A method, apparatus, device and storage medium for providing a service based on artificial intelligence (AI)

Abstract

The present disclosure provides a method, device and equipment for providing AI service, and a storage medium. The method comprises: receiving a first request message sent by an AMF network element, the first request message indicating an AI service requested by a terminal device; determining a data allocation result based on the first request message, the data allocation result comprising: indication information corresponding to data allocated to a first AI network function network element and at least one second AI network function network element participating in the execution of the AI service among data required for completing the AI service; sending the data allocation result to a network function NF network element, receiving data allocated by the NF network element based on the data allocation result; determining a first data execution result based on the data allocated by the NF network element, and receiving a second data execution result sent by the second AI network function network element. The present disclosure meets the demand of personalized AI service, makes the AI service result provided more accurate, improves the execution efficiency, improves the overall effectiveness and speed of the AI service, and avoids the problem of AI application scene fragmentation.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to methods, apparatus, devices and storage media for providing services based on AI. Background Technology

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

[0003] The relevant technologies mainly involve optimizing and modifying traditional network architectures to provide AI services based on AI technology.

[0004] However, because these technologies provide AI services by optimizing and modifying traditional network architectures, they lack a unified technical framework for delivering AI services. This leads to fragmented network AI application scenarios and the AI ​​service delivery process is merely a simple overlay on existing network processes. The lack of a universal AI service delivery process fails to meet personalized AI service needs. Furthermore, these technologies do not differentiate the types of data required to complete AI services, nor do they categorize and manage the AI ​​algorithms needed, resulting in low efficiency and poor convenience. Summary of the Invention

[0005] The present disclosure provides methods, apparatus, devices, and storage media for providing services based on AI, in order to solve the technical problems of fragmented AI application scenarios, inability to meet personalized AI service needs, low efficiency, and poor convenience of related technologies.

[0006] In a first aspect, embodiments of this disclosure provide a method for providing services based on AI, the method being executed by a second AI network functional element possessing decision-making capabilities, including: Receive a first request message sent by a Mobility Management Function (AMF) network element, wherein the first request message indicates that there is an AI service requested by a terminal device; The data allocation result is determined based on the first request message. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function element and at least one second AI network function element that participates in the execution of the AI ​​service from the data required to complete the AI ​​service. Send the data allocation result to the network function (NF) element and receive the data allocated by the NF element based on the data allocation result; The first data execution result is determined based on the data allocated by the NF network element, and the second data execution result sent by the second AI network function network element is received.

[0007] This disclosure provides a method for providing services based on AI. A first AI network function element (ANF) with decision-making capabilities receives a first request message from an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to an NF (Agency Function) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple overlay on existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0008] Optionally, the method further includes: The final service execution result corresponding to the AI ​​service is determined based on the first data execution result and the second data execution result. Send the final service execution result corresponding to the AI ​​service to the AMF.

[0009] Optionally, the first request message includes at least one of the following: The type of AI service requested by the terminal device; The AI ​​service identifier ID corresponding to the AI ​​service requested by the terminal device.

[0010] Optionally, the method further includes: From a plurality of second AI network function elements that are communicatively connected to the first AI network function element, at least one second AI network function element is identified that participates in the execution of AI services.

[0011] Optionally, determining at least one second AI network function element participating in the execution of AI services includes: Determine the AI ​​service type corresponding to the AI ​​service; Determine the AI ​​algorithm required to complete the AI ​​service; Determine the data categories required to complete the AI ​​service; A status request message is sent to a second AI network function network element that is communicatively connected to the first AI network function network element. The status request message is used to request status information related to the AI ​​service execution capability of the second AI network function network element. Receive status information sent by the second AI network function element; At least one second AI network function element is selected to participate in the execution of the AI ​​service based on at least one of the AI ​​service type, AI algorithm, data category, and status information.

[0012] Optionally, the status information includes at least one of the following: Energy state information; Communication status information.

[0013] Optionally, the indication information includes at least one of the following: Data name; Data identifier.

[0014] Optionally, determining the data allocation result based on the first request message includes: Based on the first request message, determine the indication information corresponding to the data required to complete the AI ​​service, wherein each indication information is used to indicate a type of data; The indication information is grouped to obtain at least one set of indication information; The first AI network function element and at least one second AI network function element participating in the execution of AI services are respectively assigned instruction information groups to obtain the data allocation result. The instruction information group assigned to the first AI network function element or at least one second AI network function element participating in the execution of AI services is used to indicate that the data group indicated by the instruction information group corresponding to the first AI network function element or the second AI network function element participating in the execution of AI services is allocated to the first AI network function element or the second AI network function element participating in the execution of AI services.

[0015] Optionally, grouping the indication information to obtain at least one set of indication information includes: The data indication information is grouped based on the importance of the data to the AI ​​service and / or the difficulty of processing the data.

[0016] Optionally, the step of allocating instruction information groups to the first AI network function element and at least one second AI network function element participating in the execution of AI services includes: Specific instruction information groups are assigned to the first AI network function network element, and other instruction information groups are respectively assigned to at least one second AI network function network element that participates in performing AI services; Among them, the data corresponding to the specific instruction information group is of the greatest importance to the AI ​​service, and / or the data corresponding to the specific instruction information group is the most difficult to process.

[0017] Optionally, the method further includes: Allocate resource blocks with different weights to at least one second AI network function element participating in the execution of AI services; The weight of the resource block allocated to the second AI network function element is positively correlated with the importance and processing difficulty of the data corresponding to the instruction information group allocated to the second AI network function element for the AI ​​service.

[0018] Optionally, the NF network element includes at least one of the following: User Data Register (UDR) network element; Unstructured data storage function UDSF network element.

[0019] Optionally, determining the final service execution result corresponding to the AI ​​service based on the first data execution result and the second data execution result includes: The execution results of the first data and the execution results of the second data are aggregated and structured to obtain the final service execution result corresponding to the AI ​​service.

[0020] Optionally, the first AI network function element and at least one second AI network function element participating in the execution of AI services determine the data execution result in parallel.

[0021] Secondly, embodiments of this disclosure provide a method for providing services based on AI, the method being executed by a second AI network functional element with execution capabilities, including: Receive data allocated by the NF network element, wherein the data is required to complete the AI ​​service; The second data execution result is determined based on the data allocated by the NF network element; The second data execution result is sent to the first AI network functional element.

[0022] Optionally, the NF network element includes at least one of the following: UDR network element; UDSF network element.

[0023] Optionally, the method further includes: Receive a status request message sent by the first AI network function element, wherein the status request message is used to request status information related to the AI ​​service execution capability of the second AI network function element; The status information is sent to the first AI network functional element.

[0024] Optionally, the status information includes at least one of the following: Energy state information; Communication status information.

[0025] Optionally, the method further includes: Receive the resource block allocated by the first AI network function element.

[0026] Optionally, the second AI network function element and other second AI network function elements and first AI network function elements determine the data execution result in parallel.

[0027] Thirdly, embodiments of this disclosure provide a method for providing services based on AI, which is executed by an NF network element, including: Receive data allocation results sent by the first AI network function element, the data allocation results including: indication information corresponding to the data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service in the data required to complete the AI ​​service; Based on the data allocation results, corresponding data are allocated to the first AI network function element and at least one second AI network function element that participates in executing AI services.

[0028] Optionally, the indication information includes at least one of the following: Data name; Data identifier.

[0029] Fourthly, embodiments of this disclosure provide a method for providing services based on AI, which is executed by an AMF network element, including: Receive a second request message sent by a terminal device, the second request message indicating the AI ​​service requested by the terminal device; Send a first request message to the first AI network function element, wherein the first request message indicates that there is an AI service requested by a terminal device; Receive the final service execution result corresponding to the AI ​​service sent by the first AI network function element; Send the final service execution result corresponding to the AI ​​service to the terminal device.

[0030] Optionally, both the first request message and the second request message include at least one of the following: The type of AI service requested by the terminal device; The AI ​​service ID corresponding to the AI ​​service requested by the terminal device.

[0031] Optionally, the method further includes: The terminal device receives a response message, which indicates whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0032] Optionally, the method further includes: The system receives feedback results sent by the terminal device, which are used to indicate the level of satisfaction with the final service execution result.

[0033] Fifthly, embodiments of this disclosure provide a method for providing services based on AI, the method being executed by a terminal device, including: Send a second request message to the AMF network element, the second request message indicating 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.

[0034] Optionally, the second request message includes at least one of the following: The type of AI service requested by the terminal device; The AI ​​service ID corresponding to the AI ​​service requested by the terminal device.

[0035] Optionally, the method further includes: A response message is sent to the AMF network element, the response message indicating whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0036] Optionally, the method further includes: Feedback results are sent to the AMF network element, and the feedback results are used to indicate the degree of satisfaction with the final service execution result.

[0037] Sixthly, embodiments of this disclosure provide a communication device configured in a first AI network functional element, comprising: The transceiver module is used to receive a first request message sent by the Mobility Management Function (AMF) network element, wherein the first request message indicates that there is an AI service requested by the terminal device. The processing module is used to determine the data allocation result based on the first request message. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service from the data required to complete the AI ​​service. The transceiver module is also used to send the data allocation result to the NF network element and receive the data allocated by the NF network element based on the data allocation result; The processing module is further configured to determine the first data execution result based on the data allocated by the NF network element, and to receive the second data execution result sent by the second AI network function network element.

[0038] In a seventh aspect, embodiments of this disclosure provide a communication device configured in a second AI network functional element, comprising: The transceiver module is used to receive data allocated by NF network elements, which is the data required to complete the AI ​​service; The processing module is used to determine the second data execution result based on the data allocated by the NF network element; The transceiver module is also used to send the second data execution result to the first AI network function element.

[0039] Eighthly, embodiments of this disclosure provide a communication device configured in an NF network element, comprising: The transceiver module is used to receive the data allocation result sent by the first AI network function network element. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function network element and at least one second AI network function network element participating in the execution of the AI ​​service from the data required to complete the AI ​​service. The transceiver module is also used to allocate corresponding data to the first AI network function element and at least one second AI network function element participating in the execution of AI services based on the data allocation result.

[0040] Ninthly, embodiments of this disclosure provide a communication device configured in an AMF network element, comprising: The transceiver module is used to receive a second request message sent by the terminal device, wherein the second request message indicates the 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 element, wherein the first request message indicates an AI service requested by a terminal device. The transceiver module is also used to receive the final service execution result corresponding to the AI ​​service sent by the first AI network function element; The transceiver module is also used to send the final service execution result corresponding to the AI ​​service to the terminal device.

[0041] In a tenth aspect, embodiments of this disclosure provide a communication device configured in a terminal device, comprising: The transceiver module is used to send a second request message to the AMF network element, the second request message indicating 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.

[0042] Eleventhly, embodiments of this disclosure provide a communication device including a processor that, when the processor invokes a computer program in memory, executes the method described in the first aspect.

[0043] In a twelfth aspect, embodiments of this disclosure provide a communication device including a processor that, when the processor invokes a computer program in memory, executes the method described in the second aspect above.

[0044] In a thirteenth aspect, embodiments of this disclosure provide a communication device including a processor that, when the processor invokes a computer program in memory, executes the method described in the third aspect above.

[0045] In a fourteenth aspect, embodiments of this disclosure provide a communication device including a processor that, when the processor invokes a computer program in memory, executes the method described in the fourth aspect above.

[0046] In a fifteenth aspect, embodiments of this disclosure provide a communication device including a processor that, when the processor invokes a computer program in memory, executes the method described in the fifth aspect above.

[0047] In a sixteenth aspect, embodiments of this disclosure provide a communication device including a processor and a memory storing a computer program; the processor executes the computer program stored in the memory to cause the communication device to perform the method described in the first aspect above.

[0048] In a seventeenth aspect, embodiments of this disclosure provide a communication device including a processor and a memory storing a computer program; the processor executes the computer program stored in the memory to cause the communication device to perform the method described in the second aspect above.

[0049] In an eighteenth aspect, embodiments of this disclosure provide a communication device including a processor and a memory storing a computer program; the processor executes the computer program stored in the memory to cause the communication device to perform the method described in the third aspect above.

[0050] In a nineteenth aspect, embodiments of this disclosure provide a communication device including a processor and a memory storing a computer program; the processor executes the computer program stored in the memory to cause the communication device to perform the method described in the fourth aspect above.

[0051] In a twentieth aspect, embodiments of this disclosure provide a communication device including a processor and a memory, the memory storing a computer program; the processor executes the computer program stored in the memory to cause the communication device to perform the method described in the fifth aspect above.

[0052] In a twentieth aspect, embodiments of this disclosure provide a communication device including a processor and an interface circuit. The interface circuit is configured to receive code instructions and transmit them to the processor, which is configured to execute the code instructions to cause the device to perform the method described in the first aspect above.

[0053] In a twentieth aspect, embodiments of this disclosure provide a communication device including a processor and an interface circuit. The interface circuit is configured to receive code instructions and transmit them to the processor, which is configured to execute the code instructions to cause the device to perform the method described in the second aspect above.

[0054] In a twentieth aspect, embodiments of this disclosure provide a communication device including a processor and an interface circuit. The interface circuit is configured to receive code instructions and transmit them to the processor, which is configured to execute the code instructions to cause the device to perform the method described in the third aspect above.

[0055] In a twentieth aspect, embodiments of this disclosure provide a communication device including a processor and an interface circuit. The interface circuit is configured to receive code instructions and transmit them to the processor, which is configured to execute the code instructions to cause the device to perform the method described in the fourth aspect above.

[0056] In a twentieth aspect, embodiments of this disclosure provide a communication device including a processor and an interface circuit. The interface circuit is configured to receive code instructions and transmit them to the processor, which is configured to execute the code instructions to cause the device to perform the method described in the fifth aspect above.

[0057] In a twentieth aspect, embodiments of this disclosure provide a communication system comprising the communication devices described in the sixth aspect to the tenth aspect, or the communication devices described in the eleventh aspect to the fifteenth aspect, or the communication devices described in the sixteenth aspect to the twentieth aspect, or the communication devices described in the twenty-first aspect to the twenty-fifth aspect.

[0058] In a twentieth aspect, embodiments of the present invention provide a computer-readable storage medium for storing instructions for use by the network device and / or the terminal device described above. When the instructions are executed, the network device performs the method described in the first aspect, and / or the terminal device performs the method described in the second aspect, and / or the terminal device performs the method described in the third aspect, and / or the terminal device performs the method described in the fourth aspect, and / or the terminal device performs the method described in the fifth aspect.

[0059] In a twentieth aspect, this disclosure also provides a computer program product including a computer program, which, when run on a computer, causes the computer to perform the method described in any one of the first to fifth aspects.

[0060] In a twentieth aspect, this disclosure provides a chip system including at least one processor and an interface for supporting network devices in implementing the functions described in the first aspect, and / or supporting terminal devices in implementing the functions described in the second aspect, and / or supporting terminal devices in implementing the functions described in the third aspect, and / or supporting terminal devices in implementing the functions described in the fourth aspect, and / or supporting terminal devices in implementing the functions described in the fifth aspect, such as determining or processing at least one of the data and information involved in the above methods. In one possible design, the chip system further includes a memory for storing computer programs and data necessary for source and auxiliary nodes. The chip system may be composed of chips or may include chips and other discrete devices.

[0061] In a thirtieth aspect, this disclosure provides a computer program that, when run on a computer, causes the computer to perform the method described in any one of the first to fifth aspects.

[0062] In a thirty-first aspect, this disclosure provides a communication system, comprising: The first network element is used to receive a second request message sent by a terminal device, the second request message indicating the AI ​​service requested by the terminal device, and to send a first request message, the first request message indicating the AI ​​service requested by the terminal device. The second network element is used to receive the first request message and determine the data allocation result based on the first request message. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function network element and at least one second AI network function network element participating in the execution of the AI ​​service in the data required to complete the AI ​​service, and sends the data allocation result. The third network element is used to receive the data allocation result and allocate data based on the data allocation result; The second network element is also used to receive data allocated by the third network element based on the data allocation result, and to determine the first data execution result; At least one fourth network element is configured to receive data allocated by the third network element based on the data allocation result, determine the second data execution result, and send the second data execution result. The second network element is also used to receive each second data execution result, and determine the final service execution result corresponding to the AI ​​service based on the first data execution result and the second data execution result, and send the final service execution result corresponding to the AI ​​service; The first network element is also 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. Attached Figure Description

[0063] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which: Figure 1a This is a schematic diagram of the architecture of a communication system provided in an embodiment of the present disclosure; Figure 1b A schematic diagram of a core network architecture provided in an embodiment of this disclosure. Figure 2 A flowchart illustrating a method for providing services based on AI, as provided in another embodiment of this disclosure; Figure 3 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 4 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 5 A flowchart illustrating a method for providing services based on AI, as provided in another embodiment of this disclosure; Figure 6 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 7A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 8 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 9 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 10 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 11 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 12 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 13 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 14 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 15 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 16 A flowchart illustrating a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 17a A schematic diagram of the interaction flow of a method for providing services based on AI, as provided in yet another embodiment of this disclosure; Figure 17b This is a schematic diagram of the structure of a communication device provided in one embodiment of the present disclosure; Figure 18 This is a schematic diagram of the structure of a communication device provided in another embodiment of the present disclosure; Figure 19 This is a schematic diagram of the structure of a communication device provided in another embodiment of the present disclosure; Figure 20 This is a schematic diagram of the structure of a communication device provided in another embodiment of the present disclosure; Figure 21 This is a schematic diagram of the structure of a communication device provided in another embodiment of the present disclosure; Figure 22 This is a schematic diagram of the structure of a communication system provided in one embodiment of the present disclosure; Figure 23 This is a block diagram of a communication device provided in one embodiment of the present disclosure; Figure 24This is a schematic diagram of the structure of a chip provided in one embodiment of the present disclosure. Detailed Implementation

[0064] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this disclosure as detailed in the appended claims.

[0065] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. The singular forms “a” and “the” as used in this disclosure and the appended claims are also intended to include the 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 and all possible combinations of one or more of the associated listed items.

[0066] It should be understood that although the terms first, second, third, etc., may be used to describe various information in embodiments of this disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of embodiments of this disclosure, and similarly, second information may also be referred to as first information. Depending on the context, the words “if” and “suppose” as used herein may be interpreted as “when”, “when”, or “in response to a determination”.

[0067] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0068] To facilitate understanding, the terminology used in this application will be introduced first.

[0069] 1. Artificial Intelligence (AI) AI is a new technical science that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence.

[0070] 2. Access and Mobility Management Function (AMF) network element AMF network elements perform registration, connection, reachability, and mobility management. They provide session management message transmission channels for terminal devices and SMF network elements, and provide authentication and authorization functions for terminal devices when they access the network; they are the access points for terminal devices and the wireless core network control plane.

[0071] To better understand the method for determining sidelink duration disclosed in the embodiments of this application, the communication system to which the embodiments of this application are applicable is first described below.

[0072] Please see Figure 1a , Figure 1a This 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. Figure 1a The number and form of the devices shown are for illustrative purposes only and do not constitute a limitation on the embodiments of this disclosure. In actual applications, it may include two or more core network devices and two or more terminal devices. Figure 1a The communication system shown is an example including a core network device 11 and a terminal device 12.

[0073] It should be noted that the technical solutions of this disclosure can be applied to various communication systems. For example, long term evolution (LTE) systems, 5th generation (5G) mobile communication systems, 5G new radio (NR) systems, or other future new mobile communication systems.

[0074] In this embodiment of the disclosure, the core network device 11 is a device deployed in the core network. The main functions of the core network device 11 are to provide user connectivity, manage users, and carry out service delivery, serving as an interface to external networks. For example, the core network device in a 5G NR system may include Access and Mobility Management Function (AMF) network elements, User Plane Function (UPF) network elements, and Session Management Function (SMF) network elements, etc.

[0075] For example, the core network device 11 in this embodiment may include a location management function network element. Optionally, the location management function network element includes a location server, which may be implemented as any of the following: LMF (Location Management Function), E-SMLC (Enhanced Serving Mobile Location Centre), SUPL (Secure User PlaneLocation), or SUPL SLP (Secure User PlaneLocation Location Platform).

[0076] The terminal device 12 in this disclosure can be a user-side entity used to receive or transmit signals, such as a mobile phone. The terminal device can also be referred to as a terminal, user equipment (UE), mobile station (MS), mobile terminal (MT), etc. The terminal device can be a car with communication capabilities, a smart car, a mobile phone, a wearable device, a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, a wireless terminal device in a smart home, and so on. This disclosure does not limit the specific technology or device form used in the terminal device.

[0077] The core network device 11 and the terminal device 12 can communicate through the base station.

[0078] And, please see Figure 1b , Figure 1b This is a schematic diagram of a core network architecture provided in an embodiment of this disclosure. Figure 1b It includes the network elements of the core network architecture and the interfaces used for communication between the various network elements.

[0079] The core network architecture abstracts the functions of network elements into multiple services. Compared to the traditional core network architecture, Figure 1b The core network architecture adds N network elements named AI0, AI1, AI2...AIN. AI0 is a decision-making network element used to assign AI tasks to AI1, AI2...AIN network elements, and also provides AI functionality. AI1, AI2...AIN network elements are all network elements that provide AI functionality based on the decisions made by AI0. AI0 can be the first AI network function network element with decision-making capabilities mentioned later in this embodiment, and AI1, AI2...AIN network elements can be the second AI network function network elements with execution capabilities mentioned later in this embodiment. Furthermore, all AI0, AI1, AI2...AIN network elements can communicate with other network elements (such as AMF network elements, SMF network elements, etc.) in the network.

[0080] It is understood that the communication system described in the embodiments of this disclosure is for the purpose of more clearly illustrating the technical solutions of the embodiments of this disclosure, and does not constitute a limitation on the technical solutions provided in the embodiments of this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this disclosure are also applicable to similar technical problems.

[0081] Furthermore, it should be noted that the method disclosed herein is specifically implemented based on the completion of the following operations; (1) The terminal device has completed the initial registration process and is connected to the network.

[0082] (2) AI network functional elements (i.e.) Figure 1b The AI0, AI1, AI2...AIN network elements have been registered with the Network Repository Function (NRF) and can be accessed and operated normally in the core network architecture.

[0083] (3) The core network has authenticated each AI network function to ensure its secure access.

[0084] (4) AI0 and AI1 / ... / AIN network elements trust each other and transmit real communication information.

[0085] The following describes in detail, with reference to the accompanying drawings, the methods, apparatus, devices, and storage media for providing AI-based services according to embodiments of this disclosure.

[0086] Figure 2 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a first AI network functional element possessing decision-making capabilities, such as... Figure 2As shown, this AI-based service delivery method may include the following steps: Step 201: Receive the first request message sent by the AMF network element.

[0087] In one embodiment of this disclosure, the first request message indicates an AI service requested by the terminal device. The first request message may include at least one of the following: The AI ​​service type corresponding to the AI ​​service requested by the terminal device; such AI service type can be video, language, etc. The AI ​​Service ID corresponding to the AI ​​service requested by the terminal device; this AI Service ID is used to uniquely identify the AI ​​service.

[0088] Furthermore, in one embodiment of this 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 (e.g., transparent transmission). The first request message may be a CreateAI0Context_Request message, and the second request message may be an AI ServiceEstablishment Request message.

[0089] Furthermore, it should be noted that, in one embodiment of this disclosure, the aforementioned first request message may further include at least one of the following: Data Network Name (DNN); User information of terminal devices; Access type; The identifier of the terminal device; wherein, the identifier may be, for example, Paging Early Indication (PEI), Generic Public Subscription Identifier (GPSI), etc.

[0090] Step 202: Determine the data allocation result based on the first request message.

[0091] In one embodiment of this disclosure, the data allocation result includes: indication information corresponding to the data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. In other words, the data allocation result specifically includes the corresponding allocation relationship between the indication information of the data required to complete the AI ​​service and the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Furthermore, the data allocation result implicitly indicates that the data indicated by the indication information corresponding to the first AI network function element is allocated to the first AI network function element, and the data indicated by the indication information corresponding to the second AI network function element is allocated to the second AI network function element. Specifically, the second AI network function element is a network element that has the ability to perform AI functions but does not have decision-making capabilities, and the indication information can be a data name and / or a data identifier.

[0092] Furthermore, in one embodiment of this disclosure, the aforementioned step of "determining data allocation results based on the first request message" may specifically include: the first AI network function element first determines, based on the first request message, what specific data is required to complete the AI ​​service, and groups the data required to complete the AI ​​service. Then, it allocates at least one data group to both the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, so that the first AI network function element and the at least one second AI network function element participating in the execution of the AI ​​service can perform corresponding tasks based on the allocated data groups to achieve the AI ​​service. However, it should be emphasized that when the first AI network function element determines what specific data is required to complete the AI ​​service, it does not determine the specific data, but rather indicates the determined data by determining the indication information corresponding to the data required to complete the AI ​​service. Simultaneously, when the first AI network function element groups the data required to complete the AI ​​service, it does not group the specific data, but implicitly groups the data by grouping the indication information corresponding to the data. Each indication information group corresponds to data primarily used to complete a portion of the tasks of the AI ​​service. Furthermore, when the first AI network function element allocates at least one set of data to itself and at least one second AI network function element participating in the execution of AI services, it does not allocate specific data sets to itself and at least one second AI network function element participating in the execution of AI services. Instead, it implicitly indicates which data is allocated to itself and at least one second AI network function element participating in the execution of AI services by determining the corresponding allocation relationship between the indication information set and the first AI network function element and at least one second AI network function element participating in the execution of AI services.

[0093] For example, in one embodiment of this disclosure, it is assumed that the aforementioned indication information is a data name, and the second AI network function network element participating in the execution of the AI ​​service includes the second AI network function network element #1 and the second AI network function network element #2. Based on this, when the first AI network function network element receives the first request message, it can determine that an AI service needs to be executed, and the first AI network function network element determines, based on the first request message, that the data names required to complete the AI ​​service include: data name 1, data name 2, data name 3, data name 4... data name 10. At this time, the data names can be grouped to obtain at least one group of data names, such as dividing data names 1-3 into data name group one, data names 4-7 into data name group two, and data names 8-10 into data name group three. Then, it can be determined that... The data allocation result is as follows: Data name group one is allocated to the first AI network function element, data name group two is allocated to the second AI network function element #1, and data name group three is allocated to the second AI network function element #2. At this time, the data allocation result implicitly indicates that data with names 1-3 in data name group one is allocated to the first AI network function element, data with names 4-7 in data name group two is allocated to the second AI network function element #1, and data with names 8-10 in data name group three is allocated to the second AI network function element #2.

[0094] Step 203: Send the data allocation result to the Network Function (NF) element and receive the data allocated by the NF element based on the data allocation result.

[0095] In one embodiment of this disclosure, the NF network element can be a UDR (User Data Repository) network element and / or a UDSF (Unstructured Data Storage Network Function) network element. The UDR and UDSF network elements respectively store structured and unstructured data sets. Furthermore, the data stored in the UDR and UDSF network elements primarily originates from: data provided during terminal device registration, or data corresponding to the requested AI service synchronously provided to the NF network element when the terminal device requests an AI service.

[0096] Furthermore, in one embodiment of this disclosure, the first AI network function element sends a data allocation result to the NF network element, so that the NF network element can allocate corresponding data to the first AI network function element and at least one second AI network function element participating in the execution of AI services based on the data allocation result, thereby enabling the first AI network function element and at least one second AI network function element participating in the execution of AI services to perform corresponding tasks based on the data allocated by the NF network element to complete the AI ​​service.

[0097] Step 204: Determine the first data execution result based on the data allocated by the NF network element, and receive the second data execution result sent by the second AI network function network element.

[0098] In one embodiment of this disclosure, the first data execution result may be obtained by training a first AI network function element based on data allocated by an NF network element. Furthermore, the second data execution result may be obtained by training a second AI network function element based on data allocated to the second AI network function element by the NF network element.

[0099] As can be seen from steps 202-204 above, in this disclosure, when the first AI network function element determines that an AI service needs to be executed, it groups the data required to complete the AI ​​service. Then, it instructs the NF network element to allocate different data groups to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, so that the first AI network function element and the at least one second AI network function element participating in the execution of the AI ​​service can respectively execute the tasks corresponding to the allocated data to achieve the AI ​​service. Therefore, this disclosure enables the first AI network function element and the at least one second AI network function element participating in the execution of the AI ​​service to respectively execute different parts of the AI ​​service tasks, thereby achieving classified management of AI services and fine-grained division of AI functions, resulting in more accurate AI service results provided subsequently.

[0100] Furthermore, it should be noted that, in one embodiment of this disclosure, the first AI network function element and at least one second AI network function element participating in the execution of AI services determine the data execution results in parallel, which results in higher efficiency.

[0101] Furthermore, in one embodiment of this disclosure, after obtaining the first data execution result and the second data execution result, the first AI network function element can provide AI services to the terminal device through the AMF element based on the first data execution result and the second data execution result.

[0102] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, which indicates an AI service requested by a terminal device. Furthermore, the first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete, universal, and finely orchestrated AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, the collaborative execution of AI services by the first and second AI network function elements in this disclosure improves the overall effectiveness and speed of the AI ​​service. Furthermore, in this disclosure, the first AI network function element and multiple second AI network function elements, along with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the fragmentation problem of AI application scenarios.

[0103] Figure 3 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a first AI network functional element possessing decision-making capabilities, such as... Figure 3 As shown, this AI-based service delivery method may include the following steps: Step 301: Determine the final service execution result corresponding to the AI ​​service based on the first data execution result and the second data execution result.

[0104] In one embodiment of this disclosure, the first AI network function element can specifically perform aggregation and structuring processing on the first data execution result and the second data execution result to obtain the final service execution result corresponding to the AI ​​service that meets the overall requirements.

[0105] Step 302: Send the final service execution result corresponding to the AI ​​service to AMF.

[0106] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, which indicates an AI service requested by a terminal device. Furthermore, the first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete, universal, and finely orchestrated AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, the collaborative execution of AI services by the first and second AI network function elements in this disclosure improves the overall effectiveness and speed of the AI ​​service. Furthermore, in this disclosure, the first AI network function element and multiple second AI network function elements, along with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the fragmentation problem of AI application scenarios.

[0107] Figure 4 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a first AI network functional element possessing decision-making capabilities, such as... Figure 4 As shown, this AI-based service delivery method may include the following steps: Step 401: From a plurality of second AI network function network elements that are communicatively connected to the first AI network function network element, determine at least one second AI network function network element that participates in performing AI services.

[0108] In one embodiment of this disclosure, the method for determining at least one second AI network function element participating in the execution of AI services may specifically include: Step a: Determine the type of AI service corresponding to the AI ​​service.

[0109] Specifically, the type of AI service can be determined based on the content included in the first request message.

[0110] Step b: Determine the AI ​​algorithm required to complete the AI ​​service.

[0111] The first AI network function element can determine the specific AI service requested by the first request message based on the AI ​​service ID and AI service type in the received first request message, and determine the AI ​​algorithm required to complete the AI ​​service by analyzing the AI ​​service.

[0112] Step c: Determine the data categories required to complete the AI ​​service.

[0113] Among them, the data categories can include Independent and Identically Distributed (IID) or non-IID.

[0114] Step d: Send a status request message to the second AI network function network element that is communicatively connected to the first AI network function network element. The status request message is used to request status information related to the AI ​​service execution capability of the second AI network function network element.

[0115] The status information may include energy status information (or power status information) and / or communication status information.

[0116] Step e: Receive status information sent by the second AI network function element; Step f: Select at least one second AI network function element to participate in the execution of AI services based on at least one of AI service type, AI algorithm, data category, and status information.

[0117] Specifically, in one embodiment of this disclosure, a second AI network function element whose energy state and / or communication state matches the AI ​​service type, AI algorithm, and data category can be selected to participate in the execution of the AI ​​service. In another embodiment of this disclosure, the first few second AI network function elements with better energy states and / or communication states can also be selected to participate in the execution of the AI ​​service. This ensures that the second AI network function elements can subsequently complete the AI ​​service with high efficiency and high accuracy, guaranteeing the efficiency and accuracy of the AI ​​service provision method.

[0118] The number of second AI network function elements selected to participate in the execution of AI services can be determined autonomously by the first AI network function element based on its implementation, or it can be determined based on the specific AI service to be executed, such as determining the number of second AI network function elements selected to participate in the execution of AI services with the aim of "executing AI services with high efficiency and high precision".

[0119] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, which indicates an AI service requested by a terminal device. Furthermore, the first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete, universal, and finely orchestrated AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, the collaborative execution of AI services by the first and second AI network function elements in this disclosure improves the overall effectiveness and speed of the AI ​​service. Furthermore, in this disclosure, the first AI network function element and multiple second AI network function elements, along with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the fragmentation problem of AI application scenarios.

[0120] Figure 5 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a first AI network functional element possessing decision-making capabilities, such as... Figure 5 As shown, this AI-based service delivery method may include the following steps: Step 501: Based on the first request message, determine the indication information corresponding to the data required to complete the AI ​​service, wherein each indication information is used to indicate one type of data.

[0121] In one embodiment of this disclosure, the indication information may specifically be: data name and / or data identifier.

[0122] Furthermore, in one embodiment of this disclosure, the first AI network function element can specifically determine the indication information corresponding to the data required to complete the AI ​​service based on the content included in the first request message.

[0123] Step 502: Group the instruction information to obtain at least one group of instruction information.

[0124] In one embodiment of this disclosure, the indication information of the data can be grouped based on the importance of the data to the AI ​​service and / or the difficulty of processing the data. For example, the indication information corresponding to data with similar importance to the AI ​​service and / or processing difficulty can be grouped together.

[0125] For example, suppose the first AI network function element determines the following instruction information corresponding to the data required to complete the AI ​​service: instruction information #1 for data 1, instruction information #2 for data 2, instruction information #3 for data 3, and instruction information #4 for data 4. If data 1 and data 2 are more important to the AI ​​service, and data 3 and data 4 are less important, then instruction information #1 and instruction information #2 can be grouped together, and instruction information #3 and instruction information #4 can be grouped together. Alternatively, if data 2 and data 3 have greater heterogeneity for the AI ​​service, and data 1 and data 4 have less heterogeneity, it indicates that data 2 and data 3 are more difficult to process, and data 1 and data 4 are less difficult to process. In this case, instruction information #2 and instruction information #3 can be grouped together, and instruction information #1 and instruction information #4 can be grouped together.

[0126] Step 503: Assign instruction information groups to the first AI network function element and at least one second AI network function element participating in the execution of AI services to obtain data allocation results.

[0127] The instruction information group assigned to the first AI network function element or at least one second AI network function element participating in the execution of AI services is used to indicate that the data group indicated by the instruction information group corresponding to the first AI network function element or the second AI network function element participating in the execution of AI services is assigned to the first AI network function element or the second AI network function element participating in the execution of AI services.

[0128] Furthermore, in one embodiment of this disclosure, the method for allocating instruction information groups to a first AI network function element and at least one second AI network function element participating in the execution of AI services may include: allocating a specific instruction information group to the first AI network function element, and allocating other instruction information groups to at least one second AI network function element participating in the execution of AI services. In one embodiment of this disclosure, the data corresponding to the specific instruction information group is of the highest importance to the AI ​​service, and / or, the data corresponding to the specific instruction information group is of the highest processing difficulty. Alternatively, in another embodiment of this disclosure, the specific instruction information group is one of the top instruction information groups whose corresponding data is of high importance to the AI ​​service, and / or, the specific instruction information group is one of the top instruction information groups whose corresponding data is of high processing difficulty.

[0129] In one embodiment of this disclosure, since the first AI network function element has strong processing capabilities, by allocating the more important and / or more difficult data among the data required to complete the AI ​​service to the first AI network function element, the first AI network function element with strong processing capabilities can complete the more important and / or more difficult parts of the AI ​​service, thereby ensuring the efficiency and accuracy of the AI ​​service.

[0130] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, which indicates an AI service requested by a terminal device. Furthermore, the first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete, universal, and finely orchestrated AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, the collaborative execution of AI services by the first and second AI network function elements in this disclosure improves the overall effectiveness and speed of the AI ​​service. Furthermore, in this disclosure, the first AI network function element and multiple second AI network function elements, along with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the fragmentation problem of AI application scenarios.

[0131] Figure 6 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a first AI network functional element possessing decision-making capabilities, such as... Figure 6 As shown, this AI-based service delivery method may include the following steps: Step 601: Assign resource blocks with different weights to at least one second AI network function element participating in the execution of AI services.

[0132] In one embodiment of this disclosure, the weight of the resource block allocated to the second AI network function element is positively correlated with the importance and processing difficulty of the data corresponding to the instruction information group allocated to the second AI network function element for the AI ​​service. For example, if the data corresponding to the instruction information group allocated to the second AI network function element is of high importance to the AI ​​service, and / or the data corresponding to the instruction information group allocated to the second AI network function element is of high processing difficulty for the AI ​​service, then a resource block with a larger weight is allocated to the second AI network function element.

[0133] It should be noted that the importance and processing difficulty of the data corresponding to the instruction information group allocated to the second AI network function element for the AI ​​service specifically reflects the processing capacity requirements of the second AI network function element in completing the AI ​​service. Based on this, by making the weight of the resource blocks allocated to the second AI network function element positively correlated with the importance and processing difficulty of the data corresponding to the instruction information group allocated to the second AI network function element for the AI ​​service, the resource blocks allocated to the second AI network function element can be matched to the processing capacity requirements of the second AI network function element in completing the AI ​​service. This avoids the technical problem of "resource waste due to allocating too many resource blocks to the second AI network function element, or low AI service completion efficiency due to allocating too few resource blocks to the second AI network function element," thus avoiding resource waste while ensuring the efficiency of AI service completion.

[0134] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0135] Figure 7 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a second AI network function element with execution capabilities, such as... Figure 7 As shown, this AI-based service delivery method may include the following steps: Step 701: Receive data allocated by the NF network element, which is the data required to complete the AI ​​service.

[0136] In one embodiment of this disclosure, the data received by the second AI network function element may be allocated to the second AI network function element by the NF network element based on the data allocation result.

[0137] Step 702: Determine the second data execution result based on the data allocated by the NF network element.

[0138] Step 703: Send the second data execution result to the first AI network functional element.

[0139] In one embodiment of this disclosure, the second AI network function element synchronously determines the data training results with the first AI network function element and other second AI network function elements.

[0140] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0141] Figure 8 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a second AI network function element with execution capabilities, such as... Figure 8 As shown, this AI-based service delivery method may include the following steps: Step 801: Receive a status request message sent by the first AI network function element. The status request message is used to request status information related to the AI ​​service execution capability of the second AI network function element.

[0142] Step 802: Send the status information to the first AI network functional element.

[0143] For a detailed description of steps 801-802, please refer to the above embodiment description.

[0144] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0145] Figure 9 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a second AI network function element with execution capabilities, such as... Figure 9As shown, this AI-based service delivery method may include the following steps: Step 901: Receive the resource block allocated by the first AI network function element.

[0146] For a detailed description of step 901, please refer to the above embodiment.

[0147] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0148] Figure 10 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. This method is executed by an NF network element, such as... Figure 10 As shown, this AI-based service delivery method may include the following steps: Step 1001: Receive the data allocation result sent by the first AI network function element. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service from the data required to complete the AI ​​service.

[0149] The relevant description of step 1001 can be found in the above embodiment description.

[0150] Step 1002: Based on the data allocation results, allocate corresponding data to the first AI network function element and at least one second AI network function element participating in the execution of AI services.

[0151] Specifically, in one embodiment of this disclosure, the NF network element can find the data indicated by each indication information in the data allocation result, and send the data allocation indicated by the indication information corresponding to the first AI network function network element to the first AI network function network element, and send the data allocation indicated by the indication information corresponding to the second AI network function network element to the second AI network function network element.

[0152] Furthermore, it should be noted that in one embodiment of this disclosure, the data allocation result may further include user information and / or the identifier of the terminal device. Specifically, the NF network element can locate the data corresponding to the terminal device stored in the NF network element based on the user information and / or the identifier of the terminal device, and then search for the data indicated by each indication information in the data allocation result within that data corresponding to the terminal device, so as to allocate the corresponding data to the first AI network function network element and the second AI network function network element participating in the execution of AI services, respectively.

[0153] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0154] Figure 11 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by an AMF network element, such as... Figure 11 As shown, this AI-based service delivery method may include the following steps: Step 1101: Receive a second request message sent by the terminal device, which indicates the AI ​​service requested by the terminal device.

[0155] Step 1102: Send a first request message to the first AI network function element, the first request message indicating the AI ​​service requested by the terminal device.

[0156] Step 1103: Receive the final service execution result corresponding to the AI ​​service sent by the first AI network function element.

[0157] Step 1104: Send the final service execution result corresponding to the AI ​​service to the terminal device.

[0158] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0159] Figure 12 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by an AMF network element, such as... Figure 12 As shown, this AI-based service delivery method may include the following steps: Step 1201: Receive a response message sent by the terminal device. This response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0160] In one embodiment of this disclosure, if the response message indicates that the terminal device has not successfully received the final service execution result, the AMF network element will resend the final service execution result corresponding to the AI ​​service to the terminal device. This can prevent the transmission of the final service execution result corresponding to the AI ​​service from failing, thus ensuring the successful provision of the AI ​​service.

[0161] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0162] Figure 13 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by an AMF network element, such as... Figure 13 As shown, this AI-based service delivery method may include the following steps: Step 1301: Receive feedback results sent by the terminal device. These feedback results are used to provide feedback on the degree of satisfaction with the final service execution result.

[0163] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0164] Figure 14 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a terminal device, such as... Figure 14 As shown, this AI-based service delivery method may include the following steps: Step 1401: Send a second request message to the AMF network element, the second request message indicating the AI ​​service requested by the terminal device.

[0165] Step 1402: Receive the final service execution result corresponding to the AI ​​service sent by the AMF network element.

[0166] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0167] Figure 15 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a terminal device, such as... Figure 15 As shown, this AI-based service delivery method may include the following steps: Step 1501: Send a response message to the AMF network element. This response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0168] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0169] Figure 16 This is a flowchart illustrating a method for providing services based on AI, as provided in an embodiment of this disclosure. The method is executed by a terminal device, such as... Figure 16 As shown, this AI-based service delivery method may include the following steps: Step 1601: Send feedback results to the AMF network element. These feedback results are used to express the degree of satisfaction with the final service execution result.

[0170] In one embodiment of this disclosure, the feedback result may be determined based on the user's rating.

[0171] In summary, in the AI-based service provision method provided by this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Feature Function) element, indicating an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function Element) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0172] Furthermore, Figure 17a Figure 17 illustrates an interactive flow diagram of an AI-based service delivery method provided in this embodiment of the present disclosure. The method includes the following steps: 1) The User Equipment (UE) (i.e., the aforementioned terminal equipment) sends an AIService Establishment Request message (i.e., the aforementioned second request message) to the AMF via (R)AN.

[0173] The AI ​​Service Establishment Request message includes: DNN, AI Service Type (video, language, etc.), AI Service ID, etc.

[0174] 2) AMF sends a CreateAI0Context_Request message to AI0 (i.e., the manager of AI services, the aforementioned first AI network function element) to request the provision of AI services.

[0175] The CreateAI0Context_Request message contains information such as: DNN, AI Service Type (video, language, etc.), AI Service ID, User information, Access type, PEI, and GPSI.

[0176] 3) AI0 analyzes and makes decisions based on the received information, analyzes the AI ​​type of the task, the AI ​​algorithm to be used, and the data category (IID / non-IID) to be used, and notifies each AI sub-function to upload its status information (including energy status, communication conditions, etc.).

[0177] 4) AI sub-function uploads information to AI0.

[0178] 5) AI0 comprehensively judges and selects AI sub-function groups to participate in the AI ​​service based on the information. The training data is divided into several groups based on reference factors such as importance and heterogeneity. Data with higher importance and greater heterogeneity is processed locally by AI0, while the remaining data is sent to the selected AI sub-functions and allocated resource blocks with different weights to achieve the ideal joint training effect. Afterwards, AI0 can send the data allocation results to the UDR network element and / or UDSF network element (this step is...). Figure 17a (Not shown in the image).

[0179] 6 & 7) Network functions UDR and UDSF provide structured and unstructured data sets to AI0 and AI sub-functions respectively. The data allocation is based on the grouping set by AI0. The data source is the data stored in these two NFs when the UE registers and submits a service request.

[0180] 8) AI0 and AI sub-functions are trained synchronously and in parallel, and: 8(a): Feedback the output results to AI0 (i.e., the execution results of the second data mentioned above); 8(b): AI0 aggregates the local training results (i.e., the first data execution results mentioned above) and the received results and performs structured processing to meet the overall requirements.

[0181] 9) AI0 transmits the result (i.e., the final service execution result corresponding to the aforementioned AI service) to AMF for output; 10) The AMF will pass the output result (i.e. the final service execution result corresponding to the aforementioned AI service) to the UE through (R)AN.

[0182] 11) The UE responds that it has received the result (i.e., the terminal device sends a response message to the AMF network element as described above) and provides feedback on the result (satisfied or dissatisfied) (i.e., the terminal device sends feedback results to the AMF network element as described above).

[0183] 12) The overall process of AI function service is completed, and the account is cancelled.

[0184] Figure 17b This is a schematic diagram of the structure of a communication device provided in an embodiment of the present disclosure, as shown below. Figure 17b As shown, the device may include: The transceiver module is used to receive a first request message sent by the Mobility Management Function (AMF) network element, wherein the first request message indicates that there is an AI service requested by the terminal device. The processing module is used to determine the data allocation result based on the first request message. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service from the data required to complete the AI ​​service. The transceiver module is also used to send the data allocation result to the NF network element and receive the data allocated by the NF network element based on the data allocation result; The processing module is further configured to determine the first data execution result based on the data allocated by the NF network element, and to receive the second data execution result sent by the second AI network function network element.

[0185] In summary, in the communication device provided in this embodiment, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Management Function) element, which indicates an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0186] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: The final service execution result corresponding to the AI ​​service is determined based on the first data execution result and the second data execution result. Send the final service execution result corresponding to the AI ​​service to the AMF.

[0187] Optionally, in one embodiment of this disclosure, the first request message includes at least one of the following: The type of AI service requested by the terminal device; The AI ​​service identifier ID corresponding to the AI ​​service requested by the terminal device.

[0188] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: From a plurality of second AI network function elements that are communicatively connected to the first AI network function element, at least one second AI network function element is identified that participates in the execution of AI services.

[0189] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: Determine the AI ​​service type corresponding to the AI ​​service; Determine the AI ​​algorithm required to complete the AI ​​service; Determine the data categories required to complete the AI ​​service; A status request message is sent to a second AI network function network element that is communicatively connected to the first AI network function network element. The status request message is used to request status information related to the AI ​​service execution capability of the second AI network function network element. Receive status information sent by the second AI network function element; At least one second AI network function element is selected to participate in the execution of the AI ​​service based on at least one of the AI ​​service type, AI algorithm, data category, and status information.

[0190] Optionally, in one embodiment of this disclosure, the status information includes at least one of the following: Energy state information; Communication status information.

[0191] Optionally, in one embodiment of this disclosure, the indication information includes at least one of the following: Data name; Data identifier.

[0192] Optionally, in one embodiment of this disclosure, the processing module is further configured to: Based on the first request message, determine the indication information corresponding to the data required to complete the AI ​​service, wherein each indication information is used to indicate a type of data; The indication information is grouped to obtain at least one set of indication information; The first AI network function element and at least one second AI network function element participating in the execution of AI services are respectively assigned instruction information groups to obtain the data allocation result. The instruction information group assigned to the first AI network function element or at least one second AI network function element participating in the execution of AI services is used to indicate that the data group indicated by the instruction information group corresponding to the first AI network function element or the second AI network function element participating in the execution of AI services is allocated to the first AI network function element or the second AI network function element participating in the execution of AI services.

[0193] Optionally, in one embodiment of this disclosure, the processing module is further configured to: The data indication information is grouped based on the importance of the data to the AI ​​service and / or the difficulty of processing the data.

[0194] Optionally, in one embodiment of this disclosure, the processing module is further configured to: Specific instruction information groups are assigned to the first AI network function network element, and other instruction information groups are respectively assigned to at least one second AI network function network element that participates in performing AI services; Among them, the data corresponding to the specific instruction information group is of the greatest importance to the AI ​​service, and / or the data corresponding to the specific instruction information group is the most difficult to process.

[0195] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: Allocate resource blocks with different weights to at least one second AI network function element participating in the execution of AI services; The weight of the resource block allocated to the second AI network function element is positively correlated with the importance and processing difficulty of the data corresponding to the instruction information group allocated to the second AI network function element for the AI ​​service.

[0196] Optionally, in one embodiment of this disclosure, the NF network element includes at least one of the following: User Data Register (UDR) network element; Unstructured data storage function UDSF network element.

[0197] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: The execution results of the first data and the execution results of the second data are aggregated and structured to obtain the final service execution result corresponding to the AI ​​service.

[0198] Optionally, in one embodiment of this disclosure, the first AI network function element and at least one second AI network function element participating in the execution of AI services determine the data execution result in parallel.

[0199] Figure 18 This is a schematic diagram of the structure of a communication device provided in an embodiment of the present disclosure, as shown below. Figure 18 As shown, the device may include: The transceiver module is used to receive data allocated by NF network elements, which is the data required to complete the AI ​​service; The processing module is used to determine the second data execution result based on the data allocated by the NF network element; The transceiver module is also used to send the second data execution result to the first AI network function element.

[0200] In summary, in the communication device provided in this embodiment, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Management Function) element, which indicates an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0201] Optionally, in one embodiment of this disclosure, the NF network element includes at least one of the following: UDR network element; UDSF network element.

[0202] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: Receive a status request message sent by the first AI network function element, wherein the status request message is used to request status information related to the AI ​​service execution capability of the second AI network function element; The status information is sent to the first AI network functional element.

[0203] Optionally, in one embodiment of this disclosure, the status information includes at least one of the following: Energy state information; Communication status information.

[0204] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: Receive the resource block allocated by the first AI network function element.

[0205] Optionally, in one embodiment of this disclosure, the second AI network function element and other second AI network function elements and first AI network function elements determine the data execution result in parallel.

[0206] Figure 19 This is a schematic diagram of the structure of a communication device provided in an embodiment of the present disclosure, as shown below. Figure 19 As shown, the device may include: The transceiver module is used to receive the data allocation result sent by the first AI network function network element. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function network element and at least one second AI network function network element participating in the execution of the AI ​​service from the data required to complete the AI ​​service. The transceiver module is also used to allocate corresponding data to the first AI network function element and at least one second AI network function element participating in the execution of AI services based on the data allocation result.

[0207] In summary, in the communication device provided in this embodiment, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Management Function) element, which indicates an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0208] Optionally, in one embodiment of this disclosure, the indication information includes at least one of the following: Data name; Data identifier.

[0209] Figure 20 This is a schematic diagram of the structure of a communication device provided in an embodiment of the present disclosure, as shown below. Figure 20 As shown, the device may include: The transceiver module is used to receive a second request message sent by the terminal device, wherein the second request message indicates the 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 element, wherein the first request message indicates an AI service requested by a terminal device. The transceiver module is also used to receive the final service execution result corresponding to the AI ​​service sent by the first AI network function element; The transceiver module is also used to send the final service execution result corresponding to the AI ​​service to the terminal device.

[0210] In summary, in the communication device provided in this embodiment, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Management Function) element, which indicates an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0211] Optionally, in one embodiment of this disclosure, both the first request message and the second request message include at least one of the following: The type of AI service requested by the terminal device; The AI ​​service ID corresponding to the AI ​​service requested by the terminal device.

[0212] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: The terminal device receives a response message, which indicates whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0213] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: The system receives feedback results sent by the terminal device, which are used to indicate the level of satisfaction with the final service execution result.

[0214] Figure 21 This is a schematic diagram of the structure of a communication device provided in an embodiment of the present disclosure, as shown below. Figure 21 As shown, the device may include: The transceiver module is used to send a second request message to the AMF network element, the second request message indicating 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.

[0215] In summary, in the communication device provided in this embodiment, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF (Advanced Management Function) element, which indicates an AI service requested by a terminal device. The first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF (Network Function) element and receives data allocated by the NF element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0216] Optionally, in one embodiment of this disclosure, the second request message includes at least one of the following: The type of AI service requested by the terminal device; The AI ​​service ID corresponding to the AI ​​service requested by the terminal device.

[0217] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: A response message is sent to the AMF network element, the response message indicating whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

[0218] Optionally, in one embodiment of this disclosure, the apparatus is further configured to: Feedback results are sent to the AMF network element, and the feedback results are used to indicate the degree of satisfaction with the final service execution result.

[0219] Figure 22 This is a schematic diagram of the structure of a communication system provided in an embodiment of the present disclosure, such as... Figure 22 As shown, the system may include: The first network element (i.e. the aforementioned AMF network element) is used to receive a second request message sent by the terminal device, the second request message indicating the AI ​​service requested by the terminal device, and to send a first request message, the first request message indicating the AI ​​service requested by the terminal device. The second network element (i.e. the aforementioned first AI network function network element) is used to receive the first request message and determine the data allocation result based on the first request message. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function network element and at least one second AI network function network element participating in the execution of the AI ​​service in the data required to complete the AI ​​service, and sends the data allocation result. The third network element (i.e., the aforementioned NF network element) is used to receive the data allocation result and allocate data based on the data allocation result; The second network element is also used to receive data allocated by the third network element based on the data allocation result, and to determine the first data execution result; At least one fourth network element (i.e., the aforementioned second AI network function network element) is used to receive data allocated by the third network element based on the data allocation result, determine the second data execution result, and send the second data execution result; The second network element is also used to receive each second data execution result, and determine the final service execution result corresponding to the AI ​​service based on the first data execution result and the second data execution result, and send the final service execution result corresponding to the AI ​​service; The first network element is also 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.

[0220] In summary, in the communication system provided by the embodiments of this disclosure, a first AI network function element with decision-making capabilities receives a first request message sent by an AMF network element, which indicates an AI service requested by a terminal device. Furthermore, the first AI network function element determines a data allocation result based on the first request message. This data allocation result includes indication information corresponding to the data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service. Subsequently, the first AI network function element sends the data allocation result to the NF network element and receives data allocated by the NF network element based on the data allocation result. Finally, the first AI network function element determines a first data execution result based on the data allocated by the NF network element and receives a second data execution result sent by the second AI network function element. Therefore, the AI ​​service provision method in this disclosure is not a simple superposition of existing network processes, but a complete and universal AI service provision process. Based on this method, the requested AI service can be accurately provided to the terminal device, thereby meeting the needs of personalized AI services. Furthermore, in the method disclosed herein, by grouping the data required to complete the AI ​​service requested by the terminal device and distributing different groups of data to a first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service, the method achieves classified management of AI services and fine-grained division of AI functions, thereby making the subsequent AI service results more accurate. Simultaneously, in the method disclosed herein, the first and second AI network function elements determine the data execution results in parallel, thereby improving execution efficiency. Moreover, in this disclosure, the first AI network function element and multiple second AI network function elements, together with other network elements in the core network, can constitute a unified technical architecture for providing AI services, thus avoiding the problem of fragmented AI application scenarios.

[0221] Please see Figure 23 , Figure 23 This is a schematic diagram of the structure of a communication device 2300 provided in an embodiment of this application. The communication device 2300 can be a network device, a terminal device, a chip, chip system, or processor that supports the implementation of the above methods in a network device, or a chip, chip system, or processor that supports the implementation of the above methods in a terminal device. This device can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0222] The communication device 2300 may include one or more processors 2301. The processor 2301 may be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control the communication device (e.g., base station, baseband chip, terminal equipment, terminal equipment chip, DU or CU, etc.), execute computer programs, and process data from the computer programs.

[0223] Optionally, the communication device 2300 may further include one or more memories 2302, which may store a computer program 2304. The processor 2301 executes the computer program 2304 to cause the communication device 2300 to perform the method described in the above method embodiments. Optionally, the memory 2302 may also store data. The communication device 2300 and the memory 2302 may be provided separately or integrated together.

[0224] Optionally, the communication device 2300 may also include a transceiver 2305 and an antenna 2306. The transceiver 2305 may be referred to as a transceiver unit, transceiver, or transceiver circuit, etc., and is used to implement the transmission and reception functions. The transceiver 2305 may include a receiver and a transmitter. The receiver may be referred to as a receiver or receiving circuit, etc., and is used to implement the receiving function; the transmitter may be referred to as a transmitter or transmitting circuit, etc., and is used to implement the transmitting function.

[0225] Optionally, the communication device 2300 may further include one or more interface circuits 2307. The interface circuits 2307 are used to receive code instructions and transmit them to the processor 2301. The processor 2301 executes the code instructions to cause the communication device 2300 to perform the methods described in the above method embodiments.

[0226] In one implementation, the processor 2301 may include a transceiver for implementing receiving and transmitting functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing receiving and transmitting functions may be separate or integrated. The aforementioned transceiver circuit, interface, or interface circuit can be used for reading and writing code / data, or it can be used for transmitting or relaying signals.

[0227] In one implementation, processor 2301 may store computer program 2303, which runs on processor 2301 and enables communication device 2300 to execute the methods described in the above method embodiments. Computer program 2303 may be embedded in processor 2301; in this case, processor 2301 may be implemented in hardware.

[0228] In one implementation, the communication device 2300 may include circuitry capable of performing the functions of transmitting, receiving, or communicating as described in the foregoing method embodiments. The processor and transceiver described in this application can be implemented on integrated circuits (ICs), analog ICs, radio frequency integrated circuits (RFICs), mixed-signal ICs, application-specific integrated circuits (ASICs), printed circuit boards (PCBs), electronic devices, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductors (CMOS), n-metal-oxide-semiconductor (NMOS), positive-channel metal oxide semiconductors (PMOS), bipolar junction transistors (BJTs), bipolar CMOS (BiCMOS), silicon-germanium (SiGe), gallium arsenide (GaAs), etc.

[0229] 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 vary. Figure 23 The communication device may be a standalone device or part of a larger device. For example, the communication device may be: (1) Independent integrated circuit IC, or chip, or chip system or subsystem; (2) A collection of one or more ICs, optionally including storage components for storing data and computer programs; (3) ASIC, such as modem; (4) Modules that can be embedded in other devices; (5) Receivers, terminal equipment, smart terminal equipment, cellular phones, wireless equipment, handheld devices, mobile units, vehicle-mounted equipment, network equipment, cloud equipment, artificial intelligence equipment, etc. (6) Others, etc.

[0230] For cases where the communication device can be a chip or a chip system, please refer to [link / reference]. Figure 24 The diagram shows the structure of the chip. Figure 24The chip shown includes a processor 2401 and an interface 2402. There can be one or more processors 2401, and multiple interfaces 2402.

[0231] Optionally, the chip also includes a memory 2403, which is used to store necessary computer programs and data.

[0232] Those skilled in the art will also understand that the various illustrative logical blocks and steps listed in the embodiments of this application can be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented through hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the described functionality using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of this application.

[0233] This application also provides a readable storage medium having instructions stored thereon that, when executed by a computer, implement the functions of any of the above method embodiments.

[0234] This application also provides a computer program product that, when executed by a computer, implements the functions of any of the above method embodiments.

[0235] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as 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, all or part of the processes or functions described in the embodiments of this application are generated. 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 transferred from one computer-readable storage medium to another. For example, the computer program can be transferred from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0236] Those skilled in the art will understand that the various numerical designations such as "first," "second," etc., involved in this application are merely for the convenience of description and are not intended to limit the scope of the embodiments of this application, nor do they indicate the order of sequence.

[0237] At least one in this application can also be described as one or more, and multiple can be two, three, four or more, and this application does not impose any limitation. In the embodiments of this application, for a technical feature, the technical features in that technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", and there is no order or size among the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0238] The correspondences shown in the tables of this application can be configured or predefined. The values ​​of the information in each table are merely examples and can be configured to other values; this application is not limited to these values. When configuring the correspondences between information and parameters, it is not necessarily required to configure all the correspondences shown in each table. For example, the correspondences shown in some rows of the tables in this application may not be configured. Furthermore, appropriate modifications and adjustments can be made based on the above tables, such as splitting, merging, etc. The names of the parameters shown in the headings of the above tables can also use other names that the communication device can understand, and the values ​​or representations of the parameters can also be other values ​​or representations that the communication device can understand. In the implementation of 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.

[0239] The term "predefined" in this application can be understood as definition, pre-defined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.

[0240] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art 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.

[0241] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0242] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for providing services based on artificial intelligence (AI), characterized in that, Executed by the first AI network functional element with decision-making capabilities, including: Receive a first request message sent by a Mobility Management Function (AMF) network element, wherein the first request message indicates that there is an AI service requested by a terminal device; The data allocation result is determined based on the first request message. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function element and at least one second AI network function element that participates in the execution of the AI ​​service from the data required to complete the AI ​​service. Send the data allocation result to the network function (NF) element and receive the data allocated by the NF element based on the data allocation result; The first data execution result is determined based on the data allocated by the NF network element, and the second data execution result sent by the second AI network function network element is received.

2. The method as described in claim 1, characterized in that, The method further includes: The final service execution result corresponding to the AI ​​service is determined based on the first data execution result and the second data execution result. Send the final service execution result corresponding to the AI ​​service to the AMF.

3. The method as described in claim 1, characterized in that, The first request message includes at least one of the following: The type of AI service requested by the terminal device; The AI ​​service identifier ID corresponding to the AI ​​service requested by the terminal device.

4. The method as described in claim 1, characterized in that, The method further includes: From a plurality of second AI network function elements that are communicatively connected to the first AI network function element, at least one second AI network function element is identified that participates in the execution of AI services.

5. The method as described in claim 4, characterized in that, The determination of at least one second AI network function element participating in the execution of AI services includes: Determine the type of AI service corresponding to the AI ​​service; Determine the AI ​​algorithm required to complete the AI ​​service; Determine the data categories required to complete the AI ​​service; A status request message is sent to a second AI network function network element that is communicatively connected to the first AI network function network element. The status request message is used to request status information related to the AI ​​service execution capability of the second AI network function network element. Receive status information sent by the second AI network function element; At least one second AI network function element is selected to participate in the execution of the AI ​​service based on at least one of the AI ​​service type, AI algorithm, data category, and status information.

6. The method as described in claim 5, characterized in that, The status information includes at least one of the following: Energy state information; Communication status information.

7. The method as described in claim 1, characterized in that, The indication information includes at least one of the following: Data name; Data identifier.

8. The method as described in claim 1 or 5, characterized in that, The process of determining the data allocation result based on the first request message includes: Based on the first request message, determine the indication information corresponding to the data required to complete the AI ​​service, wherein each indication information is used to indicate a type of data; The indication information is grouped to obtain at least one set of indication information; The first AI network function element and at least one second AI network function element participating in the execution of AI services are respectively assigned instruction information groups to obtain the data allocation result. The instruction information group assigned to the first AI network function element or at least one second AI network function element participating in the execution of AI services is used to indicate that the data group indicated by the instruction information group corresponding to the first AI network function element or the second AI network function element participating in the execution of AI services is allocated to the first AI network function element or the second AI network function element participating in the execution of AI services.

9. The method as described in claim 8, characterized in that, The process of grouping the indication information to obtain at least one set of indication information includes: The data indication information is grouped based on the importance of the data to the AI ​​service and / or the difficulty of processing the data.

10. The method as described in claim 8, characterized in that, The allocation of instruction information groups to the first AI network function element and at least one second AI network function element participating in the execution of AI services includes: Specific instruction information groups are assigned to the first AI network function network element, and other instruction information groups are respectively assigned to at least one second AI network function network element that participates in performing AI services; Among them, the data corresponding to the specific instruction information group is of the greatest importance to the AI ​​service, and / or the data corresponding to the specific instruction information group is the most difficult to process.

11. The method as described in claim 9, characterized in that, The method further includes: Allocate resource blocks with different weights to at least one second AI network function element participating in the execution of AI services; The weight of the resource block allocated to the second AI network function element is positively correlated with the importance and processing difficulty of the data corresponding to the instruction information group allocated to the second AI network function element for the AI ​​service.

12. The method as described in claim 1, characterized in that, The NF network element includes at least one of the following: User Data Register (UDR) network element; Unstructured data storage function UDSF network element.

13. The method as described in claim 2, characterized in that, The step of determining the final service execution result corresponding to the AI ​​service based on the first data execution result and the second data execution result includes: The execution results of the first data and the execution results of the second data are aggregated and structured to obtain the final service execution result corresponding to the AI ​​service.

14. The method as described in claim 1, characterized in that, The first AI network function element and at least one second AI network function element participating in the execution of AI services determine the data execution result in parallel.

15. A method for providing services based on AI, characterized in that, Executed by a second AI network function element with execution capabilities, including: Receive data allocated by the NF network element, the data being the data required to complete the AI ​​service; The second data execution result is determined based on the data allocated by the NF network element; Send the second data execution result to the first AI network functional element; Wherein, the data allocated by the NF network element is allocated by the NF network element based on the data allocation result sent by the first AI network function network element; the data allocation result is determined by the first AI network function network element based on the first request message sent by the mobility management function AMF network element; the first request message indicates the AI ​​service requested by the terminal device; the data allocation result includes: indication information corresponding to the data allocated to the first AI network function network element and at least one second AI network function network element participating in the execution of the AI ​​service from the data required to complete the AI ​​service; the second data execution result and the first data execution result of the first AI network function network element are used to determine the final service execution result.

16. The method as described in claim 15, characterized in that, The NF network element includes at least one of the following: UDR network element; UDSF network element.

17. The method as described in claim 15, characterized in that, The method further includes: Receive a status request message sent by the first AI network function element, wherein the status request message is used to request status information related to the AI ​​service execution capability of the second AI network function element; The status information is sent to the first AI network functional element.

18. The method as described in claim 17, characterized in that, The status information includes at least one of the following: Energy state information; Communication status information.

19. The method as described in claim 15, characterized in that, The method further includes: Receive the resource block allocated by the first AI network function element.

20. The method as described in claim 15, characterized in that, The second AI network function element, along with other second AI network function elements and the first AI network function element, determines the data execution result in parallel.

21. A method for providing services based on AI, characterized in that, Executed by NF network elements, including: Receive data allocation results sent by the first AI network function element, the data allocation results including: indication information corresponding to the data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service in the data required to complete the AI ​​service; Based on the data allocation results, corresponding data are allocated to the first AI network function element and at least one second AI network function element that participates in the execution of AI services. The data allocation result is determined by the first AI network function element based on the first request message sent by the mobility management function (AMF) element; the first request message indicates the AI ​​service requested by the terminal device; the data allocated to the first AI network function element is used to determine the first data execution result, the data allocated to the second AI network function element is used to determine the second data execution result, and the first data execution result and the second data execution result are used to determine the final service execution result.

22. The method as described in claim 21, characterized in that, The indication information includes at least one of the following: Data name; Data identifier.

23. A method for providing services based on AI, characterized in that, Executed by AMF network elements, including: Receive a second request message sent by a terminal device, the second request message indicating the AI ​​service requested by the terminal device; Send a first request message to the first AI network function element, wherein the first request message indicates that there is an AI service requested by a terminal device; Receive the final service execution result corresponding to the AI ​​service sent by the first AI network function element; Send the final service execution result corresponding to the AI ​​service to the terminal device; Wherein, the first request message is used by the first AI network function element to determine the data allocation result, and the data allocation result is used to allocate data to the first AI network function element and at least one second AI network function element; wherein, the data allocated to the first AI network function element is used to determine the first data execution result, the data allocated to the second AI network function element is used to determine the second data execution result, and the first data execution result and the second data execution result are used to determine the final service execution result.

24. The method as described in claim 23, characterized in that, Both the first request message and the second request message include at least one of the following: The type of AI service requested by the terminal device; The AI ​​service ID corresponding to the AI ​​service requested by the terminal device.

25. The method as described in claim 23, characterized in that, The method further includes: The terminal device receives a response message, which indicates whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

26. The method as described in claim 23, characterized in that, The method further includes: The system receives feedback results sent by the terminal device, which are used to indicate the level of satisfaction with the final service execution result.

27. 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, the second request message indicating 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; Wherein, the second request message is used by the AMF network element to send a first request message to the first AI network function network element, the first request message is used by the first AI network function network element to determine the data allocation result, the data allocation result is used to allocate data to the first AI network function network element and at least one second AI network function network element; wherein, the data allocated to the first AI network function network element is used to determine the first data execution result, the data allocated to the second AI network function network element is used to determine the second data execution result, and the first data execution result and the second data execution result are used to determine the final service execution result.

28. The method as described in claim 27, characterized in that, The second request message includes at least one of the following: The type of AI service requested by the terminal device; The AI ​​service ID corresponding to the AI ​​service requested by the terminal device.

29. The method as described in claim 28, characterized in that, The method further includes: A response message is sent to the AMF network element, and the response message is used to indicate whether the terminal device has successfully received the final service execution result corresponding to the AI ​​service.

30. The method as described in claim 27, characterized in that, The method further includes: Feedback results are sent to the AMF network element, and the feedback results are used to indicate the degree of satisfaction with the final service execution result.

31. A communication device, characterized in that, The device is configured in a first AI network functional element with decision-making capabilities, including: The transceiver module is used to receive a first request message sent by the Mobility Management Function (AMF) network element, wherein the first request message indicates that there is an AI service requested by the terminal device. The processing module is used to determine the data allocation result based on the first request message. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function element and at least one second AI network function element participating in the execution of the AI ​​service from the data required to complete the AI ​​service. The transceiver module is also used to send the data allocation result to the NF network element and receive the data allocated by the NF network element based on the data allocation result; The processing module is further configured to determine the first data execution result based on the data allocated by the NF network element, and to receive the second data execution result sent by the second AI network function network element.

32. A communication device, characterized in that, The device is configured to be executed by a second AI network function element with execution capabilities, including: The transceiver module is used to receive data allocated by NF network elements, which is the data required to complete the AI ​​service; The processing module is used to determine the second data execution result based on the data allocated by the NF network element; The transceiver module is also used to send the second data execution result to the first AI network functional element; Wherein, the data allocated by the NF network element is allocated by the NF network element based on the data allocation result sent by the first AI network function network element; the data allocation result is determined by the first AI network function network element based on the first request message sent by the mobility management function AMF network element; the first request message indicates the AI ​​service requested by the terminal device; the data allocation result includes: indication information corresponding to the data allocated to the first AI network function network element and at least one second AI network function network element participating in the execution of the AI ​​service from the data required to complete the AI ​​service; the second data execution result and the first data execution result of the first AI network function network element are used to determine the final service execution result.

33. A communication device, characterized in that, The device is configured in an NF network element and includes: The transceiver module is used to receive the data allocation result sent by the first AI network function network element. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function network element and at least one second AI network function network element participating in the execution of the AI ​​service from the data required to complete the AI ​​service. The transceiver module is also used to allocate corresponding data to the first AI network function element and at least one second AI network function element participating in the execution of AI services based on the data allocation result. The data allocation result is determined by the first AI network function element based on the first request message sent by the mobility management function (AMF) element; the first request message indicates the AI ​​service requested by the terminal device; the data allocated to the first AI network function element is used to determine the first data execution result, the data allocated to the second AI network function element is used to determine the second data execution result, and the first data execution result and the second data execution result are used to determine the final service execution result.

34. A communication device, characterized in that, The device is configured in an AMF network element and includes: The transceiver module is used to receive a second request message sent by the terminal device, wherein the second request message indicates the 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 element, wherein the first request message indicates an AI service requested by a terminal device. The transceiver module is also used to receive the final service execution result corresponding to the AI ​​service sent by the first AI network function network element; The transceiver module is also used to send the final service execution result corresponding to the AI ​​service to the terminal device; Wherein, the first request message is used by the first AI network function element to determine the data allocation result, and the data allocation result is used to allocate data to the first AI network function element and at least one second AI network function element; wherein, the data allocated to the first AI network function element is used to determine the first data execution result, the data allocated to the second AI network function element is used to determine the second data execution result, and the first data execution result and the second data execution result are used to determine the final service execution result.

35. A communication device, characterized in that, The device is configured in a terminal device and includes: The transceiver module is used to send a second request message to the AMF network element, the second request message indicating 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; Wherein, the second request message is used by the AMF network element to send a first request message to the first AI network function network element, the first request message is used by the first AI network function network element to determine the data allocation result, the data allocation result is used to allocate data to the first AI network function network element and at least one second AI network function network element; wherein, the data allocated to the first AI network function network element is used to determine the first data execution result, the data allocated to the second AI network function network element is used to determine the second data execution result, and the first data execution result and the second data execution result are used to determine the final service execution result.

36. A communication device, characterized in that, The device includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program stored in the memory to cause the device to perform the method as claimed in any one of claims 1 to 14, or the processor executes the computer program stored in the memory to cause the device to perform the method as claimed in claims 15 to 20, or the processor executes the computer program stored in the memory to cause the device to perform the method as claimed in claims 21 to 22, or the processor executes the computer program stored in the memory to cause the device to perform the method as claimed in claims 23 to 26, or the processor executes the computer program stored in the memory to cause the device to perform the method as claimed in claims 27 to 30.

37. A communication device, characterized in that, include: Processor and interface circuitry, among which 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 as claimed in any one of claims 1 to 14, or to execute the code instructions to perform the method as claimed in claims 15 to 20, or to execute the code instructions to perform the method as claimed in claims 21 to 22, or to execute the code instructions to perform the method as claimed in claims 23 to 26, or to execute the code instructions to perform the method as claimed in claims 27 to 30.

38. A communication system, characterized in that, The system includes: The first network element is used to receive a second request message sent by a terminal device, the second request message indicating the AI ​​service requested by the terminal device, and to send a first request message, the first request message indicating the AI ​​service requested by the terminal device. The second network element is used to receive the first request message and determine the data allocation result based on the first request message. The data allocation result includes: indication information corresponding to the data allocated to the first AI network function network element and at least one second AI network function network element participating in the execution of the AI ​​service in the data required to complete the AI ​​service, and sends the data allocation result. The third network element is used to receive the data allocation result and allocate data based on the data allocation result; The second network element is also used to receive data allocated by the third network element based on the data allocation result, and to determine the first data execution result; At least one fourth network element is configured to receive data allocated by the third network element based on the data allocation result, determine the second data execution result, and send the second data execution result. The second network element is also used to receive each second data execution result, and determine the final service execution result corresponding to the AI ​​service based on the first data execution result and the second data execution result, and send the final service execution result corresponding to the AI ​​service; The first network element is also 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.

39. A computer-readable storage medium for storing instructions that, when executed, cause the method of any one of claims 1 to 14 to be implemented, or when executed, cause the method of claims 15 to 20 to be implemented, or when executed, cause the method of claims 21 to 22 to be implemented, or when executed, cause the method of claims 23 to 26 to be implemented, or when executed, cause the method of claims 27 to 30 to be implemented.

Images