Method, device and equipment for providing service based on artificial intelligence AI and storage medium

Abstract

The present disclosure proposes a method, apparatus and device for providing a service based on AI, and a storage medium, the method comprising: receiving a first request message sent by a mobility management function AMF network element, the first request message indicating an AI service requested by a terminal device; determining an execution task for realizing the AI service based on the first request message, and dividing the execution task into a plurality of sub-tasks; and respectively issuing the plurality of sub-tasks to a plurality of second AI network function network elements for executing the tasks, and receiving sub-task execution results sent by the second AI network function network elements. According to the method disclosed by the invention, the requirement of personalized AI service is met, the provided AI service result is more accurate, the execution efficiency is higher, and the problem of fragmentation of an AI application scene is avoided.

Description

Method, device, equipment and storage medium for providing services based on artificial intelligence (AI) Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular to methods, devices, equipment, and storage media for providing services based on AI. Background Art

[0002] Because AI (Artificial Intelligence) technology can help networks achieve a higher level of autonomy and reduce costs and increase efficiency, networks often use AI technology to provide AI services.

[0003] Among the related technologies, the main approach is to provide AI services based on AI technology by optimizing and transforming the traditional network architecture.

[0004] However, the related art methods provide AI services by optimizing and transforming traditional network architectures, lacking a unified technical framework for providing AI services. This has led to fragmented network AI application scenarios and reduced the AI ​​service provision process to a simple overlay on existing network processes. The lack of a universal AI service provision process makes it impossible to meet personalized AI service needs. Furthermore, the related art methods for providing AI services lack a fine-grained division of AI functions and cannot implement multi-tasking in parallel.

[0005] Summary of the Invention

[0006] The present disclosure proposes a method, apparatus, device, and storage medium for providing AI-based services to address the technical issues of related technical methods, such as fragmented AI application scenarios, inability to meet personalized AI service needs, insufficiently granular division of AI functions, and inability to achieve multi-tasking parallel work.

[0007] In a first aspect, an embodiment of the present disclosure provides a method for providing an AI-based service, the method being executed by a second AI network function network element for decision-making, including:

[0008] Receive a first request message sent by a mobility management function (AMF) network element, where the first request message indicates an AI service requested by a terminal device;

[0009] Determining an execution task for implementing the AI ​​service based on the first request message, and dividing the execution task into multiple subtasks;

[0010] The multiple subtasks are respectively issued to multiple second AI network function network elements for executing the tasks, and subtask execution results sent by each second AI network function network element are received.

[0011] In the present disclosure, a method for providing services based on AI is provided. It is not a simple superposition on the existing network process, but a complete and universal AI service provision process. Based on the method of the present disclosure, the AI ​​service requested by the terminal device can be accurately provided, thereby meeting the needs of personalized AI services. In addition, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, the classification management of the AI ​​service is realized, and the fine-grained division of the AI ​​function is realized, which will make the subsequent AI service results more accurate. At the same time, in the method of the present disclosure, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. In addition, in the present disclosure, the first AI network function network element and multiple second AI network function network elements and other network elements in the core network can constitute a unified technical framework for providing AI services, thereby avoiding the problem of fragmentation of AI application scenarios.

[0012] Optionally, the method further includes:

[0013] Determine a final service execution result corresponding to the AI ​​service based on the execution results of the multiple subtasks;

[0014] Send the final service execution result corresponding to the AI ​​service to the AMF network element.

[0015] Optionally, the first request message includes at least one of the following:

[0016] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0017] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0018] User information of the terminal device.

[0019] Optionally, dividing the execution task into multiple subtasks includes:

[0020] Determine the AI ​​service type corresponding to the AI ​​service;

[0021] Determine the AI ​​algorithms required to implement the AI ​​services;

[0022] The execution task is divided into a plurality of subtasks based on the AI ​​service type and the AI ​​algorithm.

[0023] Optionally, different second AI network function network elements are used to perform subtasks of different task types;

[0024] The sending of the plurality of subtasks to a plurality of second AI network function network elements for executing the tasks respectively includes:

[0025] Based on the task types corresponding to the multiple subtasks, the multiple subtasks are sent to the corresponding second AI network function network element.

[0026] Optionally, the method further includes:

[0027] Send the user information of the terminal device to the second AI network function network element.

[0028] Optionally, the method further includes:

[0029] Send a first response message to the multiple second AI network function network elements, where the first response message is used to indicate whether the first AI network function network element successfully receives the subtask execution result.

[0030] In a second aspect, an embodiment of the present disclosure provides a method for providing an AI-based service, which is executed by a second AI network function network element that performs a task, including:

[0031] receiving a subtask sent by a first AI network function network element for decision-making;

[0032] Executing the subtask to obtain a subtask execution result;

[0033] Send the subtask execution result to the first AI network function network element.

[0034] Optionally, executing the subtask to obtain a subtask execution result includes:

[0035] Acquiring data required for executing the subtask from the network function NF network element based on the subtask;

[0036] The subtask is executed based on the data to obtain a corresponding subtask execution result.

[0037] Optionally, the NF network element includes at least one of the following:

[0038] User Data Register UDR network element;

[0039] Unstructured data storage function UDSF network element.

[0040] Optionally, the second AI network function network element and other second AI network function network elements perform the subtask in parallel.

[0041] Optionally, the method further includes:

[0042] Obtain user information of a terminal device sent by the first AI network function network element, where the terminal device is a device requesting an AI service.

[0043] Optionally, the acquiring, based on the subtask, from the NF network element, data required for executing the subtask includes:

[0044] Based on the subtask, the data required to execute the subtask is obtained from the NF network element from the data corresponding to the terminal device.

[0045] Optionally, the second AI network function network element includes at least one AI model, and the AI ​​model is used to output the subtask execution result based on the data.

[0046] Optionally, the method further includes:

[0047] The AI ​​model is trained based on local data.

[0048] Optionally, the method further includes:

[0049] Receive a first response message sent by the first AI network function network element, where the first response message is used to indicate whether the first AI network function network element successfully receives the subtask execution result.

[0050] In a third aspect, an embodiment of the present disclosure provides a method for providing services based on AI, which is executed by an AMF network element, including:

[0051] receiving a second request message sent by the terminal device, where the second request message indicates an AI service requested by the terminal device;

[0052] Sending a first request message to the first AI network function network element, where the first request message indicates an AI service requested by the terminal device;

[0053] receiving a final service execution result corresponding to the AI ​​service sent by the first AI network function network element;

[0054] Send the final service execution result corresponding to the AI ​​service to the terminal device.

[0055] Optionally, the first request message and the second request message both include at least one of the following:

[0056] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0057] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0058] User information of the terminal device.

[0059] Optionally, the method further includes:

[0060] Receive a second response message sent by the terminal device, where the second response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0061] Optionally, the method further includes:

[0062] Receive a feedback result sent by the terminal device, where the feedback result is used to provide feedback on the satisfaction level of the final service execution result.

[0063] In a fourth aspect, an embodiment of the present disclosure provides a method for providing a service based on AI, which is executed by a terminal device and includes:

[0064] Send a second request message to the AMF network element, where the second request message indicates the AI ​​service requested by the terminal device;

[0065] Receive the final service execution result corresponding to the AI ​​service sent by the AMF network element.

[0066] Optionally, the second request message includes at least one of the following:

[0067] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0068] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0069] User information of the terminal device.

[0070] Optionally, the method further includes:

[0071] A second response message is sent to the AMF network element, where the second response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0072] Optionally, the method further includes:

[0073] Send a feedback result to the AMF network element, where the feedback result is used to provide feedback on the satisfaction level with the final service execution result.

[0074] In a fifth aspect, an embodiment of the present disclosure provides a communication device, including:

[0075] A transceiver module, configured to receive a first request message sent by a mobility management function (AMF) network element, where the first request message indicates an AI service requested by a terminal device;

[0076] a processing module, configured to determine an execution task for implementing the AI ​​service based on the first request message, and divide the execution task into multiple subtasks;

[0077] The transceiver module is further configured to respectively send the multiple subtasks to multiple second AI network function network elements for executing the tasks, and receive subtask execution results sent by each second AI network function network element.

[0078] In a sixth aspect, an embodiment of the present disclosure provides a communication device, which is configured in a terminal device and includes:

[0079] a transceiver module, configured to receive a subtask sent by a first AI network function network element for decision-making;

[0080] A processing module, configured to execute the subtask to obtain a subtask execution result;

[0081] The transceiver module is further configured to send the subtask execution result to the first AI network function network element.

[0082] In a seventh aspect, an embodiment of the present disclosure provides a communication device, including:

[0083] a transceiver module, configured to receive a second request message sent by a terminal device, where the second request message indicates an AI service requested by the terminal device;

[0084] The transceiver module is further configured to send a first request message to the first AI network function network element, where the first request message indicates an AI service requested by the terminal device;

[0085] The transceiver module is further configured to receive a final service execution result corresponding to the AI ​​service sent by the first AI network function network element;

[0086] The transceiver module is further configured to send the final service execution result corresponding to the AI ​​service to the terminal device.

[0087] In an eighth aspect, an embodiment of the present disclosure provides a communication apparatus, which is configured in a terminal device and includes:

[0088] A transceiver module, configured to send a second request message to the AMF network element, where the second request message indicates the AI ​​service requested by the terminal device;

[0089] The transceiver module is used to receive the final service execution result corresponding to the AI ​​service sent by the AMF network element.

[0090] In a ninth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor. When the processor calls a computer program in a memory, it executes the method described in the first aspect above.

[0091] In a tenth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor. When the processor calls a computer program in a memory, it executes the method described in the second aspect above.

[0092] In an eleventh aspect, an embodiment of the present disclosure provides a communication device, which includes a processor. When the processor calls a computer program in a memory, the method described in the third aspect is executed.

[0093] In a twelfth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor. When the processor calls a computer program in a memory, it executes the method described in the fourth aspect above.

[0094] In the thirteenth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and a memory, in which a computer program is stored; the processor executes the computer program stored in the memory so that the communication device executes the method described in the first aspect above.

[0095] In the fourteenth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and a memory, in which a computer program is stored; the processor executes the computer program stored in the memory so that the communication device executes the method described in the second aspect above.

[0096] In the fifteenth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and a memory, in which a computer program is stored; the processor executes the computer program stored in the memory so that the communication device executes the method described in the third aspect above.

[0097] In the sixteenth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and a memory, in which a computer program is stored; the processor executes the computer program stored in the memory so that the communication device executes the method described in the fourth aspect above.

[0098] In the seventeenth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to run the code instructions to enable the device to execute the method described in the first aspect above.

[0099] In the eighteenth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to run the code instructions to enable the device to execute the method described in the second aspect above.

[0100] In the nineteenth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to run the code instructions to enable the device to execute the method described in the third aspect above.

[0101] In the twentieth aspect, an embodiment of the present disclosure provides a communication device, which includes a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to run the code instructions to enable the device to execute the method described in the fourth aspect above.

[0102] In aspect 21, an embodiment of the present disclosure provides a communication system, which includes the communication device described in aspect 5 to the communication device described in aspect 8, or the system includes the communication device described in aspect 9 to the communication device described in aspect 12, or the system includes the communication device described in aspect 13 to the communication device described in aspect 16, or the system includes the communication device described in aspect 17 to the communication device described in aspect 20.

[0103] In aspect 22, an embodiment of the present invention provides a computer-readable storage medium for storing instructions for the above-mentioned network device and / or the above-mentioned terminal device. When the instructions are executed, the network device executes the method described in aspect 1, and / or the terminal device executes the method described in aspect 2, and / or the terminal device executes the method described in aspect 3, and / or the terminal device executes the method described in aspect 4.

[0104] In a twenty-third aspect, the present disclosure further provides a computer program product comprising a computer program, which, when executed on a computer, enables the computer to execute the method described in any one of the first to fourth aspects above.

[0105] In the twenty-fourth aspect, the present disclosure provides a chip system, which includes at least one processor and an interface, for supporting a network device to implement the functions involved in the method described in the first aspect, and / or, supporting a terminal device to implement the functions involved in the method described in the second aspect, and / or, supporting a terminal device to implement the functions involved in the method described in the third aspect, and / or, supporting a terminal device to implement the functions involved in the method described in the fourth aspect, for example, determining or processing at least one of the data and information involved in the above methods. In one possible design, the chip system also includes a memory, which is used to store computer programs and data necessary for the source auxiliary node. The chip system can be composed of chips, or it can include chips and other discrete devices.

[0106] In a twenty-fifth aspect, the present disclosure provides a computer program which, when executed on a computer, enables the computer to execute the method described in any one of the first to fourth aspects above.

[0107] In a twenty-sixth aspect, the present disclosure provides a communication system, including:

[0108] A first network element is configured to receive a second request message sent by a terminal device, where the second request message indicates an AI service requested by the terminal device, and send a first request message, where the first request message indicates the AI ​​service requested by the terminal device;

[0109] A second network element is configured to receive the first request message, determine an execution task for implementing the AI ​​service based on the first request message, divide the execution task into multiple subtasks, and issue the multiple subtasks;

[0110] at least one third network element, configured to receive the issued subtask, execute the subtask to obtain a subtask execution result; and send the subtask execution result;

[0111] The second network element is further used to receive the subtask execution results of each subtask, and determine the final service execution result corresponding to the AI ​​service based on the multiple subtask execution results; and send the final service execution result corresponding to the AI ​​service to the AMF network element;

[0112] The first network element is further used to receive the final service execution result corresponding to the AI ​​service, and send the final service execution result corresponding to the AI ​​service to the terminal device. BRIEF DESCRIPTION OF THE DRAWINGS

[0113] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0114] FIG1a is a schematic diagram of the architecture of a communication system provided by an embodiment of the present disclosure;

[0115] Figure 1b is a schematic diagram of a core network architecture provided by an embodiment of the present disclosure

[0116] FIG2 is a flow chart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0117] FIG3 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0118] FIG4 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0119] FIG5 is a flow chart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0120] FIG6 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0121] FIG7 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0122] FIG8 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0123] FIG9 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0124] FIG10 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0125] FIG11 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0126] FIG12 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0127] FIG13 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0128] FIG14 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0129] FIG15 is a flowchart of a method for providing services based on AI according to another embodiment of the present disclosure;

[0130] FIG16 is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure;

[0131] FIG17 is a schematic structural diagram of a communication device provided by another embodiment of the present disclosure;

[0132] FIG18 is a schematic structural diagram of a communication device provided by another embodiment of the present disclosure;

[0133] FIG19a is a schematic structural diagram of a communication device provided by another embodiment of the present disclosure;

[0134] FIG19b is a schematic structural diagram of a communication system provided by an embodiment of the present disclosure;

[0135] FIG20 is a block diagram of a communication device provided by one embodiment of the present disclosure;

[0136] FIG21 is a schematic structural diagram of a chip provided in accordance with an embodiment of the present disclosure. DETAILED DESCRIPTION

[0137] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring 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 possible implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0138] The terms used in the embodiments of the present disclosure are for the purpose of describing specific embodiments only and are not intended to limit the embodiments of the present disclosure. The singular forms "a," "an," and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0139] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the embodiments of the present disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the embodiments of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0140] The embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be understood as limiting the present disclosure.

[0141] To facilitate understanding, the terms involved in this application are first introduced.

[0142] 1. Artificial Intelligence (AI)

[0143] AI is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

[0144] 2. Access and Mobility Management Function (AMF) network element

[0145] The AMF network element performs registration, connection, reachability, and mobility management. It provides a session management message transmission channel between terminal devices and SMF network elements, and provides authentication and authorization functions for terminal device access. It is the access point between terminal devices and the wireless core network control plane.

[0146] 3. Application Function (AF) Network Element

[0147] AF network element, a network element that provides applications. The authorization server can be deployed as an AF.

[0148] In order to better understand the method for determining the side link duration disclosed in an embodiment of the present application, the communication system to which the embodiment of the present application is applicable is first described below.

[0149] Please refer to Figure 1a, which is a schematic diagram of the architecture of a communication system provided in an embodiment of the present disclosure. The communication system may include, but is not limited to, a core network device and a terminal device. The number and configuration of devices shown in Figure 1a are for example purposes only and do not constitute a limitation on the embodiments of the present disclosure. In actual applications, two or more core network devices and two or more terminal devices may be included. The communication system shown in Figure 1a includes, for example, a core network device 11 and a terminal device 12.

[0150] It should be noted that the technical solutions of the embodiments of the present disclosure can be applied to various communication systems, such as long-term evolution (LTE) systems, fifth-generation (5G) mobile communication systems, 5G new radio (NR) systems, or other future new mobile communication systems.

[0151] The core network device 11 in the embodiment of the present disclosure is a device deployed in the core network. The function of the core network device 11 is mainly to provide user connection, user management, and service bearer, and to provide an interface to the external network as a bearer network. For example, the core network device in the 5G NR system may include an Access and Mobility Management Function (AMF) network element, a User Plane Function (UPF) network element, and a Session Management Function (SMF) network element.

[0152] Exemplarily, the core network device 11 in the embodiment of the present application may include a location management function network element. Optionally, the location management function network element includes a location server (location server), which may be implemented as any one of the following: LMF (Location Management Function, location management network element), E-SMLC (Enhanced Serving Mobile Location Centre, enhanced serving mobile location center), SUPL (Secure User Plane Location, secure user plane location), SUPL SLP (SUPL Location Platform, secure user plane location platform).

[0153] The terminal device 12 in the embodiment of the present disclosure can be an entity on the user side for receiving or transmitting signals, such as a mobile phone. The terminal device can also be called a terminal device (terminal), user equipment (UE), mobile station (MS), mobile terminal device (MT), etc. The terminal device can be a car with communication function, a smart car, a mobile phone, a wearable device, a tablet computer (Pad), a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control (industrial control), a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in smart grid (smart grid), a wireless terminal device in transportation safety (transportation safety), a wireless terminal device in smart city (smart city), a wireless terminal device in smart home (smart home), etc. The embodiment of the present disclosure does not limit the specific technology and specific device form adopted by the terminal device.

[0154] Among them, the core network device 11 and the terminal device 12 can communicate through the base station.

[0155] Also, please refer to Figure 1b, which is a schematic diagram of a core network architecture provided by an embodiment of the present disclosure. Figure 1b includes network elements included in the core network architecture and interfaces used for communication between the network elements.

[0156] The core network architecture abstracts the functions of network elements into multiple services. Compared with the traditional core network architecture, the core network architecture of Figure 1b adds N network elements AI0, AI1, AI2...AIN, among which AI0 is a decision-making network element used to assign AI tasks to AI1, AI2...AIN network elements, and AI1, AI2...AIN network elements are all network elements for providing AI functions. Among them, AI0 can be the first AI network function network element for decision-making mentioned later in this embodiment, and AI1, AI2...AIN network elements can be the second AI network function network elements for executing tasks mentioned later in this embodiment. In addition, the AI0, AI1, AI2...AIN network elements can communicate with other network elements in the network (such as AMF network elements, SMF network elements, etc.).

[0157] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution provided by the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution provided by the embodiment of the present disclosure is also applicable to similar technical problems.

[0158] In addition, it should be noted that the method disclosed herein is specifically implemented on the basis of completing the following operations:

[0159] (1) The terminal device has completed the initial registration process and is connected to the network.

[0160] (2) The AI ​​network function network elements (i.e., AI0, AI1, AI2, ... AIN network elements in Figure 1b) have completed registration at the NRF (Network Repository Function) function and can be accessed and work normally in the core network architecture.

[0161] (3) The core network has authenticated each AI network function to ensure its secure access.

[0162] (4) AI0 and AI1 / ... / AIN network elements trust each other and transmit real communication information.

[0163] (5) Each time AI0 allocates tasks, each AI1 / ... / AIN network element completes the total task in parallel, each taking responsibility for a part of the task.

[0164] (6) There is a certain correlation between the tasks received by the AI1 / ... / AIN network elements, and they belong to the same category. For example, the AI1 / ... / AIN network elements receive image segmentation tasks, entity labeling tasks, object detection tasks, and face recognition tasks respectively. Among them, the image segmentation task, entity labeling task, object detection task, and face recognition task all belong to the category of "surveillance video stream analysis."

[0165] The following describes in detail the method, apparatus, device, and storage medium for providing AI-based services provided by the embodiments of the present disclosure with reference to the accompanying drawings.

[0166] FIG2 is a flow chart of a method for providing services based on AI according to an embodiment of the present disclosure. The method is performed by a first AI network function element for decision-making. As shown in FIG2 , the method for providing services based on AI may include the following steps:

[0167] Step 201: Receive the first request message sent by the AMF network element.

[0168] In one embodiment of the present disclosure, the first request message indicates an AI service requested by the terminal device.

[0169] In one embodiment of the present disclosure, the first request message may include at least one of the following:

[0170] The AI ​​service type corresponding to the AI ​​service requested by the terminal device (AI Service Type), such as CV (Computer Vision), NLP (Natural Language Processing), etc.

[0171] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device. The AI ​​service ID is used to uniquely identify the AI ​​service;

[0172] User information of the terminal device.

[0173] And, in one embodiment of the present disclosure, the first request message may be sent by the AMF network element to the first AI network function network element after receiving the second request message sent by the terminal device through the base station (such as transparent transmission). The first request message may be a CreateAI0Context_Request message, and the second request message may be an AI Service Establishment Request message.

[0174] Step 202: Determine an execution task for implementing the AI ​​service based on the first request message, and divide the execution task into multiple subtasks.

[0175] In one embodiment of the present disclosure, after receiving the first request message, the first AI network function element can determine the AI ​​service specifically requested by the first request message based on the AI ​​service ID and AI service type, and determine the execution task for implementing the AI ​​service. It then analyzes the AI ​​algorithm required to implement the AI ​​service, specifically which AI algorithms are required to execute the execution task. Finally, based on the AI ​​service type and the different AI algorithms used in different parts of the execution process, the execution task is divided into multiple subtasks.

[0176] For example, assuming that the first AI network function network element determines that the execution task for implementing the AI ​​service is: monitoring video stream analysis, the execution task: monitoring video stream analysis can be divided into subtask 1: image segmentation, subtask 2: entity labeling, subtask 3: target detection and subtask 4: face recognition tasks.

[0177] From this, it can be seen that the execution tasks corresponding to the AI ​​service will be divided into multiple subtasks in this disclosure, thereby realizing the classified management of the AI ​​service and the fine-grained division of the AI ​​functions, which will make the subsequent AI service results more accurate.

[0178] Step 203: Send the multiple subtasks to multiple second AI network function network elements for executing the tasks, and receive the subtask execution results sent by each second AI network function network element.

[0179] In one embodiment of the present disclosure, different second AI network function elements are used to perform subtasks of different task types. For example, second AI network function element #1 may be used to perform image classification tasks, second AI network function element #2 may be used to perform object detection tasks, and third AI network function element #3 may be used to perform object recognition and localization tasks.

[0180] Based on this, in one embodiment of the present disclosure, the first AI network function network element may specifically send the multiple subtasks to the corresponding second AI network function network element based on the task types corresponding to the multiple subtasks.

[0181] For example, if the multiple subtasks are subtask 1: image segmentation, subtask 2: entity labeling, and subtask 3: target detection, subtask 1 can be sent to the second AI network function network element #1 for performing image classification tasks, subtask 2 can be sent to the second AI network function network element #3 for performing object recognition and positioning tasks, and subtask 3 can be sent to the second AI network function network element #2 for performing target detection tasks.

[0182] Furthermore, when each second AI network function element receives a subtask, it can execute the subtask to obtain a subtask execution result (for example, the subtask execution result corresponding to subtask 1 can be a segmentation result, and the subtask execution result corresponding to subtask 2 can be a labeled sample), and send the subtask execution result to the first AI network function element. The specific execution of the subtask by the second AI network function element will be described in detail in subsequent embodiments corresponding to the second AI network function element.

[0183] It should be noted that in one embodiment of the present disclosure, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency.

[0184] In addition, in one embodiment of the present disclosure, after the first AI network function network element receives the execution results of each subtask, it can provide AI services to the terminal device through the AMF network element based on the subtask execution results.

[0185] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0186] FIG3 is a flow chart of a method for providing services based on AI according to an embodiment of the present disclosure. The method is performed by a first AI network function element for decision-making. As shown in FIG3 , the method for providing services based on AI may include the following steps:

[0187] Step 301: Receive the first request message sent by the AMF network element.

[0188] Step 302: Determine an execution task for implementing the AI ​​service based on the first request message, and divide the execution task into multiple subtasks.

[0189] Step 303: Send the multiple subtasks to multiple second AI network function network elements for executing the tasks, and receive the subtask execution results sent by each second AI network function network element.

[0190] Step 304: Determine the final service execution result corresponding to the AI ​​service based on the execution results of the multiple subtasks.

[0191] In one embodiment of the present disclosure, the first AI network function network element can obtain the final service execution result by summarizing the execution results of each subtask.

[0192] Step 305: Send the final service execution result corresponding to the AI ​​service to the AMF network element.

[0193] Among them, the final service execution result corresponding to the AI ​​service is sent to the AMF network element so that the AMF network element can provide the final service execution result to the terminal device, thereby realizing the provision of AI service to the terminal device.

[0194] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0195] FIG4 is a flow chart of a method for providing services based on AI according to an embodiment of the present disclosure. The method is performed by a first AI network function element for decision-making. As shown in FIG4 , the method for providing services based on AI may include the following steps:

[0196] Step 401: Receive the first request message sent by the AMF network element.

[0197] Step 402: Determine an execution task for implementing the AI ​​service based on the first request message, and divide the execution task into multiple subtasks.

[0198] Step 403: Send user information of the terminal device to the second AI network function network element.

[0199] In one embodiment of the present disclosure, a first AI network function element specifically sends user information of a terminal device (i.e., user information of the terminal device requesting an AI service) included in a first request message to a second AI network function element. This information enables the second AI network function element to execute the received subtask based on the user information. Specifically, when executing a subtask, the second AI network function element typically needs to first obtain data required for executing the subtask from a network function (NF) element, so that it can execute the subtask based on the data. The data required for executing the subtask should be data corresponding to the terminal device requesting the AI ​​service. Therefore, the first AI network function element needs to send the user information of the terminal device requesting the AI ​​service to the second AI network function element, so that the second AI network function element can obtain the data required for executing the subtask from the NF element based on the user information of the terminal device requesting the AI ​​service, thereby enabling the second AI network function element to successfully execute the subtask.

[0200] Step 404: Send the multiple subtasks to multiple second AI network function network elements for executing the tasks, and receive the subtask execution results sent by each second AI network function network element.

[0201] For a detailed description of steps 401 , 403 and 404 , please refer to the above embodiment description, which will not be elaborated herein in detail.

[0202] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0203] FIG5 is a flow chart of a method for providing services based on AI according to an embodiment of the present disclosure. The method is performed by a first AI network function element for decision-making. As shown in FIG5 , the method for providing services based on AI may include the following steps:

[0204] Step 501: Receive the first request message sent by the AMF network element.

[0205] Step 502: Determine an execution task for implementing the AI ​​service based on the first request message, and divide the execution task into multiple subtasks.

[0206] Step 503: Send the multiple subtasks to multiple second AI network function network elements for executing the tasks, and receive the subtask execution results sent by each second AI network function network element.

[0207] Step 504: Send a first response message to the multiple second AI network function network elements. The response message is used to indicate whether the first AI network function network element has successfully received the subtask execution result.

[0208] In one embodiment of the present disclosure, if the first response message indicates that the first AI network function failed to successfully receive the subtask execution result, the second AI network function element will resend the subtask execution result to the first AI network function element. This prevents the failure of transmitting the subtask execution result and ensures the successful provision of the AI ​​service.

[0209] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0210] FIG6 is a flow chart of a method for providing an AI-based service according to an embodiment of the present disclosure. The method is performed by a second AI network function element for performing a task. As shown in FIG6 , the method for providing an AI-based service may include the following steps:

[0211] Step 601: Receive a subtask sent by a first AI network function network element for decision-making.

[0212] In one embodiment of the present disclosure, the second AI network function network element may receive user information of a terminal device requesting an AI service sent by the first AI network function network element while receiving the subtask sent by the first AI network function network element.

[0213] Step 602: Execute the subtask to obtain the subtask execution result.

[0214] In one embodiment of the present disclosure, the method for the second AI network function network element to perform a subtask may include the following steps:

[0215] The first step is to obtain the data required to execute the subtask from the NF network element based on the subtask.

[0216] In one embodiment of the present disclosure, the NF network element may be a UDR (User Data Repository) network element and / or a UDSF (Unstructured Data Storage Network Function) network element, wherein the UDR network element and the UDSF network element respectively store structured data sets and unstructured data sets. Furthermore, the data stored in the UDR network element and the UDSF network element primarily originate from data provided by a terminal device during registration, or data corresponding to the requested AI service provided synchronously to the NF network element when the terminal device requests the AI ​​service.

[0217] Furthermore, in one embodiment of the present disclosure, the method by which the second AI network function element obtains data required for executing a subtask from the NF element may include at least one of the following:

[0218] Method 1: The second AI network function network element first determines, based on the received subtask, the type of data required for the second AI network function network element to perform the subtask. Then, the second AI network function network element sends a data request message to the NF network element. The data request message includes user information of the terminal device requesting the AI ​​service and the type of data required for the second AI network function network element to perform the subtask. In this case, the NF network element may determine the data corresponding to the terminal device requesting the AI ​​service based on the user information of the terminal device requesting the AI ​​service, and select the data used to perform the subtask from the data corresponding to the terminal device requesting the AI ​​service based on the type of data required for the second AI network function network element to perform the subtask, and then send the data to the second AI network function network element.

[0219] Method 2: The second AI network function network element directly sends a data request message to the NF network element. The data request message includes the subtask to be performed by the second AI network function network element and the user information of the terminal device requesting the AI ​​service. The NF network element can then directly determine the data required for the second AI network function network element to perform the subtask based on the subtask to be performed by the second AI network function network element and the user information of the terminal device requesting the AI ​​service, and send the data to the second AI network function network element.

[0220] The second step is to execute the subtask based on the acquired data to obtain the corresponding subtask execution result.

[0221] Specifically, in one embodiment of the present disclosure, the second AI network function element includes at least one AI model, where different AI models are used to execute different subtasks. Furthermore, after acquiring the data required to execute a subtask, the second AI network function element can select an AI model suitable for the subtask to be executed and use the acquired data as input to the selected AI model, so that the AI ​​model outputs the subtask execution result.

[0222] As can be seen from the above, the second AI network function element can determine the subtask execution result by executing the first and second steps. Furthermore, it should be noted that in one embodiment of the present disclosure, different second AI network function elements execute subtasks in parallel, thereby improving execution efficiency.

[0223] Step 603: Send the subtask execution result to the first AI network function network element.

[0224] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0225] FIG7 is a flow chart of a method for providing an AI-based service according to an embodiment of the present disclosure. The method is performed by a second AI network function element for performing a task. As shown in FIG7 , the method for providing an AI-based service may include the following steps:

[0226] Step 701: Receive a subtask sent by a first AI network function network element for decision-making.

[0227] Step 702: Obtain user information of a terminal device sent by the first AI network function network element, where the terminal device is a device requesting an AI service.

[0228] Step 703: Execute the subtask to obtain the subtask execution result.

[0229] Step 704: Send the subtask execution result to the first AI network function network element.

[0230] The detailed explanation of steps 701-704 can be referred to the description of the above embodiment, and will not be repeated here in the embodiment of the present disclosure.

[0231] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0232] FIG8 is a flow chart of a method for providing an AI-based service according to an embodiment of the present disclosure. The method is performed by a second AI network function element for performing a task. As shown in FIG8 , the method for providing an AI-based service may include the following steps:

[0233] Step 801: Receive a subtask sent by a first AI network function network element for decision-making.

[0234] Step 802: Execute the subtask to obtain the subtask execution result.

[0235] Step 803: Send the subtask execution result to the first AI network function network element.

[0236] The detailed explanation of steps 801-803 can be referred to the above embodiment description, and the embodiment of the present disclosure will not be repeated here.

[0237] Step 804: Receive a first response message sent by the first AI network function network element. The first response message is used to indicate whether the first AI network function network element has successfully received the subtask execution result.

[0238] In one embodiment of the present disclosure, in response to the first response message indicating that the first AI network function network element successfully received the subtask execution result, the second AI network function network element does not need to send the subtask execution result to the first AI network function network element.

[0239] In another embodiment of the present disclosure, in response to the first response message indicating that the first AI network function network element has not successfully received the subtask execution result, the second AI network function network element needs to resend the subtask execution result to the first AI network function network element.

[0240] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0241] FIG9 is a flow chart of a method for providing an AI-based service according to an embodiment of the present disclosure. The method is performed by a second AI network function element for performing a task. As shown in FIG9 , the method for providing an AI-based service may include the following steps:

[0242] Step 901: Train the AI ​​model based on local data.

[0243] In one embodiment of the present disclosure, each second AI network function element can use local data to train the AI ​​model separately. Each AI network function element can select an appropriate parameter optimization method (SGD, Adam, etc.) to train the AI ​​model according to its own situation.

[0244] For example, in one embodiment of the present disclosure, the second AI network function network element for performing image classification tasks can use the cifar-10 image dataset and the VGGNet neural network to train the AI ​​model; the second AI network function network element for performing target detection tasks can use the Faster-RCNN algorithm to train the AI ​​model; the second AI network function network element for performing object recognition and positioning tasks can use the YOLO algorithm to train the AI ​​model, etc.

[0245] Furthermore, in one embodiment of the present disclosure, the second AI network function element may train the AI ​​model when the AI ​​model is initially created, or may train the AI ​​model that executes the subtask upon receiving the subtask. The present embodiment does not specifically limit the timing of AI model training.

[0246] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0247] FIG10 is a flow chart of a method for providing services based on AI according to an embodiment of the present disclosure. The method is executed by an AMF network element. As shown in FIG10 , the method for providing services based on AI may include the following steps:

[0248] Step 1001: Receive a second request message sent by a terminal device, where the second request message indicates an AI service requested by the terminal device.

[0249] The second request message may include at least one of the following:

[0250] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0251] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0252] User information of the terminal device.

[0253] For example, the second request message may be an AI Service Establishment Request message.

[0254] Step 1002: Send a first request message to the first AI network function network element, where the first request message indicates an AI service requested by the terminal device.

[0255] Step 1003: Receive the final service execution result corresponding to the AI ​​service sent by the first AI network function network element.

[0256] Step 1004: Send the final service execution result corresponding to the AI ​​service to the terminal device.

[0257] Among them, the AMF network element can transparently transmit the final service execution results to the terminal device through the base station.

[0258] Also, for a detailed description of steps 1001 - 1004 , please refer to the above embodiment description.

[0259] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0260] FIG11 is a flow chart of a method for providing an AI-based service according to an embodiment of the present disclosure. The method is executed by an AMF network element. As shown in FIG11 , the method for providing an AI-based service may include the following steps:

[0261] Step 1101: Receive a second request message sent by a terminal device, where the second request message indicates an AI service requested by the terminal device.

[0262] Step 1102: Send a first request message to the first AI network function network element, where the first request message indicates an AI service requested by the terminal device.

[0263] The first request message and the second request message each include at least one of the following:

[0264] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0265] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0266] User information of the terminal device.

[0267] Step 1103: Receive the final service execution result corresponding to the AI ​​service sent by the first AI network function network element.

[0268] Step 1104: Send the final service execution result corresponding to the AI ​​service to the terminal device.

[0269] Step 1105: Receive a second response message sent by the terminal device, where the second response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0270] Among them, in one embodiment of the present disclosure, when the second response message indicates that the terminal device has not successfully received the final service execution result corresponding to the AI ​​service, the AMF network element needs to retransmit the final service execution result corresponding to the AI ​​service to the terminal device.

[0271] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0272] FIG12 is a flow chart of a method for providing services based on AI according to an embodiment of the present disclosure. The method is performed by an AMF network element. As shown in FIG12 , the method for providing services based on AI may include the following steps:

[0273] Step 1201: Receive a second request message sent by a terminal device, where the second request message indicates an AI service requested by the terminal device.

[0274] Step 1202: Send a first request message to the first AI network function network element, where the first request message indicates an AI service requested by the terminal device.

[0275] The first request message and the second request message each include at least one of the following:

[0276] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0277] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0278] User information of the terminal device.

[0279] Step 1203: Receive the final service execution result corresponding to the AI ​​service sent by the first AI network function network element.

[0280] Step 1204: Send the final service execution result corresponding to the AI ​​service to the terminal device.

[0281] Step 1205: Receive the feedback result sent by the terminal device, where the feedback result is used to provide feedback on the satisfaction level with the final service execution result.

[0282] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0283] FIG13 is a flow chart of a method for providing services based on AI according to an embodiment of the present disclosure. The method is executed by a terminal device. As shown in FIG13 , the method for providing services based on AI may include the following steps:

[0284] Step 1301: Send a second request message to the AMF network element, where the second request message indicates the AI ​​service requested by the terminal device.

[0285] Step 1302: Receive the final service execution result corresponding to the AI ​​service sent by the AMF network element.

[0286] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0287] FIG14 is a flow chart of a method for providing services based on AI according to an embodiment of the present disclosure. The method is executed by a terminal device. As shown in FIG14 , the method for providing services based on AI may include the following steps:

[0288] Step 1401: Send a second request message to the AMF network element, where the second request message indicates the AI ​​service requested by the terminal device.

[0289] Step 1402: Receive the final service execution result corresponding to the AI ​​service sent by the AMF network element.

[0290] Step 1403: Send a second response message to the AMF network element, where the second response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0291] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0292] FIG15 is a flow chart of a method for providing services based on AI according to an embodiment of the present disclosure. The method is executed by a terminal device. As shown in FIG15 , the method for providing services based on AI may include the following steps:

[0293] Step 1501: Send a second request message to the AMF network element, where the second request message indicates the AI ​​service requested by the terminal device.

[0294] Step 1502: Receive the final service execution result corresponding to the AI ​​service sent by the AMF network element.

[0295] Step 1503: Send a feedback result to the AMF network element, where the feedback result is used to provide feedback on the satisfaction level with the final service execution result.

[0296] In one embodiment of the present disclosure, the feedback result may be determined based on the user's rating.

[0297] In summary, in the AI-based service provision method provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF network element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then distributes each of the multiple subtasks to multiple second AI network function elements used for task execution, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, thereby making the subsequent AI service results more accurate. Furthermore, in the disclosed method, different second AI network function elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the disclosed method, the first AI network function element, multiple second AI network function elements, and other elements in the core network can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0298] FIG16 is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure. As shown in FIG16 , the device may include:

[0299] A transceiver module, configured to receive a first request message sent by a mobility management function (AMF) network element, where the first request message indicates an AI service requested by a terminal device;

[0300] a processing module, configured to determine an execution task for implementing the AI ​​service based on the first request message, and divide the execution task into multiple subtasks;

[0301] The transceiver module is further configured to respectively send the multiple subtasks to multiple second AI network function network elements for executing the tasks, and receive subtask execution results sent by each second AI network function network element.

[0302] In summary, in the communication device provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then sends each of the multiple subtasks to multiple second AI network function elements for executing the tasks, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, which will make the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0303] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:

[0304] Determine a final service execution result corresponding to the AI ​​service based on the execution results of the multiple subtasks;

[0305] Send the final service execution result corresponding to the AI ​​service to the AMF network element.

[0306] Optionally, in one embodiment of the present disclosure, the first request message includes at least one of the following:

[0307] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0308] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0309] User information of the terminal device.

[0310] Optionally, in one embodiment of the present disclosure, the processing module is further configured to:

[0311] Determine the AI ​​service type corresponding to the AI ​​service;

[0312] Determine the AI ​​algorithms required to implement the AI ​​services;

[0313] The execution task is divided into a plurality of subtasks based on the AI ​​service type and the AI ​​algorithm.

[0314] Optionally, in one embodiment of the present disclosure, different second AI network function network elements are used to perform subtasks of different task types;

[0315] The transceiver module is further used for:

[0316] Based on the task types corresponding to the multiple subtasks, the multiple subtasks are sent to the corresponding second AI network function network element.

[0317] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:

[0318] Send the user information of the terminal device to the second AI network function network element.

[0319] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:

[0320] Send a first response message to the multiple second AI network function network elements, where the first response message is used to indicate whether the first AI network function network element successfully receives the subtask execution result.

[0321] FIG17 is a schematic diagram of the structure of a communication device provided by an embodiment of the present disclosure. As shown in FIG17 , the device may include:

[0322] a transceiver module, configured to receive a subtask sent by a first AI network function network element for decision-making;

[0323] A processing module, configured to execute the subtask to obtain a subtask execution result;

[0324] The transceiver module is further configured to send the subtask execution result to the first AI network function network element.

[0325] In summary, in the communication device provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then sends each of the multiple subtasks to multiple second AI network function elements for executing the tasks, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, which will make the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0326] Optionally, in one embodiment of the present disclosure, the processing module is further configured to:

[0327] Acquiring data required for executing the subtask from the network function NF network element based on the subtask;

[0328] The subtask is executed based on the data to obtain a corresponding subtask execution result.

[0329] Optionally, in one embodiment of the present disclosure, the NF network element includes at least one of the following:

[0330] User Data Register UDR network element;

[0331] Unstructured data storage function UDSF network element.

[0332] Optionally, in one embodiment of the present disclosure, the second AI network function network element and other second AI network function network elements perform the subtask in parallel.

[0333] Optionally, in one embodiment of the present disclosure, the apparatus further includes:

[0334] Obtain user information of a terminal device sent by the first AI network function network element, where the terminal device is a device requesting an AI service.

[0335] Optionally, in one embodiment of the present disclosure, the processing module is further configured to:

[0336] Based on the subtask, the data required to execute the subtask is obtained from the NF network element from the data corresponding to the terminal device.

[0337] Optionally, in one embodiment of the present disclosure, the second AI network function network element includes at least one AI model, and the AI ​​model is used to output the subtask execution result based on the data.

[0338] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:

[0339] The AI ​​model is trained based on local data.

[0340] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:

[0341] Receive a first response message sent by the first AI network function network element, where the first response message is used to indicate whether the first AI network function network element successfully receives the subtask execution result.

[0342] FIG18 is a schematic diagram of the structure of a communication device provided by an embodiment of the present disclosure. As shown in FIG18 , the device may include:

[0343] a transceiver module, configured to receive a second request message sent by a terminal device, where the second request message indicates an AI service requested by the terminal device;

[0344] The transceiver module is further configured to send a first request message to the first AI network function network element, where the first request message indicates an AI service requested by the terminal device;

[0345] The transceiver module is further configured to receive a final service execution result corresponding to the AI ​​service sent by the first AI network function network element;

[0346] The transceiver module is further configured to send the final service execution result corresponding to the AI ​​service to the terminal device.

[0347] In summary, in the communication device provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then sends each of the multiple subtasks to multiple second AI network function elements for executing the tasks, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, which will make the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0348] Optionally, in an embodiment of the present disclosure, the first request message and the second request message each include at least one of the following:

[0349] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0350] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0351] User information of the terminal device.

[0352] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:

[0353] Receive a second response message sent by the terminal device, where the second response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0354] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:

[0355] Receive a feedback result sent by the terminal device, where the feedback result is used to provide feedback on the satisfaction level of the final service execution result.

[0356] FIG19a is a schematic structural diagram of a communication device provided by an embodiment of the present disclosure. As shown in FIG19a , the device may include:

[0357] A transceiver module, configured to send a second request message to the AMF network element, where the second request message indicates the AI ​​service requested by the terminal device;

[0358] The transceiver module is used to receive the final service execution result corresponding to the AI ​​service sent by the AMF network element.

[0359] In summary, in the communication device provided in the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then sends each of the multiple subtasks to multiple second AI network function elements for executing the tasks, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and a fine-grained division of AI functions is achieved, which will make the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0360] Optionally, in an embodiment of the present disclosure, the second request message includes at least one of the following:

[0361] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0362] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0363] User information of the terminal device.

[0364] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:

[0365] A second response message is sent to the AMF network element, where the second response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0366] Optionally, in one embodiment of the present disclosure, the apparatus is further configured to:

[0367] Send feedback results to the AMF network element, the feedback results are used to feedback the satisfaction of the final service execution results

[0368] FIG19b is a schematic diagram of the structure of a communication system provided by an embodiment of the present disclosure. As shown in FIG19b , the system may include:

[0369] The first network element (i.e., the AMF network element in the above embodiment) is configured to receive a second request message sent by a terminal device, where the second request message indicates an AI service requested by the terminal device, and send a first request message, where the first request message indicates the AI ​​service requested by the terminal device;

[0370] The second network element (i.e., the first AI network function network element for decision-making in the above embodiment) is configured to receive the first request message, determine an execution task for implementing the AI ​​service based on the first request message, divide the execution task into multiple subtasks, and issue the multiple subtasks;

[0371] At least one third network element (i.e., the second AI network function network element for executing the task in the above embodiment), configured to receive the issued subtask, execute the subtask to obtain a subtask execution result, and transmit the subtask execution result;

[0372] The second network element is further used to receive the subtask execution results of each subtask, and determine the final service execution result corresponding to the AI ​​service based on the multiple subtask execution results; and send the final service execution result corresponding to the AI ​​service to the AMF network element;

[0373] The first network element is further used to receive the final service execution result corresponding to the AI ​​service, and send the final service execution result corresponding to the AI ​​service to the terminal device.

[0374] The first network element, the second network element, and the third network element can communicate with each other.

[0375] In summary, in the communication system provided by the embodiments of the present disclosure, the first AI network function element used for decision-making receives a first request message sent by the AMF element, indicating an AI service requested by a terminal device. Subsequently, the first AI network function element determines, based on the first request message, an execution task for implementing the AI ​​service, divides the execution task into multiple subtasks, and then sends each of the multiple subtasks to multiple second AI network function elements for executing the tasks, and receives the subtask execution results sent by each second AI network function element. It can be seen that the AI ​​service provision method of the present disclosure is not a simple overlay on existing network processes, but rather a complete and universal AI service provision process. Based on the method of the present disclosure, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method of the present disclosure, by dividing the execution task corresponding to the AI ​​service requested by the terminal device into multiple subtasks, classified management of AI services is achieved, and fine-grained division of AI functions is achieved, which will make the subsequent AI service results more accurate. At the same time, in the method disclosed herein, different second AI network function network elements execute subtasks in parallel, thereby improving execution efficiency. Furthermore, in the method disclosed herein, the first AI network function network element and multiple second AI network function network elements, along with other network elements in the core network, can form a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0376] Optionally, the first request message includes at least one of the following:

[0377] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0378] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0379] User information of the terminal device.

[0380] Optionally, the second network element is further configured to:

[0381] Determine the AI ​​service type corresponding to the AI ​​service;

[0382] Determine the AI ​​algorithms required to implement the AI ​​services;

[0383] The execution task is divided into a plurality of subtasks based on the AI ​​service type and the AI ​​algorithm.

[0384] Optionally, different third network elements are used to perform subtasks of different task types;

[0385] The second network element is further configured to:

[0386] Based on the task types corresponding to the multiple subtasks, the multiple subtasks are sent to the corresponding third network element.

[0387] Optionally, the second network element is further configured to:

[0388] Send user information of the terminal device to the third network element.

[0389] Optionally, the second network element is further configured to:

[0390] A first response message is sent to the multiple third network elements, where the first response message is used to indicate whether the second network element has successfully received the subtask execution result.

[0391] Optionally, the third network element is further configured to:

[0392] Acquiring data required for executing the subtask from the network function NF network element based on the subtask;

[0393] The subtask is executed based on the data to obtain a corresponding subtask execution result.

[0394] Optionally, the NF network element includes at least one of the following:

[0395] User Data Register UDR network element;

[0396] Unstructured data storage function UDSF network element.

[0397] Optionally, the third network element is further configured to: execute the subtask in parallel with other third network elements.

[0398] Optionally, the third network element is further configured to:

[0399] Obtain user information of a terminal device sent by the second network element, where the terminal device is a device requesting an AI service.

[0400] Optionally, the third network element is further configured to:

[0401] Based on the subtask, the data required to execute the subtask is obtained from the NF network element from the data corresponding to the terminal device.

[0402] Optionally, the third network element includes at least one AI model, and the AI ​​model is used to output the subtask execution result based on the data.

[0403] Optionally, the third network element is further configured to:

[0404] The AI ​​model is trained based on local data.

[0405] Optionally, the third network element is further configured to:

[0406] Receive a first response message sent by the second network element, the first response message is used to indicate whether the second network element has successfully received the subtask execution result

[0407] Optionally, the second request message includes at least one of the following:

[0408] The AI ​​service type corresponding to the AI ​​service requested by the terminal device;

[0409] The AI ​​service ID corresponding to the AI ​​service requested by the terminal device;

[0410] User information of the terminal device.

[0411] Optionally, the first network element is further configured to:

[0412] Receive a second response message sent by the terminal device, where the second response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0413] Optionally, the first network element is further configured to:

[0414] Receive a feedback result sent by the terminal device, where the feedback result is used to provide feedback on the satisfaction level of the final service execution result.

[0415] Please refer to Figure 20, which is a schematic diagram of the structure of a communication device 2000 provided in an embodiment of the present application. Communication device 2000 can be a network device or a terminal device, or a chip, chip system, or processor that supports a network device to implement the above method, or a chip, chip system, or processor that supports a terminal device to implement the above method. This device can be used to implement the method described in the above method embodiment, and for details, please refer to the description of the above method embodiment.

[0416] The communication device 2000 may include one or more processors 2001. The processor 2001 may be a general-purpose processor or a dedicated processor. For example, it may be a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control the communication device (e.g., a base station, a baseband chip, a terminal device, a terminal device chip, a DU or CU, etc.), execute computer programs, and process computer program data.

[0417] Optionally, the communication device 2000 may further include one or more memories 2002, on which a computer program 2004 may be stored. The processor 2001 executes the computer program 2004 to cause the communication device 2000 to perform the method described in the above method embodiment. Optionally, the memory 2002 may also store data. The communication device 2000 and the memory 2002 may be provided separately or integrated together.

[0418] Optionally, the communication device 2000 may further include a transceiver 2005 and an antenna 2006. The transceiver 2005 may be referred to as a transceiver unit, a transceiver, or a transceiver circuit, and is configured to implement transceiver functions. The transceiver 2005 may include a receiver and a transmitter. The receiver may be referred to as a receiver or a receiving circuit, and is configured to implement a receiving function; the transmitter may be referred to as a transmitter or a transmitting circuit, and is configured to implement a transmitting function.

[0419] Optionally, the communication device 2000 may further include one or more interface circuits 2007. The interface circuit 2007 is configured to receive code instructions and transmit the code instructions to the processor 2001. The processor 2001 executes the code instructions to enable the communication device 2000 to execute the method described in the above method embodiment.

[0420] In one implementation, the processor 2001 may include a transceiver for implementing receiving and transmitting functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing the receiving and transmitting functions may be separate or integrated. The transceiver circuit, interface, or interface circuit may be used for reading and writing code / data, or may be used for transmitting or delivering signals.

[0421] In one implementation, processor 2001 may store a computer program 2003. Computer program 2003, when executed on processor 2001, may cause communication device 2000 to perform the method described in the above method embodiment. Computer program 2003 may be embedded in processor 2001, in which case processor 2001 may be implemented by hardware.

[0422] In one implementation, the communication device 2000 may include a circuit that can implement the functions of sending, receiving, or communicating in the aforementioned method embodiments. The processor and transceiver described in this application can be implemented on an integrated circuit (IC), an analog IC, a radio frequency integrated circuit RFIC, a mixed signal IC, an application specific integrated circuit (ASIC), a printed circuit board (PCB), an electronic device, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (nMetal-oxide-semiconductor, NMOS), P-type metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (bipolar junction transistor, BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.

[0423] The communication device described in the above embodiments may be a network device or a terminal device, but the scope of the communication device described in this application is not limited thereto, and the structure of the communication device may not be limited to FIG20. The communication device may be an independent device or may be part of a larger device. For example, the communication device may be:

[0424] (1) An independent integrated circuit (IC), or chip, or chip system or subsystem;

[0425] (2) a collection of one or more ICs, optionally including a storage component for storing data and computer programs;

[0426] (3) ASIC, such as modem;

[0427] (4) Modules that can be embedded in other devices;

[0428] (5) Receivers, terminal devices, intelligent terminal devices, cellular phones, wireless devices, handheld devices, mobile units, vehicle-mounted devices, network devices, cloud devices, artificial intelligence devices, etc.;

[0429] (6)Others, etc.

[0430] In the case where the communication device can be a chip or a chip system, please refer to the structural diagram of the chip shown in Figure 21. The chip shown in Figure 21 includes a processor 2101 and an interface 2102. The number of processors 2101 can be one or more, and the number of interfaces 2102 can be multiple.

[0431] Optionally, the chip further includes a memory 2103, which is used to store necessary computer programs and data.

[0432] Those skilled in the art will also appreciate that the various illustrative logical blocks and steps listed in the embodiments of the present application can be implemented by electronic hardware, computer software, or a combination of both. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of the present application.

[0433] The present application also provides a readable storage medium having instructions stored thereon, which implement the functions of any of the above method embodiments when executed by a computer.

[0434] The present application also provides a computer program product, which implements the functions of any of the above method embodiments when executed by a computer.

[0435] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0436] Those skilled in the art will understand that the various numerical numbers such as first and second involved in this application are only for the convenience of description and are not used to limit the scope of the embodiments of this application, and also indicate the order of precedence.

[0437] In this application, "at least one" may also be described as one or more, and "a plurality" may be two, three, four, or more, which is not limited in this application. In the embodiments of this application, for a technical feature, "first," "second," "third," "A," "B," "C," and "D" are used to distinguish technical features within the technical feature. There is no order of precedence or size between the technical features described by "first," "second," "third," "A," "B," "C," and "D."

[0438] The correspondences shown in the tables in this application can be configured or predefined. The values ​​of the information in each table are examples only and can be configured to other values, which are not limited by this application. When configuring the correspondence between information and parameters, it is not necessarily required to configure all the correspondences shown in each table. For example, in the tables in this application, the correspondences shown in certain rows may not be configured. For another example, appropriate deformation adjustments can be made based on the above tables, such as splitting, merging, etc. The names of the parameters shown in the titles of the above tables can also use other names that can be understood by the communication device, and the values ​​or representations of the parameters can also use other values ​​or representations that can be understood by the communication device. When implementing the above tables, other data structures can also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables or hash tables, etc.

[0439] The predefined in this application may be understood as defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.

[0440] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0441] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0442] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for providing services based on artificial intelligence (AI), characterized in that: The first AI network function implemented by network elements for decision-making includes: Receive a first request message sent by a mobility management function (AMF) network element, where the first request message indicates an AI service requested by a terminal device; Determining an execution task for implementing the AI ​​service based on the first request message, and dividing the execution task into multiple subtasks; The multiple subtasks are respectively issued to multiple second AI network function network elements for executing the tasks, and subtask execution results sent by each second AI network function network element are received.

2. The method according to claim 1, wherein The method further comprises: Determine a final service execution result corresponding to the AI ​​service based on the execution results of the multiple subtasks; Send the final service execution result corresponding to the AI ​​service to the AMF network element.

3. The method according to claim 1, wherein The first request message includes at least one of the following: The AI ​​service type corresponding to the AI ​​service requested by the terminal device; The AI ​​service ID corresponding to the AI ​​service requested by the terminal device; User information of the terminal device.

4. The method according to claim 1, wherein The execution task is divided into a plurality of subtasks, including: Determine the AI ​​service type corresponding to the AI ​​service; Determine the AI ​​algorithms required to implement the AI ​​services; The execution task is divided into a plurality of subtasks based on the AI ​​service type and the AI ​​algorithm.

5. The method according to claim 1, wherein Different second AI network function network elements are used to perform subtasks of different task types; The sending of the plurality of subtasks to a plurality of second AI network function network elements for executing the tasks respectively includes: Based on the task types corresponding to the multiple subtasks, the multiple subtasks are sent to the corresponding second AI network function network element.

6. The method according to claim 1, wherein The method further comprises: Send the user information of the terminal device to the second AI network function network element.

7. The method according to claim 1, wherein The method further comprises: Send a first response message to the multiple second AI network function network elements, where the first response message is used to indicate whether the first AI network function network element successfully receives the subtask execution result.

8. A method for providing services based on AI, characterized in that: The second AI network function element is used to perform tasks, including: receiving a subtask sent by a first AI network function network element for decision-making; Executing the subtask to obtain a subtask execution result; Send the subtask execution result to the first AI network function network element.

9. The method according to claim 8, wherein The executing the subtask to obtain a subtask execution result includes: Acquiring data required for executing the subtask from the network function NF network element based on the subtask; The subtask is executed based on the data to obtain a corresponding subtask execution result.

10. The method according to claim 9, wherein The NF network element includes at least one of the following: User Data Register UDR network element; Unstructured data storage function UDSF network element.

11. The method according to claim 8, wherein The second AI network function network element and other second AI network function network elements perform the subtask in parallel.

12. The method according to claim 9, wherein The method further comprises: Obtain user information of a terminal device sent by the first AI network function network element, where the terminal device is a device requesting an AI service.

13. The method according to claim 12, wherein: The acquiring, based on the subtask, from the NF network element, data required for executing the subtask, includes: Based on the subtask, the data required to execute the subtask is obtained from the NF network element from the data corresponding to the terminal device.

14. The method according to claim 9, wherein The second AI network function network element includes at least one AI model, and the AI ​​model is used to output the subtask execution result based on the data.

15. The method according to claim 14, wherein The method further comprises: The AI ​​model is trained based on local data.

16. The method according to claim 8, wherein The method further comprises: Receive a first response message sent by the first AI network function network element, where the first response message is used to indicate whether the first AI network function network element successfully receives the subtask execution result.

17. A method for providing services based on AI, characterized in that: Executed by the AMF network element, including: receiving a second request message sent by the terminal device, where the second request message indicates an AI service requested by the terminal device; Sending a first request message to the first AI network function network element, where the first request message indicates an AI service requested by the terminal device; receiving a final service execution result corresponding to the AI ​​service sent by the first AI network function network element; Send the final service execution result corresponding to the AI ​​service to the terminal device.

18. The method according to claim 17, wherein The first request message and the second request message each include at least one of the following: The AI ​​service type corresponding to the AI ​​service requested by the terminal device; The AI ​​service ID corresponding to the AI ​​service requested by the terminal device; User information of the terminal device.

19. The method according to claim 17, wherein The method further comprises: Receive a second response message sent by the terminal device, where the second response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

20. The method of claim 17, wherein: The method further comprises: Receive a feedback result sent by the terminal device, where the feedback result is used to provide feedback on the satisfaction level of the final service execution result.

21. A method for providing services based on AI, characterized in that: Executed by the terminal device, including: Send a second request message to the AMF network element, where the second request message indicates the AI ​​service requested by the terminal device; Receive the final service execution result corresponding to the AI ​​service sent by the AMF network element.

22. The method according to claim 21, wherein The second request message includes at least one of the following: The AI ​​service type corresponding to the AI ​​service requested by the terminal device; The AI ​​service ID corresponding to the AI ​​service requested by the terminal device; User information of the terminal device.

23. The method according to claim 21, wherein The method further comprises: A second response message is sent to the AMF network element, where the second response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

24. The method of claim 21, wherein: The method further comprises: Send a feedback result to the AMF network element, where the feedback result is used to provide feedback on the satisfaction level with the final service execution result.

25. A communication device, characterized in that: The device is configured in a first AI network function network element for decision-making, including: A transceiver module, configured to receive a first request message sent by a mobility management function (AMF) network element, where the first request message indicates an AI service requested by a terminal device; a processing module, configured to determine an execution task for implementing the AI ​​service based on the first request message, and divide the execution task into multiple subtasks; The transceiver module is further configured to respectively send the multiple subtasks to multiple second AI network function network elements for executing the tasks, and receive subtask execution results sent by each second AI network function network element.

26. A communication device, characterized in that: The device is configured in a second AI network function network element for performing a task, and includes: a transceiver module, configured to receive a subtask sent by a first AI network function network element for decision-making; A processing module, configured to execute the subtask to obtain a subtask execution result; The transceiver module is further configured to send the subtask execution result to the first AI network function network element.

27. A communication device, characterized in that: The device is configured in the AMF network element and includes: a transceiver module, configured to receive a second request message sent by a terminal device, where the second request message indicates an AI service requested by the terminal device; The transceiver module is further configured to send a first request message to the first AI network function network element, where the first request message indicates an AI service requested by the terminal device; The transceiver module is further configured to receive a final service execution result corresponding to the AI ​​service sent by the first AI network function network element; The transceiver module is further configured to send the final service execution result corresponding to the AI ​​service to the terminal device.

28. A communication device, characterized in that: The device is configured in a terminal device and includes: A transceiver module, configured to send a second request message to the AMF network element, where the second request message indicates the AI ​​service requested by the terminal device; The transceiver module is used to receive the final service execution result corresponding to the AI ​​service sent by the AMF network element.

29. A communication device, characterized in that: The device includes a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program stored in the memory so that the device performs the method according to any one of claims 1 to 7, or the processor executes the computer program stored in the memory so that the device performs the method according to claims 8 to 16, or the processor executes the computer program stored in the memory so that the device performs the method according to claims 17 to 20, or the processor executes the computer program stored in the memory so that the device performs the method according to claims 21 to 24.

30. A communication device, characterized in that: include: processor and interface circuitry, wherein The interface circuit is used to receive code instructions and transmit them to the processor; The processor is configured to execute the code instructions to perform the method according to any one of claims 1 to 7, or to execute the code instructions to execute the method according to claims 8 to 16, or to execute the code instructions to execute the method according to claims 17 to 20, or to execute the code instructions to execute the method according to claims 21 to 24.

31. A communication system, characterized in that: The system comprises: A first network element is configured to receive a second request message sent by a terminal device, where the second request message indicates an AI service requested by the terminal device, and send a first request message, where the first request message indicates the AI ​​service requested by the terminal device; A second network element is configured to receive the first request message, determine an execution task for implementing the AI ​​service based on the first request message, divide the execution task into multiple subtasks, and issue the multiple subtasks; at least one third network element, configured to receive the issued subtask, execute the subtask to obtain a subtask execution result; and send the subtask execution result; The second network element is further used to receive the subtask execution results of each subtask, and determine the final service execution result corresponding to the AI ​​service based on the multiple subtask execution results; and send the final service execution result corresponding to the AI ​​service to the AMF network element; The first network element is further used to receive the final service execution result corresponding to the AI ​​service, and send the final service execution result corresponding to the AI ​​service to the terminal device.

32. A computer-readable storage medium storing instructions, which, when executed, cause the method according to any one of claims 1 to 7 to be implemented, or, when executed, cause the method according to claims 8 to 16 to be implemented, or, when executed, cause the method according to claims 17 to 20 to be implemented, or, when executed, cause the method according to claims 21 to 24 to be implemented.

Images