in some other embodiments of the data service method disclosed herein;

[0041] Figure 6 A schematic diagram of a process of performing manual reasoning in some embodiments of the data service method according to the present disclosure;

[0042] Figure 7 A schematic diagram of a process of performing manual reasoning in other embodiments of the data service method according to the present disclosure;

[0043] Figure 8A schematic diagram of a process of determining an execution network element in some embodiments of the data service method according to the present disclosure;

[0044] Figure 9A-9C is a schematic diagram of a data service system according to the present disclosure;

[0045] Fig. 10A A schematic diagram of a service-oriented interface to support data services; Fig. 10B Schematic diagram of a point-to-point interface supporting data services. DETAILED DESCRIPTION

[0046] Exemplary embodiments of the present disclosure will be described below in conjunction with the accompanying drawings. For the sake of clarity and conciseness, not all features of the embodiments are described in the specification. However, it should be understood that many implementation-specific settings must be made in the process of implementing the embodiments in order to achieve the specific goals of the developer, for example, to meet those restrictions related to the device and the service, and these restrictions may vary depending on the implementation. In addition, it should be understood that although the development work may be very complex and time-consuming, it is only a routine task for those skilled in the art who benefit from the content of this disclosure.

[0047] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

[0048] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0049] It should also be understood that in the embodiments of the present disclosure, “plurality” may refer to two or more than two, and “at least one” may refer to one, two, or more than two.

[0050] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0051] In addition, the term "and / or" in the present disclosure is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present disclosure generally indicates that the associated objects before and after are in an "or" relationship.

[0052] It should also be understood that the description of the various embodiments in the present disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0053] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0054] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0055] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0056] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0057] In addition, in order to avoid obscuring the present disclosure due to unnecessary details, only the processing steps and / or device structures closely related to at least the scheme according to the present disclosure are shown in the drawings, and other details that are not closely related to the present disclosure are omitted. It should also be noted that similar reference numerals and letters in the drawings indicate similar items, and therefore once an item is defined in one drawing, it does not need to be discussed again for subsequent drawings.

[0058] Figure 1 is a flowchart of some embodiments of the data service method according to the present disclosure, such as Figure 1 As shown:

[0059] Step S101: The data service network element receives an artificial intelligence data service request sent by a service demand device.

[0060] Data service network elements may include multiple network elements; service demand devices may include multiple devices, such as smart terminals, UE (User Equipment), cars, drones, etc. AI data service requests may include AI model training requests, AI reasoning requests, and other requests.

[0061] In the process of AI model training and reasoning, various data types are involved. These data are called AI data, including models, gradients, confidence, vectors, etc. The information carried by AI data service requests includes: one or more of the following: request type, request node location information, AI task identifier, AI data service type, data service capability type, and identifier of sample data carried by the service request device.

[0062] Step S102: The data service network element performs corresponding processing operations according to the artificial intelligence data service request and returns the execution result to the service demand device.

[0063] The data service network element performs corresponding processing operations including artificial intelligence model training, artificial intelligence reasoning, etc.; the execution result may be the execution result of the data service network element for artificial intelligence model training requests, artificial intelligence reasoning requests, etc.

[0064] The data service method disclosed in the present invention receives the artificial intelligence data service request sent by the service demand device through the data service network element and performs corresponding processing operations. It proposes a technical solution for the service demand device to request the network side to complete the artificial intelligence data service, and provides artificial intelligence data in a service-oriented form, so that the service demand device can use the artificial intelligence data service; it can provide diversified artificial intelligence data services for service demand devices, improve the efficiency of service processing such as artificial intelligence model training and reasoning, and improve the quality of artificial intelligence data services.

[0065] In some embodiments, the data service network element includes a data service management function (DSMF) network element and an execution network element; the data service management function network element is used to translate the data service requirements, break them down into data service tasks, select execution network elements with different data capabilities, and form a logical topology of executable services to realize specific data service functions.

[0066] Execution network elements include data plane function (DPF) network elements, data storage (DSF) function network elements, etc. Data plane function network elements are used to realize data collection, transmission, preprocessing, analysis and other functions; data storage function network elements are used to realize functions such as storage of collected data and data service results.

[0067] Figure 2 FIG. 1 is a flow chart of a control execution network element executing a processing operation in some embodiments of the data service method of the present disclosure, such as Figure 2 As shown:

[0068] Step S201: The data service management function network element receives an artificial intelligence data service request.

[0069] Step S202: The data service management function network element determines the execution network element corresponding to the artificial intelligence data service request, and controls the execution network element to perform the processing operation.

[0070] In the case where the artificial intelligence data service request includes an artificial intelligence model training request, the execution network element includes a first data plane functional network element, a first data storage functional network element, etc. The data service management functional network element generates a training task for model training, and controls the first data plane functional network element and the first data storage functional network element to perform model training processing according to the training task.

[0071] For example, the training task includes a data storage task, a first data processing task, etc.; the data service management functional network element assigns the first data processing task to the first data plane functional network element, and the first data processing task may be a model training task, etc., so that the first data plane functional network element performs model training based on sample data, obtains model training results and sends them to the first data storage functional network element; the model training results include a trained artificial intelligence model, etc. The data service management functional network element sends the data storage task to the first data storage functional network element, so that the first data storage functional network element stores the model training results.

[0072] The data service management function network element may send the first data collection task to the wireless access network so that the wireless access network collects sample data and sends it to the first data plane function network element. Alternatively, the data service management function network element sends a data request to the service demand device so that the service demand device sends the sample data to the first data plane function network element.

[0073] After the first data plane functional network element completes model training based on the sample data sent by the wireless access network or the service demand device, the data service management functional network element returns model training completion information to the service demand device. The model training completion information may carry notification information of the completion of model training, but may not include the trained model.

[0074] The model type, model characteristics and other information of the initial model can be carried in the artificial intelligence model training request. The model characteristics can be the functions and performance characteristics of the model, etc. The initial model can be a variety of models, for example, the initial model is a neural network model, etc. The initial model can be stored in a model library on the network side.

[0075] A pre-trained model library can be maintained on the network side, and the initial model stored in the model library has a certain generalization ability after preliminary training and optimization. The data service management functional network element determines the matching initial model from the model library based on the model type, model characteristics and other information of the initial model carried in the artificial intelligence model training request, and dispatches the initial model to the first data plane functional network element; the first data plane functional network element can use the existing model training method to further train and optimize the initial model based on the sample data to obtain a trained model.

[0076] In some embodiments, the AI ​​service demand device may be a UE, etc. The AI ​​service demand device sends an artificial intelligence model training request to the data service network element. The information carried in the artificial intelligence model training request may include one or more of the request type, request node location information, artificial intelligence task identifier, artificial intelligence data service type, data service capability type, identifier of the service demand device carrying sample data, and information such as model type and model characteristics. The data service network element performs model training and sends model training completion information to the AI ​​service demand device.

[0077] Figure 3 The flowchart of performing artificial intelligence model training in some embodiments of the data service method disclosed herein is as follows: the data service network element includes a data service management function network element, a first data plane function network element, and a first data storage function network element; the first data plane function network element includes a first data processing network element and a first data collection network element; Figure 3 As shown:

[0078] Step S301: The AI ​​service demand device sends an AI model training request.

[0079] Step S302: The data service management function network element arranges and selects the appropriate first data collection network element, first data processing network element and first data storage network element as the execution network element according to the data service type, data service capability and other information carried in the AI ​​model training request. The data service management function network element can use a variety of methods to arrange and select the execution network element.

[0080] For example, the data service management function network element selects a network element that meets the data service type (such as statistical analysis of registration or session) and data service capabilities (data collection, processing, storage, etc.) required by the AI ​​model training request from the registered data service NF (Network Function) as the execution network element.

[0081] Step S303, the data service management function network element dispatches tasks such as data collection, data analysis, data processing, and data storage to each execution network element, and notifies each execution network element of the specific execution task and the object of output report.

[0082] Step S304: the data service execution network elements cooperate to execute the tasks.

[0083] Step S305: The first data processing network element sends a request to store the training results. The request carries the AI ​​model training results, and the AI ​​model training results include the trained model, etc.

[0084] Step S306: The first data storage network element stores the AI ​​model training results according to the received request.

[0085] Step S307: The first data storage network element sends storage completion response information to the first data processing network element.

[0086] Step S308: The first data processing network element sends the completion information of the AI ​​model training to the AI ​​service demand device.

[0087] Figure 4 Schematic diagram of the process of performing artificial intelligence model training in other embodiments of the data service method according to the present disclosure; the data service network element includes a data service management function network element DSMF, a data plane function network element DPF, and a data storage function network element DSF; before performing artificial intelligence model training, each network element registers its own data service capability and other information to the network registration center; Figure 4 As shown:

[0088] In step S401, the UE sends an AI model training request to the eAMF (evolved Access and Mobility Management Function) through a NAS (Non-Access Stratum) message; the information carried in the AI ​​model training request includes parameters such as request type (data service request type, etc.), requesting node location information (UE location information, etc.), AI task identifier, AI data service type (training or reasoning service type), data service capability type (capability types such as collection, analysis, processing or storage), as well as model type, model characteristics and other information.

[0089] Step S402: eAMF sends an AI model training request to DSMF.

[0090] Step S403, DSMF selects matching RAN (Radio Access Network), DPF and DSF according to task configuration arrangement; wherein DSMF can determine the network element that performs corresponding data collection, processing and storage according to the data service capability type information registered by each network element.

[0091] Step S404, DSMF dispatches tasks such as data storage DS, data processing DP, data collection DC, etc. to each data service execution network element, wherein:

[0092] Step S404a, the DSMF sends the data processing task to the selected DSF.

[0093] Step S404b, DPF uses the AI ​​task identifier task_id and the data service capability identifier task_cap (DP) as indexes to construct a task table for storing data processing tasks. DP is for data preprocessing, analysis, etc.

[0094] Step S404c: DSMF sends the data storage task to the selected DSF.

[0095] Step S404d, DSF uses the AI ​​task identifier task_id and the data service capability identifier task_cap (DS) as indexes to construct a task table for storing data storage tasks. DS is used to store collected data and data service results.

[0096] Step S404e: DSMF sends the data collection task to RAN.

[0097] Step S404f, DPF uses the AI ​​task identifier task_id and the data service capability identifier task_cap (DC) as indexes to construct a task table for storing data collection tasks. DC is for obtaining data from data sources, including user data, network data, AI data, perception data, etc.

[0098] Step S405: RAN collects sample data according to the task type. RAN can use a variety of existing methods to collect sample data.

[0099] Step S406: RAN sends the sample data to the DPF, and sends the AI ​​task identifier task_id to the DPF.

[0100] In step S407, DPF queries the task table according to the AI ​​task identifier task_id and the data service capability identifier task_cap, parses the sample data, determines the algorithm according to the AI ​​task identifier, data type, data service capability type, and combines the sample data and sample result content to complete the model training.

[0101] Step S408: After DPF completes AI model training, it sends a model training result storage request to DSF.

[0102] Step S409: DSF stores the AI ​​model training results. DSF stores the DPF trained model using task_id as the index.

[0103] Step S410: DSF responds to DPF with storage result information.

[0104] Step S411: DPF sends response information to DSMF.

[0105] Step S412: DSMF sends AI model training task completion information to UE.

[0106] Figure 5 Schematic diagram of the process of performing artificial intelligence model training in some other embodiments of the data service method according to the present disclosure, such as Figure 5 As shown:

[0107] In step S501, the UE sends an AI model training request to the eAMF through a NAS message. The information carried in the AI ​​model training request includes parameters such as request type (data service request type, etc.), request node location information (UE location information, etc.), AI task identifier, AI data service type (training or reasoning service type), data service capability type (capability type such as collection, analysis, processing or storage), as well as model type, model characteristics and other information.

[0108] Step S502: eAMF sends an AI model training request to DSMF.

[0109] Step S503, DSMF arranges and selects matching DPF and DSF according to the task configuration, wherein DSMF determines the network element to perform corresponding data collection, processing and storage according to the data service capability type registered by each network element.

[0110] Step S504, DSMF dispatches data storage, data processing, and data collection tasks to each data service execution network element, wherein:

[0111] Step S504a: DSMF sends the data storage task to the selected DSF.

[0112] Step S504b, DSF uses the AI ​​task identifier task_id and the data service capability identifier task_cap (DP) as indexes to construct a task table for storing data storage tasks.

[0113] Step S504c: DSMF sends the data processing task to the selected DPF.

[0114] Step S504d, DPF constructs a task table using the AI ​​task identifier task_id and the data service capability identifier task_cap (DS) as indexes to store data processing tasks.

[0115] Step S505: DSMF sends a request for obtaining sample data to UE through eAMF, and the request carries the AI ​​task identifier and the address information of the selected DPF network element.

[0116] Step S506: The UE sends the sample data to the DPF.

[0117] In step S507, DPF queries the task table according to the AI ​​task identifier task_id and the data service capability identifier task_cap, parses the sample data, determines the algorithm according to the AI ​​task identifier, data type, data service capability type, and combines the sample data and sample result content to complete the model training.

[0118] Step S508: After DPF completes AI model training, it sends a model training result storage request to DSF.

[0119] Step S509, DSF stores the AI ​​model training results.

[0120] Step S510: DSF responds to DPF with storage result information.

[0121] Step S511: DPF sends response information to DSMF.

[0122] Step S512: DSMF sends AI model training task completion information to UE.

[0123] In some embodiments, the artificial intelligence data service request includes an artificial intelligence reasoning processing request; the execution network element includes a second data plane functional network element and a second data storage functional network element. The data service management functional network element generates a reasoning task for performing artificial intelligence reasoning, and controls the second data plane functional network element and the second data storage functional network element to perform reasoning processing according to the reasoning task.

[0124] Artificial intelligence reasoning can be used in a variety of ways, such as traffic identification, data classification, prediction, and intelligent orchestration. For traffic identification, artificial intelligence reasoning can analyze the characteristics and behavior patterns of network traffic and identify different types of traffic, such as video traffic, voice traffic, and data traffic.

[0125] For data classification, AI reasoning can be used to classify network data for user profiling and behavior analysis. For prediction, AI reasoning can be used to predict future network conditions, user behavior, or business needs based on historical data, providing a basis for network planning and optimization. For intelligent orchestration, AI reasoning can be used to automatically adjust and optimize the allocation and scheduling of network resources based on network status and business needs.

[0126] The reasoning task includes a second data collection task and a second data processing task; the data service management functional network element assigns the second data processing task to the second data plane functional network element. The second data processing task may be an artificial intelligence reasoning task, etc., so that the second data plane functional network element uses the artificial intelligence model stored in the second data storage functional network element to perform reasoning processing on the reasoning sample data to obtain reasoning results. The reasoning results may be traffic identification and processing results, data classification results, prediction results, intelligent orchestration results, etc.

[0127] The data service management functional network element sends the second data collection task to the second data storage functional network element to notify the second data storage functional network element of the artificial intelligence model that needs to be provided. The artificial intelligence model can be a previously stored trained artificial intelligence model. Upon receiving the model request sent by the second data plane functional network element, the second data storage functional network element returns the artificial intelligence model to the second data plane functional network element. The second data storage functional network element can pre-store the trained artificial intelligence model corresponding to the artificial intelligence reasoning processing request. The second data storage functional network element determines the artificial intelligence model to be returned to the second data plane functional network element based on the second data collection task.

[0128] The data service management functional network element sends the address of the second data storage functional network element to the service demand device, so that the service demand device sends the sample data to be inferred to the second data plane functional network element. The sample data to be inferred can be traffic identification sample data, data classification sample data, prediction sample data, intelligent orchestration sample data, etc. The second data plane functional network element performs inference processing based on the sample to be inferred and uses the artificial intelligence model, and returns the inference result information to the service demand device.

[0129] Figure 6 The flowchart of performing manual reasoning in some embodiments of the data service method disclosed herein is as follows: the data service network element includes a data service management function network element, a second data plane function network element, and a second data storage function network element; the second data plane function network element includes a second data processing network element; the data service network element performs AI reasoning (such as traffic identification, classification, prediction, intelligent orchestration, etc.) on network services based on a trained AI model, and outputs reasoning results; Figure 6 As shown:

[0130] Step S601: The AI ​​service demand device initiates an AI reasoning processing request to the data service management function network element.

[0131] Step S602: The data service management function network element arranges and selects a suitable second data processing network element and a second data storage network element for scheduling processing.

[0132] Step S603: the data service management function network element sends the data processing and data collection tasks to each execution network element.

[0133] Step S604: The data service management function network element feeds back the address of the selected second data processing network element to the AI ​​service demand device.

[0134] Step S605: The AI ​​service demand device sends the data to be inferred to the second data processing network element.

[0135] Step S606: The second data processing network element interacts with the second data storage network element to obtain a trained model, and inputs the data to be inferred into the model for processing to obtain an inference result.

[0136] Step S607: The second data processing network element sends the inference response result to the AI ​​service demand device, and the AI ​​service demand device performs subsequent operations based on the result.

[0137] Figure 7 FIG. 1 is a flow chart of performing manual reasoning in other embodiments of the data service method according to the present disclosure, such as Figure 7 As shown:

[0138] Step S701: UE sends an AI reasoning processing request to eAMF via a NAS message.

[0139] Step S702: eAMF sends an AI reasoning processing request to DSMF.

[0140] Step S703: DSMF arranges and selects appropriate DSF and DPF network elements according to the request message.

[0141] Step S704, DSMF dispatches data processing and data collection tasks to DPF and DSF, wherein:

[0142] Step S704a, DSMF sends the data processing task to the selected DPF.

[0143] Step S704b, DPF uses the inference task identifier guess_task_id and the data service capability identifier task_cap(DP) as indexes to construct a task table and store the data processing tasks.

[0144] Step S704c: DSMF sends the data collection task to DSF.

[0145] Step S704d, DSF determines that the AI ​​data service type is AI reasoning, and uses the task identifier task_id and the data service capability identifier task_cap (DS) as indexes to query the previous AI training tasks.

[0146] Step S705: DSMF feeds back the address of the selected DPF to the UE through the eAMF.

[0147] Step S706: The UE sends sample data to be inferred to the DPF.

[0148] Step S707 : The DPF uses the reasoning task identifier and the data service capability identifier as indexes to query the task table and store the data to be reasoned.

[0149] Step S708: DPF initiates a request to DSF to call the AI ​​training model.

[0150] Step S709: DSF sends the AI ​​training result obtained by querying the local task to DPF. The AI ​​training result includes the trained AI model.

[0151] In step S710, the DPF queries the data to be inferred in the task table based on the inference task identifier and the data service capability identifier as indexes, and executes the AI ​​inference task based on the loaded AI model to obtain the inference result.

[0152] Step S711, DPF sends the AI ​​reasoning result to UE.

[0153] Step S712: The UE performs subsequent related operations based on the AI ​​reasoning result.

[0154] In some embodiments, the data service management function network element can use a variety of methods to determine the execution network element corresponding to the artificial intelligence data service request. For example, the data service management function network element sends a service discovery request message to the network registration center according to the artificial intelligence data service request; the data service management function network element receives the service discovery response message returned by the network registration center, and determines the execution network element from the artificial intelligence data service network element carried in the service discovery response message.

[0155] Before the data service management function network element determines the execution network element, each data service execution network element registers its own data service capabilities and other information to the network registration center. After receiving the request, the data service management function network element selects appropriate network elements from the registered data service execution network elements to form a work chain according to the request type and data service requirements. For example, the data service management function network element selects the DPF with data preprocessing capabilities to be responsible for data processing, and selects the DSF with data storage capabilities to be responsible for data storage.

[0156] After receiving the AI ​​data service request, the data service management function network element selects the execution network element with different data capabilities through the network registration center. Figure 8 FIG. 1 is a flow chart of determining an execution network element in some embodiments of the data service method according to the present disclosure, such as Figure 8 As shown:

[0157] Step S801: The data service management function network element sends an AI service discovery request message to query the network registration center for execution network elements with different data capabilities that meet the AI ​​data service requirements.

[0158] The service discovery request message carries at least one of the following information: AI data service executor type identifier, AI data service business type (DC, DS, DP services), AI data service area, AI data service execution node information, AI data service specific QoS requirements, AI data transmission protocol type, etc.

[0159] Step S802: The network registration center authorizes the data service management function network element to discover AI data services.

[0160] Step S803: Send an AI data service request response message. In the AI ​​data service request response message, the network registration center provides the data service management function network element with multiple groups of AI data service execution network elements (for example, IP addresses of multiple groups of execution network elements with different AI data service capabilities) that meet the AI ​​data service requirements and are grouped according to data capabilities.

[0161] Step S804: Select an AI data service execution network element that meets the business requirements. The data service management function network element selects one or more execution network elements from multiple groups of AI data service execution network elements with different data capabilities as the AI ​​data service execution network elements in the AI ​​data service task work chain. When selecting execution network elements, the data service management function network element can make selections based on multiple factors such as the network element's data service capability, performance, and reliability.

[0162] Step S805: The data service management function network element sends the AI ​​data service task to each selected execution network element, and controls each execution network element to collaboratively complete each link in the work chain.

[0163] The data service method in the above embodiment receives the artificial intelligence data service request sent by the service demand device through the data service network element and performs corresponding processing operations. It proposes a technical solution for the service demand device to request the network side to complete the artificial intelligence data service, provides artificial intelligence data in a service-oriented form, and can control, manage and realize AI data transmission, processing, analysis, storage and other functions, so that the service demand device can use the artificial intelligence data service; it can provide diversified artificial intelligence data services for service demand devices, improve the efficiency of service processing such as artificial intelligence model training and reasoning, and improve the quality of artificial intelligence data services.

[0164] In some embodiments, Fig. 9A As shown, the data service network element includes a data service management function network element 91 and an execution network element 92; the data service management function network element 91 receives an artificial intelligence data service request. The data service management function network element 91 determines the execution network element 92 corresponding to the artificial intelligence data service request and controls the execution network element 92 to perform a processing operation.

[0165] The data service management function network element 91 sends a service discovery request message to the network registration center based on the artificial intelligence data service request; the data service management function network element 91 receives the service discovery response message returned by the network registration center, and determines the execution network element 92 from the artificial intelligence data service network element carried in the service discovery response message.

[0166] like Fig. 9B As shown, the execution network element includes a first data plane functional network element 921 and a first data storage functional network element 922; the data service management functional network element 91 generates a training task for model training, and controls the first data plane functional network element 921 and the first data storage functional network element 922 to perform model training processing according to the training task.

[0167] For example, the training task includes a data storage task and a first data processing task; the data service management function network element 91 assigns the first data processing task to the first data plane function network element 921, and sends the data storage task to the first data storage function network element 922.

[0168] The first data plane functional network element 921 performs model training based on the sample data, obtains the model training result and sends it to the first data storage functional network element 922; the first data storage functional network element 922 stores the model training result. The execution result includes model training completion information, and the data service management functional network element 91 returns the model training completion information to the service demand device.

[0169] The data service management function network element 91 sends the first data collection task to the wireless access network so that the wireless access network collects sample data and sends it to the first data plane function network element 921; or, the data service management function network element 91 sends a data request to the service demand device so that the service demand device sends the sample data to the first data plane function network element 921.

[0170] In some embodiments, the execution network element includes a second data plane functional network element 923 and a second data storage functional network element 924; the data service management functional network element 91 generates an inference task for performing artificial intelligence reasoning, and controls the second data plane functional network element 923 and the second data storage functional network element 924 to perform inference processing according to the inference task.

[0171] The reasoning task includes a second data collection task and a second data processing task; the data service management function network element 91 assigns the second data processing task to the second data plane function network element 923, and sends the second data collection task to the second data storage function network element 924.

[0172] The second data plane functional network element 923 uses the artificial intelligence model stored in the second data storage functional network element to perform inference processing on the sample data to be inferred to obtain an inference result; upon receiving the model request sent by the second data plane functional network element, the second data storage functional network element 924 returns the artificial intelligence model to the second data plane functional network element 923.

[0173] The data service management function network element 91 sends the address of the second data storage function network element 923 to the service demand device, so that the service demand device sends the sample data to be inferred to the second data plane function network element 923. The execution result includes the inference result information, etc. The second data plane function network element 923 returns the inference result information to the service demand device.

[0174] In some embodiments, the present disclosure provides a communication system, including a data service system as in any of the above embodiments, and the communication system may be a 6G communication system or other system.

[0175] In the 6G network system, AI data services provide data as a service product based on the framework of data collection, preprocessing, distribution, analysis and release. In the 6G network system, service-oriented interfaces that support data services are as follows: Fig. 10A As shown, the point-to-point interface supporting data services is as follows Fig. 10BThe network elements set up in the 6G network system include DSMF, DPF, DSF, CSMF (Connection Service Management Function), SEF (Service Exposure Function), eAMF, DC, DS and DP, etc. Each network element can communicate with each other through multiple interfaces. For example, DSMF can communicate with eAMF through the N4 interface.

[0176] DSMF is used to select specific NFs with different data capabilities, such as DPF and DSF, to form an executable UE, RAN, DPF, and DSF logical topology, and control the work chain to implement specific data service functions. DSMF also needs to support the data service capability reporting function of DPF.

[0177] DPF is used to realize functions such as data collection, transmission, preprocessing, and analysis. DSF is used to store collected data and data service results. CSMF is used to receive connection service tasks, control the establishment, modification, and release of UE-data network DN connections, etc. SEF is used to open 6G network services to the outside world. DC is used to obtain data from data sources, including the collection of user data, network data, AI data, perception data, etc. DS is used to store collected data and data service results. DP is used for data preprocessing and analysis.

[0178] In some embodiments, the present disclosure provides a computer-readable storage medium storing computer instructions, which implement the methods in any of the above embodiments when the instructions are executed by a processor.

[0179] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive enumeration) of readable storage media can include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0180] The embodiments of the present disclosure may also be a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0181] The data service method, system, communication system, storage medium and computer program product in the above-mentioned embodiments can provide artificial intelligence data in a service-oriented form, can control, manage and implement AI data transmission, processing, analysis, storage and other functions, so that service-demand devices can utilize artificial intelligence data services; can provide diversified artificial intelligence data services for service-demand devices, can improve the efficiency of service processing such as artificial intelligence model training and reasoning, improve the quality of artificial intelligence data services, and improve the user experience.

[0182] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0183] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0184] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0185] It should also be noted that in the apparatus, device and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0186] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0187] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, it will be appreciated by those skilled in the art that the above embodiments are merely illustrative and do not limit the scope of the present disclosure. It will be appreciated by those skilled in the art that the above embodiments may be combined, modified or replaced without departing from the scope and essence of the present disclosure.

Claims

1. A data service method, comprising: The data service network element receives the artificial intelligence data service request sent by the service demand device; The data service network element performs corresponding processing operations according to the artificial intelligence data service request and returns the execution result to the service demand device.

2. The method of claim 1, wherein: The data service network element includes a data service management function network element; the data service network element receives an artificial intelligence data service request sent by a terminal, including: The data service management function network element receives the artificial intelligence data service request.

3. The method of claim 2, wherein: The data service network element includes an execution network element; the data service management function network element, the data service network element performs corresponding processing operations according to the artificial intelligence data service request, including: The data service management function network element determines the execution network element corresponding to the artificial intelligence data service request, and controls the execution network element to perform the processing operation.

4. The method of claim 3, wherein: The artificial intelligence data service request includes the artificial intelligence model training request; the execution network element includes a first data plane function network element and a first data storage function network element; The controlling the executing network element to execute the processing operation includes: The data service management function network element generates a training task for model training, and controls the first data plane function network element and the first data storage function network element to perform model training processing according to the training task.

5. The method of claim 4, wherein: The training task includes a data storage task and a first data processing task; The controlling the first data plane functional network element and the first data storage functional network element to perform model training processing according to the training task includes: The data service management function network element assigns the first data processing task to the first data plane function network element, so that the first data plane function network element performs model training based on the sample data, obtains the model training result and sends it to the first data storage function network element; The data service management function network element sends the data storage task to the first data storage function network element so that the first data storage function network element stores the model training result.

6. The method of claim 5, comprising: The data service management function network element sends the first data collection task to the wireless access network, so that the wireless access network collects the sample data and sends it to the first data plane function network element.

7. The method of claim 5, comprising: The data service management function network element sends a data request to the service demand device, so that the service demand device sends the sample data to the first data plane function network element.

8. The method of claim 4, wherein: The execution result includes model training completion information; The returning the execution result to the service demand device comprises: The data service management function network element returns the model training completion information to the service demand device.

9. The method of claim 3, wherein: The artificial intelligence data service request includes the artificial intelligence reasoning processing request; the execution network element includes a second data plane function network element and a second data storage function network element; The data service management function network element determines the execution network element corresponding to the artificial intelligence data service request, and controls the execution network element to perform the processing operation, including: The data service management function network element generates an inference task for performing artificial intelligence reasoning, and controls the second data plane function network element and the second data storage function network element to perform inference processing according to the inference task.

10. The method of claim 9, wherein: The reasoning task includes a second data collection task and a second data processing task; The controlling the second data plane function network element and the second data storage function network element to perform reasoning processing according to the reasoning task includes: The data service management function network element assigns the second data processing task to the second data plane function network element, so that the second data plane function network element uses the artificial intelligence model stored by the second data storage function network element to perform reasoning processing on the sample data to be inferred, and obtains the reasoning result; The data service management functional network element sends the second data collection task to the second data storage functional network element, so that the second data storage functional network element returns the artificial intelligence model to the second data plane functional network element when receiving the model request sent by the second data plane functional network element.

11. The method of claim 10, comprising: The data service management function network element sends the address of the second data storage function network element to the service demand device, so that the service demand device sends the sample data to be inferred to the second data plane function network element.

12. The method of claim 10, wherein: The execution result includes reasoning result information; and returning the execution result to the service demand device includes: The second data plane functional network element returns the inference result information to the service demand device.

13. The method of claim 3, wherein: The data service management function network element determines that the execution network element corresponding to the artificial intelligence data service request includes: The data service management function network element sends a service discovery request message to the network registration center according to the artificial intelligence data service request; The data service management function network element receives the service discovery response message returned by the network registration center, and determines the execution network element from the artificial intelligence data service network element carried by the service discovery response message.

14. The method according to any one of claims 1 to 13, wherein: The information carried by the artificial intelligence data service request includes: one or more of the request type, request node location information, artificial intelligence task identifier, artificial intelligence data service type, data service capability type, and an identifier of sample data carried by the service request device.

15. A data service system, comprising: Data service network element, used to receive artificial intelligence data service requests sent by service demand devices; According to the artificial intelligence data service request, the corresponding processing operation is performed, and the execution result is returned to the service demand device.

16. The system of claim 15, wherein: The data service network element includes a data service management function network element; The data service management function network element is used to receive the artificial intelligence data service request.

17. The system of claim 16, wherein: The data service network element includes an execution network element; The data service management function network element is used to determine the execution network element corresponding to the artificial intelligence data service request, and control the execution network element to perform the processing operation.

18. The system of claim 17, wherein: The artificial intelligence data service request includes the artificial intelligence model training request; the execution network element includes a first data plane function network element and a first data storage function network element; The data service management function network element is used to generate a training task for model training, and control the first data plane function network element and the first data storage function network element to perform model training processing according to the training task.

19. The system of claim 18, wherein: The training task includes a data storage task and a first data processing task; The data service management function network element is used to allocate the first data processing task to the first data plane function network element; Sending the data storage task to the first data storage functional network element; The first data plane functional network element is used to perform model training based on the sample data, obtain the model training result and send it to the first data storage functional network element; The first data storage functional network element is used to store the model training result.

20. The system of claim 19, wherein: The data service management function network element is used to send the first data collection task to the wireless access network, so that the wireless access network collects the sample data and sends it to the first data plane function network element.

21. The system of claim 19, wherein: The data service management function network element is used to send a data request to the service demand device, so that the service demand device sends the sample data to the first data plane function network element.

22. The system of claim 18, wherein: The execution result includes model training completion information; The data service management function network element is used to return the model training completion information to the service demand device.

23. The system of claim 17, wherein: The artificial intelligence data service request includes the artificial intelligence reasoning processing request; the execution network element includes a second data plane function network element and a second data storage function network element; The data service management function network element is used to generate an inference task for performing artificial intelligence reasoning, and control the second data plane function network element and the second data storage function network element to perform reasoning processing according to the inference task.

24. The system of claim 23, wherein: The reasoning task includes a second data collection task and a second data processing task; The data service management function network element is used to assign the second data processing task to the second data plane function network element, and issue the second data collection task to the second data storage function network element; The second data plane functional network element is used to use the artificial intelligence model stored in the second data storage functional network element to perform reasoning processing on the sample data to be inferred, and obtain a reasoning result; The second data storage functional network element is used to return the artificial intelligence model to the second data plane functional network element upon receiving a model request sent by the second data plane functional network element.

25. The system of claim 24, wherein: The data service management function network element is used to send the address of the second data storage function network element to the service demand device, so that the service demand device sends the sample data to be inferred to the second data plane function network element.

26. The system of claim 24, wherein: The execution result includes reasoning result information; The second data plane functional network element is used to return the reasoning result information to the service demand device.

27. The system of claim 17, wherein: The data service management function network element is used to send a service discovery request message to the network registration center according to the artificial intelligence data service request; receive the service discovery response message returned by the network registration center, and determine the execution network element from the artificial intelligence data service network element carried by the service discovery response message.

28. A communication system comprising: A data service system as claimed in any one of claims 15 to 27.

29. A computer-readable storage medium storing computer instructions, wherein the computer instructions are executed by a processor to perform the method according to any one of claims 1 to 14.

30. A computer program product, wherein the computer program product stores computer instructions, wherein the computer instructions are executed by a processor to perform the method according to any one of claims 1 to 14.

Images