Service joint processing method based on artificial intelligence, network node and terminal

Abstract

The invention provides a service joint processing method based on artificial intelligence, a network node and a terminal, and relates to the field of artificial intelligence and communication. The method is executed by a network node supporting an artificial intelligence service in a wireless communication system, and the method comprises the following steps: determining an AI-based joint computing task to be executed; determining at least one first terminal participating in the joint computing task; related information of the joint computing task is sent to each first terminal, so that at least one second terminal participates in the joint computing task based on the related information, and the at least one second terminal is part of or all of the at least one first terminal. According to the invention, the terminal can be combined to realize AI-based combined calculation.

Description

Technical Field

[0001] The embodiments of the present application belong to the field of communication technology and may involve artificial intelligence technology, and specifically relate to a service joint processing method, network node and terminal based on artificial intelligence. Background Art

[0002] At present, although business processing solutions based on artificial intelligence (AI) can effectively speed up business processing efficiency, due to the limitations of terminal privacy and network bandwidth in communication systems, the practical application of many business processing solutions based on AI will be limited. How to integrate AI technology into wireless communication systems is a technical issue that technicians in related fields are currently studying. At present, the business processing method based on AI in wireless communication networks is not yet clear. Summary of the invention

[0003] The embodiments of the present application provide a service joint processing method based on artificial intelligence, a network node and a terminal, which can realize AI-based joint computing in conjunction with the terminal.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] On the one hand, an embodiment of the present application provides a service joint processing method based on artificial intelligence, which is applied to a wireless communication system. The method is executed by a network node in the wireless communication system, and the network node supports artificial intelligence services. The method includes:

[0006] Determine the joint computing tasks based on artificial intelligence (AI) to be performed;

[0007] Determining at least one first terminal participating in the joint computing task;

[0008] Sending relevant information of the joint computing task to each of the first terminals, so that at least one second terminal participates in the joint computing task based on the relevant information, the at least one second terminal being part or all of the at least one first terminal;

[0009] Among them, the relevant information includes task information and session parameter information, the task information includes indication information of AI model information, the indication information of the AI ​​model is used to indicate the target AI model called by the terminal to participate in the joint computing task, and the session parameter information is used for the terminal to establish a data transmission channel with the data network corresponding to the joint computing task.

[0010] On the other hand, an embodiment of the present application provides a service joint processing device based on artificial intelligence, the device comprising:

[0011] A task determination module, used to determine the joint computing tasks to be performed based on artificial intelligence AI;

[0012] The terminal determination module is further used to determine at least one first terminal participating in the joint computing task;

[0013] A task sending module is used to send relevant information of the joint computing task to each of the first terminals, so that at least one second terminal participates in the joint computing task based on the relevant information, and the at least one second terminal is part or all of the at least one first terminal; wherein the relevant information includes task information and session parameter information, the task information includes indication information of the AI ​​model, the indication information of the AI ​​model is used to indicate the target AI model called by the terminal to participate in the joint computing task, and the session parameter information is used for the terminal to establish a data transmission channel with the data network corresponding to the joint computing task.

[0014] Optionally, the terminal determination module is further used to determine the terminal requirement information participating in the joint computing task;

[0015] Acquiring terminal information of at least one third terminal;

[0016] Based on the terminal information of each of the third terminals, at least one first terminal that meets the terminal requirement information is determined from the at least one third terminal.

[0017] Optionally, whether a first terminal participates in the joint computing task depends on the first terminal.

[0018] Optionally, whether a first terminal participates in the joint computing task may be determined based on at least one of the following:

[0019] The location information of the first terminal, and the resource information of the first terminal or the intention of the user of the first terminal.

[0020] Optionally, the terminal determination module is further used to send a first request to a target network element, where the first request is used to request terminal information, and the target network element is associated with at least one of a task type of the joint computing task or the terminal requirement information;

[0021] receiving terminal information of at least one third terminal sent by the target network element in response to the first request.

[0022] Optionally, the terminal requires that the information be associated with a task type of the joint computing task.

[0023] Optionally, the first request includes a terminal constraint condition, and the terminal constraint condition is associated with at least one of the task type or the terminal requirement information;

[0024] The terminal information of the at least one third terminal is determined by the target network element based on the terminal constraint condition.

[0025] Optionally, the target network element is associated with the task type;

[0026] Optionally, the task type includes at least one of the following:

[0027] Tasks related to the performance of the terminal; Tasks related to the location of the terminal; Tasks related to the session of the terminal;

[0028] Optionally, the target network element satisfies at least one of the following:

[0029] The target network elements corresponding to the tasks related to the performance of the terminal include network storage network elements;

[0030] The target network elements corresponding to the tasks related to the location of the terminal include a mobility management network element;

[0031] The target network elements corresponding to the tasks related to the session of the terminal include the session management network elements.

[0032] Optionally, the terminal determination module is further used to receive response information sent by each of the first terminals, where the response information is used to instruct the first terminal to participate in the joint computing task, or to instruct the first terminal not to participate in the joint computing task.

[0033] Optionally, the task sending module is further used to send the relevant information to each first terminal through a base station.

[0034] Optionally, the sending the relevant information of the joint computing task to each of the first terminals includes any one of the following:

[0035] Sending first information to each of the first terminals, where the first information includes a container, and the container includes various information of the related information;

[0036] Sending second information to each of the first terminals, where the second information includes each item of information in the related information.

[0037] Optionally, the network node is a newly added network element in the wireless communication system, or is any one of the following in the wireless network system: a network data analysis network element, a mobility management network element, a session management network element, and a policy control network element.

[0038] Optionally, the indication information of the AI ​​model includes at least one of the task type or AI model information of the joint computing task;

[0039] Optionally, the task information further includes at least one of the following:

[0040] Task instruction information, task validity information, and first instruction information;

[0041] Among them, the indication information of the task is used to indicate the subtask of the joint computing task executed by the terminal; the effective information of the task is used to indicate the execution time information of the task; and the first indication information is used to indicate information related to the return of the task processing result.

[0042] Optionally, the artificial intelligence-based service joint processing device further includes a result receiving module, and the result receiving module is used to perform at least one of the following:

[0043] receiving a task processing result corresponding to the task information sent by the at least one second terminal, and providing the task processing result to a service server corresponding to the joint computing task;

[0044] Receive the task processing result corresponding to the task information sent by the at least one second terminal, determine the final processing result of the joint processing task based on the received task processing result, and provide the final processing result to the service server.

[0045] Optionally, the task information also includes result requirement information for the task processing result.

[0046] On the other hand, an embodiment of the present application provides an artificial intelligence-based service joint processing method, which is applied to a wireless communication system. The method is executed by a terminal in the wireless communication system. The method includes:

[0047] Receiving relevant information of an artificial intelligence-based joint computing task sent by a network node, the network node supporting artificial intelligence services, the relevant information including task information and session parameter information, the task information including indication information of an artificial intelligence AI model;

[0048] Based on the session parameter information, sending a session establishment request to establish a data transmission channel between the data networks corresponding to the joint computing task;

[0049] Interact with the data network through the data transmission channel, and call the target AI model corresponding to the indication information of the AI ​​model to participate in the joint computing task.

[0050] On the other hand, an embodiment of the present application provides a service joint processing device based on artificial intelligence, the device comprising:

[0051] An information receiving module receives relevant information of an artificial intelligence-based joint computing task sent by a network node, wherein the network node supports artificial intelligence services, the relevant information includes task information and session parameter information, and the task information includes indication information of an artificial intelligence AI model;

[0052] A request sending module, used to send a session establishment request based on the session parameter information to establish a data transmission channel between the data networks corresponding to the joint computing task;

[0053] A data interaction module is used to interact with the data network through the data transmission channel, and call the target AI model corresponding to the indication information of the AI ​​model to participate in the joint computing task.

[0054] Optionally, the request sending module is further used to send response information to the network node, where the response information is used to instruct the terminal to participate in the joint computing task, or to instruct the terminal not to participate in the joint computing task;

[0055] Optionally, sending a session establishment request based on the session parameter information includes:

[0056] In a case where the terminal determines to participate in the joint computing task, a session establishment request is sent based on the session parameters.

[0057] Optionally, the request sending module is further used to send a session release request to release the data transmission channel.

[0058] On the other hand, an embodiment of the present application further provides a network node, the network node comprising a transceiver and a processor coupled to the transceiver, the processor being configured to implement the artificial intelligence-based service joint processing method provided in any optional embodiment of the present application.

[0059] On the other hand, an embodiment of the present application further provides a terminal, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the artificial intelligence-based business joint processing method provided in any optional embodiment of the present application when running the computer program.

[0060] On the other hand, an embodiment of the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the artificial intelligence-based business joint processing method provided in any optional embodiment of the present application.

[0061] The beneficial effects of the technical solution provided by the embodiment of the present application are as follows:

[0062] In an embodiment of the present application, for the joint computing tasks corresponding to the artificial intelligence-based services, the first network element in the wireless communication system determines the joint computing tasks corresponding to the services, and sends the relevant information of the joint computing tasks to at least one first terminal, so that at least one second terminal participates in the joint computing tasks based on the relevant information. In this way, the terminals in the wireless communication system can be integrated to participate in the joint computing, thereby realizing AI-based joint computing with the participation of the terminals. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figures 1A-1C It is a flowchart of a service joint processing method based on artificial intelligence provided by an embodiment of the present application;

[0064] Figure 2 It is a flowchart of a service joint processing method based on artificial intelligence provided by an embodiment of the present application;

[0065] Figure 3 is a flow chart of a method for determining a first terminal provided in an embodiment of the present application;

[0066] Figure 4 This is another flowchart of a service joint processing method based on artificial intelligence provided by an embodiment of the present application;

[0067] Figure 5 This is an example diagram of a business joint processing method based on artificial intelligence in an embodiment of the present application;

[0068] Fig. 6A Schematic diagram of an artificial intelligence service joint processing device provided in an embodiment of the present application;

[0069] Figure 6B is another schematic diagram of the artificial intelligence service joint processing device provided in an embodiment of the present application;

[0070] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0071] The embodiments of the present application are described below in conjunction with the drawings in the present application. It should be understood that the implementation methods described below in conjunction with the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0072] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present application refer to that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude the implementation as other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the one element may be directly connected or coupled to the other element, or it may refer to that the one element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" may be implemented as "A", or as "B", or as "A and B". When describing multiple (two or more) items, if the relationship between the multiple items is not clearly defined, the multiple items may refer to one, multiple or all of the multiple items. For example, the description of "parameter A includes A1, A2, A3" can be implemented as parameter A including A1 or A2 or A3, and can also be implemented as parameter A including at least two of the three items A1, A2, A3.

[0073] The embodiment of the present application is a method for joint business processing based on artificial intelligence, which is proposed in response to the current technology of supporting AI services in wireless communication networks, which cannot implement business processing solutions based on AI calculations by specific network elements due to terminal privacy and network bandwidth limitations. The method provided in the embodiment of the present application can integrate at least one terminal in the wireless communication system to participate in AI-based joint computing tasks.

[0074] The service joint processing method provided in the embodiment of the present application is implemented based on AI technology.

[0075] Artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Artificial intelligence technology is an interdisciplinary subject that covers a wide range of fields, including both hardware-level technology and software-level technology. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operating / interactive systems, and mechatronics. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, as well as machine learning / deep learning, autonomous driving, and smart transportation.

[0076] Machine Learning (ML) is a multi-disciplinary interdisciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning. With the research and progress of artificial intelligence technology, artificial intelligence technology has been widely studied and applied in many fields. It is believed that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.

[0077] Optionally, the business joint processing method based on artificial intelligence involved in the embodiment of the present application can be implemented based on cloud technology. For example, the data calculation involved in the above-mentioned terminal participating in the joint computing task and the data calculation involved in the process of network nodes determining the target result of the joint computing task can be implemented based on cloud computing. Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and network in a wide area network or a local area network to realize the calculation, storage, processing, and sharing of data. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model application, which can form a resource pool, which is used on demand and is flexible and convenient. Cloud computing technology will become an important support. Cloud computing refers to the delivery and use mode of IT infrastructure, which refers to obtaining the resources required for the business in an on-demand and easily scalable manner through the network, such as computing resources, storage resources, network resources, etc.; generalized cloud computing refers to the delivery and use mode of services, which refers to obtaining the required services in an on-demand and easily scalable manner through the network.

[0078] It should be noted that in the optional embodiments of the present application, the terminals involved, the terminal user information and other related data, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0079] In order to better understand the solutions of the embodiments of the present application, the nouns and terms involved in the embodiments of the present application are explained below. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0080] 1) Explain the following network elements in the 5G communication network:

[0081] The Access and Mobility Management Function (AMF) network element can be used to manage terminal access to the core network, such as terminal location update, network registration, access control, terminal mobility management, terminal attachment and detachment, etc.

[0082] The session management function (SMF) network element can be used to select user plane network elements for the terminal, redirect user plane network elements for the terminal, establish a bearer (also called a session) between the terminal and the user plane function (UPF) network element, modify and release the session, and control the quality of service (QoS).

[0083] The Unified Data Management (UDM) is also called the network storage element, which is similar to the 4G HSS in terms of 3GPP AKA authentication, user identification, access authorization, registration, mobility, subscription, and SMS management. UDM includes functions such as the generation and storage of user contract data and the management of authentication data.

[0084] Policy Control function (PCF), a unified policy framework, provides policy rules for control plane functions, similar to PCRF in 4G. PCF network elements are used to provide policies to AMF network elements and SMF network elements, such as QoS policies and slice selection policies.

[0085] The data network (DN) can provide data services to users, such as IP multimedia service (IMS) network, Internet, etc. There can be multiple application servers (AS) in the DN, providing different application services, such as operator services, Internet services, etc.

[0086] The user plane function (UPF) network element is mainly responsible for the transmission of user data, and other network elements can be called control plane function network elements, which are mainly responsible for authentication, authorization, registration management, session management, mobility management and policy control, etc., to ensure reliable and stable transmission of user data. UPF network elements can be used to forward and receive terminal data. For example, the UPF network element can receive service data from the data network and transmit it to the terminal through the access network device; the UPF network element can also receive user data from the terminal through the access network device and forward it to the data network. Among them, the transmission resources allocated and scheduled by the UPF network element to the terminal are managed and controlled by the SMF network element. The bearer between the terminal and the UPF network element may include: the user plane connection between the UPF network element and the access network device, and the establishment of a channel between the access network device and the terminal. Among them, the user plane connection is a QoS flow that can be established between the UPF network element and the access network device to transmit data.

[0087] AF network elements are used to interact with core network elements to support application-affected data routing, access network exposure functions, and interact with PCF network elements for policy control.

[0088] 2) Network slicing: Network slicing is an on-demand networking method that allows operators to separate multiple virtual end-to-end networks on a unified infrastructure. Each network slice is logically isolated from the wireless access network to the bearer network and then to the core network to adapt to various types of applications. In a network slice, it can be divided into at least three parts: wireless network sub-slices, bearer network sub-slices, and core network sub-slices. The core of network slicing technology is NFV (network function virtualization). NFV separates the hardware and software parts from the traditional network. The hardware is deployed by a unified server, and the software is undertaken by different network functions (NFs), thereby realizing the needs of flexible assembly of services. Network slicing is based on the concept of logic and is a reorganization of resources. The reorganization is to select the required virtual machines and physical resources for specific communication service types according to SLA (service level agreement).

[0089] 3) Protocol Data Unit (PDU) session: A key function of the 5G system, which can provide a connection to the DN for the terminal UE. In order to connect to the DN, the UE needs to initiate a request for establishing a PDU session. The destination of the connection is provided by the UE in the form of a data network name (DNN). The DNN is the code of the target data network (DN). The DNN can be an operator connected to the Internet, a custom DNN; the DNN can also be a well-known DNN, such as a DNN to the IMS network. Among them, the simplified PDU session establishment process is as follows: the UE initiates a PDU session request to the SMF through the base station and AMF; after receiving the request, the SMF obtains the subscription data of the UE from the UDM; after receiving the request, the SMF obtains the policy rules for this type of user from the PCF; after receiving the request, the SMF establishes a session with the UPF to establish a user plane connection; the SMF initiates a wireless resource request to the base station; after receiving the request, the base station sets the corresponding wireless resources and replies to the SMF's request; after receiving the reply, the SMF updates the UPF to establish a tunnel from the UPF to the base station; and finally generates a tunnel: UE<->AN<->UPF. The UE reaches the UPF through the tunnel to connect to the target DN. During the PDU session establishment process, the corresponding user plane connection (UE<–>DN) will be activated. The role of this user plane connection is to: transmit PDU (Protocol Data Units); PDU is the protocol type of the end user carried on the PDU session; the type of PDU depends on the type of PDU session (for example, IP data packet or Ethernet frame).

[0090] The following describes a variety of optional implementation methods to illustrate the technical solutions provided by the present application and the technical effects produced by the technical solutions. In the absence of conflicts or contradictions, the following implementation methods can refer to, draw on or combine with each other, and the same terms, similar features and similar implementation steps in different implementation methods will not be described repeatedly. For the interaction steps between different nodes, it is possible to derive the corresponding solution of the network node on the other side based on the description of the solution for the network node on one side, such as when a network node receives configuration information from another network node, it can be concluded that the other network node sends configuration information to the above-mentioned network node. In an embodiment including multiple steps, if there is no clear order of precedence for the multiple steps, the embodiment of the present application does not make a unique limitation on the implementation order of the multiple steps.

[0091] In order to better meet the needs of various wireless communication scenarios and solve or improve one or more of the current problems, the artificial intelligence-based service joint processing method provided in the embodiment of the present application is applied to a wireless communication system, which can be executed by a network node or terminal in the wireless communication system, or it can be executed jointly by the terminal and the network node. Among them, the network node can support artificial intelligence services, the network node can be a newly added network element in the wireless communication network that can support artificial intelligence services, and the network node can also be an existing network element that has additional support for AI services. For ease of description, the network node that executes the AI-based service joint processing method provided in the embodiment of the present application may be referred to as the first network element. As an example, the artificial intelligence-based service joint processing system provided in the embodiment of the present application is described. Figures 1A-1C This is a schematic diagram of the architecture of the business joint processing system based on artificial intelligence provided by the embodiment of the present application. In order to support a business joint processing application based on artificial intelligence, see Figure 1A , Figure 1AThe service joint processing system based on artificial intelligence includes a terminal 400 (terminal 400-1 and terminal 400-2 are shown as examples), a wireless communication network 300 (including multiple network nodes, a newly added network element 310, a session management network element 320, and a mobility management network element 330 are shown as examples), and a data network 200 (data network 200-1 and data network 200-2 are shown as examples), wherein the terminal 400 is connected to the data network 200 through the wireless communication network 300, the first network element is the newly added network element 310 in the figure, which can support AI services, and the session management network element 320 and the mobility management network element 330 are network elements that already exist in the wireless communication network. The terminal 400 accesses the core network of the wireless communication network through a base station. The data network 200 (data network 200-1 and data network 200-2 are shown as examples) is related to the joint computing task, and the wireless communication network 300 assists the terminal 400, the data network 200, and the service network server 300 to jointly complete the joint computing task. In actual implementation, the first network element 310 is used to determine the AI-based joint computing task to be executed after the condition / timing for executing the joint computing task is triggered, and determine the first terminal that can participate in the joint computing according to at least one of the task type of the joint computing task, the terminal requirement information for the terminal, and the indication information of the AI ​​model, and send the relevant information of the joint computing task to each first terminal, after receiving the response information of the second terminal (part or all of the terminals in at least one first terminal 400) agreeing to participate in the joint computing task based on the relevant information, receive the session establishment request sent by the second terminal according to the session parameters, and establish a data transmission channel between the second terminal and the data network 200 corresponding to the joint computing task through the network element 320 with a session management function in the wireless communication network 300, so that the second terminal participates in the joint computing task through the data transmission channel. Subsequently, the first network element 310 receives the task processing result of each second terminal, forwards it to the service server 500 that finally performs the joint computing task, and the service server determines the final processing result of the joint computing task based on the processing results of each task. That is to say, at this time, the first network element has the ability to determine the final processing result of the joint computing task.

[0092] Continue to see Figure 1BAt this time, the first network element 310 is a newly added network element in the wireless communication network, and has the ability to determine the final processing result of the joint computing task. The first network element 310 exists as a functional module in the service server 500, and the service server 500 also includes a service processing function 510. With the assistance of the wireless communication network 300, the first network element 310 and the first terminal 400 obtain the task processing result corresponding to each second terminal participating in the joint computing task, and then determine the final processing result of the joint computing task based on the received task processing results, and provide the final processing result to the service processing function 510 in the service server 500 corresponding to the joint computing task to perform subsequent processing, such as processing result statistics.

[0093] Continue to see Figure 1C , Figure 1C The first network element 310 is an existing session management network element 320 in the wireless communication network 300. The network element has newly added a function based on AI services and can support joint computing tasks. The first network element receives a task processing request, confirms the joint computing task corresponding to the task processing request, and determines at least one first terminal 400 participating in the joint computing task based on the relevant information of the joint computing task, receives a response message from at least one first terminal 400 (i.e., the second terminal) confirming participation in the joint computing task, and receives a session establishment request sent by the second terminal to establish a data transmission channel between the second terminal and the corresponding data network 200. When the first network element has the ability to determine the final processing result of the joint processing task, the first network element receives the task processing result determined by each second terminal, and then determines the final processing result of the joint computing task based on the task processing result, and sends it to the business server 500.

[0094] Optionally, the above-mentioned terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, an intelligent voice interaction device (such as a smart speaker), a wearable electronic device (such as a smart watch), a vehicle-mounted terminal, a smart home appliance (such as a smart TV), a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, etc., but is not limited to this. The business server corresponding to the above-mentioned artificial intelligence-based business can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal and the server can be directly or indirectly connected via wireless communication, which is not limited in the embodiments of the present application.

[0095] It should be noted that some of the term names involved in the embodiments of the present application may adopt the term names that already exist in the communication standards, and some term names may be newly added or newly defined term names. The names of these newly added or newly defined terms may also adopt other names in future communication standards, or may be described in other ways (such as a text description). The names or names of the various information / messages / parameters / configurations involved in the embodiments of the present application are not unique. As long as the role of the information / message / parameter / configuration, the content contained, or the description or description of the information / message / parameter / configuration can correspond or be associated, the name or name of the information / message / parameter / configuration can be changed. For example, the configuration information in the embodiments of the present application may also be referred to as the first message or other message or signal configuration information, the first information may also be referred to as sequence information, the second information may also be referred to as resource information, the resource information may be frequency domain resource information and / or time domain resource information, and the first signal may also be referred to as a perception signal, a channel estimation signal, a physical signal or other names.

[0096] Take a network node in a wireless communication system executing an artificial intelligence-based service joint processing method provided in an embodiment of the present application as an example for explanation, see Figure 2 , Figure 2 is a flow chart of a service joint processing method based on artificial intelligence provided by an embodiment of the present application, such as Figure 2 As shown in , the artificial intelligence-based business joint processing method provided in the embodiment of the present application may include the following steps S101 to S103.

[0097] Step S101: Determine the joint computing task based on artificial intelligence AI to be executed.

[0098] It should be noted that the network node described in the embodiments of the present application may also be referred to as a network element, a network function, a functional entity or a network unit, etc. For ease of description, the network node executing the embodiments of the present application is referred to as a first network element. The tasks in the embodiments of the present application are computing tasks related to specific services, and joint processing / joint computing refers to computing processing of tasks jointly participated in by multiple electronic devices, such as executing part of the AI ​​computing by the terminal and executing part of the AI ​​computing by the service server. For example, the service server determines the target result of the task based on the task processing result of the terminal.

[0099] In an embodiment of the present application, the first network element may be an existing network element in the wireless communication system or a newly added network element. The first network element supports artificial intelligence services, that is, the first network element may perform business processing based on an AI model (such as a neural network model). Optionally, at least one AI model may be deployed in the first network element, each AI model having its own corresponding function, and the first network element may perform business processing by calling the AI ​​model.

[0100] As an optional solution of the present application, the first network element may be a newly added network element in the wireless communication system, and the name of the newly added network element is not limited in the present application embodiment. Optionally, the first network element is an existing network element in the wireless communication system in which the artificial intelligence service is deployed. For example, the first network element may be but is not limited to any existing network element in the 4G communication system, 5G communication system or 6G communication network, such as a network element of the core network. Taking the 5G communication system as an example, as an optional solution, the first network element may be but is not limited to any of the following network elements:

[0101] Network data analysis NWDAF network element, mobility management AMF network element, session management SMF network element or policy control PCF network element.

[0102] It should be noted that for wireless communication systems with different architectures, the names and functions of existing network elements may be different, and the names of network elements with similar or identical functions in different communication systems may also be different. For example, the function of the AMF network element in the 5G communication system is similar to the Mobility Management Entity (MME) in the 4G communication system.

[0103] In actual implementation, the embodiments of the present application do not limit the conditions / timing for triggering the execution of the joint computing task (that is, the timing for executing the method provided in the embodiments of the present application). Optionally, the first network element may execute the joint computing task upon receiving the execution command of the joint computing task, or the first network element may trigger the execution of the joint computing task according to a preconfigured joint computing task execution strategy. For example, there are three types of joint computing tasks, and each task has preconfigured task triggering conditions / task execution conditions (such as periodic execution according to a preset period). When the condition is met, the first network element can determine the joint computing task to be executed.

[0104] Optionally, the first network element may trigger the execution of the joint computing task corresponding to the target business when receiving a business processing request for the target business, such as generating a joint computing task corresponding to the target business. Optionally, the business processing request may be triggered by the manager of the target business through the management client. Optionally, the first network element receives a task processing request from one or more business servers corresponding to the business based on artificial intelligence services, determines the relevant information of the joint computing task according to the task processing request of the business server, and generates a corresponding joint computing task. Determining the relevant information of the joint computing task may include, but is not limited to, confirmation of one or more of the following information:

[0105] The task type of joint computing task, the terminal requirements information participating in the joint computing task, the result requirements information for the business processing results returned by the terminal, the relevant information of the corresponding AI model or the transmission of the joint computing task related content, session parameters, etc.

[0106] Among them, the task type of the joint computing task refers to the classification of the joint computing task. In actual implementation, the first network element can support multiple different types of joint computing tasks, wherein the correspondence between the service and the joint computing task can be one-to-one or one-to-many, that is, one service can correspond to one or more joint computing tasks, and each joint computing task may realize different service processing requirements. The specific classification method of the task is not limited in the embodiment of the present application, and can be configured according to actual application requirements, and each task corresponds to its own task processing strategy / process. For example, the task type can be divided according to the function implemented by the task. For example, the task type may refer to calculations related to the terminal location information (location-based calculations), or calculations related to the communication session content of the terminal, or calculations related to the terminal's own performance, etc.

[0107] For example, for the above-mentioned location calculation, it can be a calculation task to predict the movement trajectory, movement speed or other parameters of the terminal. For the communication session calculation, it can be a calculation task related to predicting the bandwidth of the terminal, or predicting the service type of the terminal access content. The calculation related to the terminal's own performance can be a calculation task related to the power of the terminal, such as a task for predicting the power consumption of the terminal.

[0108] Among them, the terminal requirement information for participating in the joint computing task refers to the conditions that the terminal participating in the joint computing task needs to meet. The reason for confirming the terminal requirement information for participating in the joint computing task is that some terminals in the communication system (or terminals in some cases) may not have the ability to participate in one or some joint computing tasks. When executing the joint computing task, according to the terminal requirement information, the first network element can initiate a joint computing request to the terminal that meets the conditions, that is, the first network element sends the task information of the joint computing task to the terminal that meets the conditions. For example, the joint computing task needs to be participated by a terminal in a specific location, and a terminal that is not in the specific location may not be suitable for participating in the joint computing task; for another example, the joint computing task requires the participation of a terminal that can access a specific slice or a specific type of data network, then the terminal that cannot range the specific slice or a specific type of data network is not suitable for participating in the joint computing task. Optionally, for any joint computing task, the task may have corresponding terminal requirement information or not. The terminal requirement information corresponding to each task can be pre-configured or agreed upon according to actual application requirements.

[0109] The above-mentioned result requirement information for the business processing results returned by the terminal refers to the information that the terminal participating in the joint computing task needs to return after performing the corresponding calculation according to the task information issued by the first network element. The result requirement information specifically includes which information can be pre-configured or agreed upon. Optionally, the result requirement information may include but is not limited to which specific parameters to return, and may also include the data format when returning the parameters.

[0110] The relevant information of the corresponding AI model refers to the information of the AI ​​model required for the joint computing task, such as the model identifier of the AI ​​model, the task type associated with the AI ​​model, etc. The session parameters for transmitting the content related to the joint computing task refer to the multiple parameters required to establish a data transmission channel between the terminal and the data network associated with the joint computing task, which may include but are not limited to network slicing information, DNN information, business continuity information, AI model information, etc.

[0111] Step S102: Determine at least one first terminal participating in the joint computing task.

[0112] The specific method for determining at least one first terminal participating in the joint computing task is not limited in the embodiments of the present application. Optionally, the at least one first terminal may be any number of terminals in the wireless communication system. Optionally, the at least one first terminal may be a plurality of terminals determined according to the terminal requirement information of the joint computing task, or may be one or more terminals determined according to the task type of the joint computing task.

[0113] As an optional solution of this application, Figure 3 is a flow chart of a determination method of a first terminal provided in an embodiment of the present application, Figure 2 Step S102 can be implemented by steps S1021 to S1023.

[0114] Step S1021: Determine the terminal requirement information for participating in the joint computing task.

[0115] Optionally, the terminal requirement information is associated with the task type of the joint computing task. The terminal requirement information is the conditions that the terminal participating in the joint computing task needs to meet, such as the location information of the terminal, the network slice or DNN type that the terminal can access, the computing resources of the terminal, the security indicators of the terminal, etc.

[0116] Step S1022: Acquire terminal information of at least one third terminal.

[0117] Optionally, the specific method of obtaining terminal information is not limited in the embodiments of the present application. Optionally, the terminal information of at least one third terminal can be the terminal information of any terminal that can be obtained by the first network element. For example, the first network element can be a mobility management network element, and the third terminal can be a terminal managed by the network element; for another example, the first network element can be a newly added network element, which can communicate with other network elements (such as a mobility management network element) in the wireless communication system to obtain terminal information of multiple terminals from other network elements.

[0118] In an embodiment of the present application, the terminal information of each terminal refers to information related to the terminal. For different joint computing tasks or terminal requirement information, the terminal information to be obtained may be different or the same. Optionally, each joint computing task has its own corresponding terminal information. Optionally, the terminal information may include, but is not limited to, one or more of the terminal identification, the terminal capability information (such as the computing capability of the terminal or the services supported by the terminal), the AI ​​model information that the terminal can support, the terminal location information, or the current performance information of the terminal.

[0119] As an optional solution of the present application, the first network element may obtain the terminal information of at least one third terminal in the following manner:

[0120] Sending a first request to a target network element, wherein the first request is used to request terminal information, and the target network element is associated with at least one of a task type of the joint computing task or terminal requirement information;

[0121] The terminal information of at least one third terminal sent by the target network element in response to the first request is received.

[0122] In actual implementation, after confirming the joint computing task, the first network element may send a first request for terminal information to the corresponding target network element in the wireless communication network according to the terminal requirement information or task type associated with the joint computing task, and obtain at least one terminal information adapted to the terminal requirement information returned by the target network element, so as to confirm at least one first terminal that can participate in the joint computing task based on the obtained terminal information. The first terminal may be part or all of the third terminals.

[0123] In a wireless communication system, different network elements have their own corresponding functions. Since different joint computing tasks correspond to different terminal requirements, the terminal information that needs to be obtained is likely to be different. If the first network element itself does not have the ability to manage terminal information, such as the first network element is an independent new network element in the communication system, after determining the task type or terminal requirement information of the joint computing task, the first network element can send a request to other network functions of the communication system based on at least one of the task type or terminal requirement information to obtain the terminal information of at least one third terminal.

[0124] Optionally, the at least one first terminal is all terminals in the at least one third terminal, and the terminal information includes a unique identifier of the terminal. For this optional method, the first request sent by the first network element to the target network element may include terminal requirement information for participating in the joint computing task, and the target network element may return terminal information of at least one third terminal that meets the requirement to the first network element according to the terminal requirement information.

[0125] Optionally, at least one first terminal may be a terminal that meets the conditions and is screened out from at least one third terminal based on the terminal requirement information. In this optional solution, the first request sent by the first network element to the target network element may include at least one item of information of the multiple requested terminals, and the at least one item of information is associated with at least one item of the terminal requirement information or the task type. For example, the terminal that can participate in the joint computing task needs to be a terminal at a specific location, and the at least one item of information may include the terminal location. The target network element returns terminal information including the terminal identification and the terminal location information to the first network element based on the information carried in the first request. After receiving the terminal information of multiple third terminals returned by the target network element, the first network element may select a third terminal at a specific location as the first terminal based on the location of the third terminal.

[0126] As an example, in a 5G communication network, the first network element can obtain terminal information located at a specific location from the mobility management network element AMF, and can obtain terminal information with specific computing resources from the network storage network element UDM, etc.

[0127] Optionally, the first request also includes a terminal constraint condition, and the terminal constraint condition is associated with at least one of the task type or terminal requirement information; the terminal information of the at least one third terminal is determined by the target network element based on the terminal constraint condition.

[0128] The terminal constraint information indicates the conditions that the terminal information returned by the target network element must meet. For example, the terminal constraint information can be used to indicate the specific content contained in the terminal information (such as terminal identification, terminal location, terminal power, network elements or data networks that the terminal can access, etc.). Optionally, the terminal constraint information can be the above-mentioned terminal requirement information.

[0129] In actual implementation, the terminal information of the third terminal returned by the target network element is determined by the target network element according to the terminal constraint carried in the first request. The terminal constraint may be related to the task type. For example, for a task related to the terminal location information, the terminal constraint may be the location where the terminal location information needs to meet the task type requirements. The terminal constraint may also be related to the network slices that the terminal can access, the DNN type, the computing resources of the terminal, the security indicators of the terminal, etc.

[0130] As an optional solution of the present application, the target network element is associated with a task type;

[0131] Optionally, the task type includes at least one of the following: a task related to the terminal location, a task related to the position of the terminal, and a task related to the session of the terminal;

[0132] Optionally, the target network element satisfies at least one of the following: the target network element corresponding to the task related to the performance of the terminal includes the network storage network element; the target network element corresponding to the task related to the location of the terminal includes the mobility management network element; the target network element corresponding to the task related to the session of the terminal includes the session management network element.

[0133] It can be understood that in the embodiment of the present application, the first network element may also be an existing network element in the communication system. For example, the first network element may be a mobility management network element, such as the AMF network element in the 5G communication system. At this time, for tasks related to the terminal location, the target network element may also be the first network element itself, and the first network element may not need to perform the above-mentioned step of sending the above-mentioned first request.

[0134] In actual implementation, in addition to the first network element, the wireless communication system may also include other network elements with specific functions, such as mobility management network element, session management network element, UDF, AMF, etc. Different network elements have their own functions. For different joint computing tasks, the conditions that the terminal must meet are likely to be different, so the terminal information required to determine the first terminal that meets the conditions is also different, so the network elements that can provide these terminal information are also likely to be different. After determining the current joint computing task, the first network element can know which network element to request the corresponding terminal information based on the current task type or at least one of the terminal requirement information. Specifically, after determining the joint computing task, the first network element can send a first request to the corresponding target network element based on the task type of the joint computing task or at least one of the terminal requirement information for the terminal to participate in the joint computing, such as the terminal's allocatable computing resources, the terminal's power, etc., to obtain the terminal information participating in the joint computing.

[0135] As an example, taking the 5G wireless network as an example, if the task type is a task related to the terminal location, as the first network element in the 5G core network, a first request can be sent to the mobility management network element AMF of the 5G core network, and the terminal information of the specific location or the terminal information of at least one terminal with the terminal location information can be obtained through AMF. If the task type is a task related to the performance of the terminal, a first request is sent to the network storage network element UDM, and UDM responds to the request to provide the first network element with terminal information with specific computing resources or terminal information including terminal computing resource information. If the task type is a task related to the session content of the terminal, a first request is sent to the session management network element SMF, and SMF responds to the request to provide the first network element with terminal information including the bandwidth of the terminal, the service type of the terminal access content, etc.

[0136] Step S1023: Based on the terminal information of each third terminal, at least one first terminal that meets the terminal requirement information is determined from at least one third terminal.

[0137] Among them, if the first network element requests the terminal information (such as terminal identification) of at least one third terminal that meets the terminal requirement information of the joint computing task from the target network element, then at least the first terminal can be all the third terminals, and the first network element can send the task information of the joint computing task to each first terminal based on the terminal identification of the first terminal. Alternatively, the first network element can determine the third terminal that meets the conditions as the first terminal based on the terminal information of the third terminal returned by the target network element.

[0138] In actual implementation, optionally, at least one first terminal can be determined based on at least one of the task type of the joint computing task and the terminal requirement information of the terminal. For example, a certain number of candidate terminals can be first screened according to the task type, and then one or more first terminals can be further screened from the candidate terminals according to the terminal requirement information. In this way, the accuracy of the terminals participating in the joint computing task can be effectively improved.

[0139] As another optional method, the terminal requirement information corresponding to each joint computing task can be pre-agreed. The first network element can send a first request with the task type to the target network element. After receiving the request, the target network element can return the corresponding terminal information to the first network element according to the task type.

[0140] After the first network element has determined at least one first terminal to participate in the joint computing task, it can request these first terminals to participate in the joint computing task. The details are as follows:

[0141] Step S103: Send relevant information of the joint computing task to each first terminal, so that at least one second terminal participates in the joint computing task based on the relevant information.

[0142] It should be noted that the at least one second terminal is part or all of the at least one first terminal.

[0143] In actual implementation, after determining at least one first terminal that can participate in the joint computing task, the first network element may continue to send relevant information of the joint task to each first terminal.

[0144] Among them, the relevant information includes task information and session parameter information, and the task information includes at least indication information based on the AI ​​model. The indication information of the AI ​​model is used to indicate the target AI model that the terminal participates in the joint computing task call. Optionally, the indication information of the AI ​​model includes at least one of the task type of the joint computing task or the AI ​​model information. The embodiments of the present application do not limit the specific content form of the AI ​​model. For example, the task type of the joint computing task is in a corresponding relationship with the AI ​​model. The indication information of the AI ​​model can be the indication information of the task type or type. For another example, the indication information of the AI ​​model can be directly the identifier of the AI ​​model, such as the name, number or other forms of identification information of the model. The first terminal can determine the target AI model participating in the joint computing task based on the AI ​​model indication information in the task information. Optionally, the first terminal can also guide the specific type of task the joint computing task is based on the AI ​​model information (such as the AI ​​model and the task type have a binding relationship), and what operations the first terminal needs to perform if it participates in the task (such as which references the terminal is to perform for each joint computing task is pre-agreed by the system, or the base station or other network element has previously sent the operations to be performed for each task or each model to each terminal in the wireless communication system, for example, the base station sends configuration information to each terminal, and the configuration information configures the terminal tasks corresponding to each joint computing task, that is, which operations the terminal is to perform).

[0145] The above-mentioned session parameter information is the session parameter information of the data transmission channel associated with the joint computing task that needs to be executed currently. The session parameter information is used to notify the first terminal of the relevant parameters required to establish the data transmission channel between the data network corresponding to the joint computing task. For example, in a 5G communication network, the session parameter information may be a PDU session parameter associated with the joint computing task. In other words, the session parameter information is used to build a data transmission channel between the first terminal and one or more service servers of the AI-based service in a wireless communication network. In other words, if the first terminal participates in the joint computing task, it is necessary to establish a user plane connection of the terminal based on the session parameter information sent by the first network element.

[0146] In an embodiment of the present application, the session parameter information includes multiple parameters required to establish a data transmission channel between data networks associated with the terminal and the joint computing task, which may include but is not limited to network slicing information, DN N information, business continuity information, AI model information, etc.

[0147] As an optional solution of the present application, after the first network element sends relevant information of the joint computing task to the first terminal, the method further includes:

[0148] Response information sent by each first terminal is received, where the response information of a first terminal is used to indicate whether the first terminal participates in the joint computing task.

[0149] Optionally, whether a first terminal participates in the joint computing task depends on the first terminal. Whether a first terminal participates in the joint computing task may be determined based on at least one of the following: location information of the first terminal, resource information of the first terminal, or willingness of a user of the first terminal.

[0150] In actual implementation, after receiving the relevant information of the joint computing task sent by the first network element, the first terminal can decide on its own (such as based on its own computing resources, power information, the user's wishes, etc.) whether to participate in the joint computing task, and send corresponding response information to the first network element, that is, the first terminal informs the first network element whether to participate in the joint computing.

[0151] Optionally, the first network element may send a request to participate in the joint computing task to the first terminal, and the request includes relevant information about the joint computing task. For the first terminal, after receiving the request for the joint computing task, the first terminal may display prompt information about the joint computing task, and the prompt information is used to prompt the user to decide whether to participate in the joint computing task. Optionally, the prompt information may also prompt relevant content of the task, such as the type of task, the operation to be performed by the terminal, the time or memory or computing resources that may be consumed by the terminal to perform the task, and other related information. The user can decide whether to participate according to his or her own situation, and the first terminal may feed back the response information of whether to participate or not to participate to the first network element according to the user's instructions.

[0152] Optionally, the above response information may specifically indicate that the first terminal participates in the joint computing task, that is, the first terminal will only feedback the response information to the first network element when it is determined to participate in the joint computing task. For the first network element, if the first network element does not receive the response information of one or some first terminals, the first network element considers that these first terminals do not participate in the joint computing task. Alternatively, the above response information may indicate that the first terminal does not participate in the joint computing task, then the first network element may consider that the first terminal that does not send the response information is the network element that is determined to participate in the joint computing task.

[0153] It should be noted that in the embodiment of the present application, the two nodes in the communication system (such as the first network element and the terminal) communicate, which can be direct communication between the two nodes, or the two nodes can communicate through other nodes. Optionally, the first network element sends the task information to each first terminal through the base station, that is, the first network element exchanges information with each first terminal through the base station. Exemplarily, in a 5G communication network, when the first network element is AMF, AMF sends task information to the terminal through the base station. When the first network element is not AMF, it must at least be sent through AMF and the base station.

[0154] In actual implementation, there is also a second network element in the wireless network system. It should be noted that the second network element can represent one network element or multiple network elements. The joint computing task initiated by the first network element can be forwarded by the second network element. As an example, in a 5G communication network, if the second network element represents one network element, the second network element may be a mobility management network element AMF, or a base station, etc.; if the second network element represents multiple network elements, the second network element may be an AMF and a base station, wherein the first terminal communicates with the first network element through the base station and the AMF. It can be understood that the connection between the first network element and the target network element belongs to the control plane connection in the wireless communication network.

[0155] As an optional solution of the present application, the first network element sends relevant information of the joint computing task to each first terminal, including any of the following:

[0156] Sending first information to each first terminal, where the first information includes a container, and the container includes various information of the related information;

[0157] Second information is sent to each first terminal, where the second information includes each item of information in the related information.

[0158] When the first network element sends the relevant information to the first terminal, the specific sending form of the relevant information is not limited in the embodiment of the present application.

[0159] In actual implementation, the related information of the joint computing task can be encapsulated in the first information sent to each first terminal. In this case, the first information includes a container, and the container includes various information in the related information. In addition, the related information of the joint computing task can also be encapsulated in the second information sent to each first terminal. Various information in the related information is independent of each other in the second information, and various information in the task information is independent of each other in the second information.

[0160] Optionally, the task information further includes at least one of the following: task instruction information, task validity information, and first instruction information;

[0161] In actual implementation, the indication information of the task is used to indicate the subtask of the joint computing task executed by the terminal; the first indication information is used to indicate information related to the return of the task processing result, that is, the result requirement information for the business processing result returned by the terminal. For the first indication information, if the terminal also configures the result requirement information for the business processing result returned by the terminal when deploying the AI ​​model (that is, the terminal itself may have clearly required information to be returned), then the task information may not carry the first indication information; if the indication information of the AI ​​model in the task information also includes the result requirement information for the business processing result returned by the terminal, then the task information may not carry the first indication information. The effective information of the task refers to the effectiveness of the execution process of the joint computing task, which is used to indicate the execution time information of the task, that is, the joint computing task has execution time information, indicating the effective time of the joint computing task, and the terminal executes the task within the effective time. When the execution time is exceeded, the relevant results obtained by the joint computing task are invalid, and the terminal does not need to continue to execute the joint computing task.

[0162] As an optional solution of the present application, after sending relevant information of the joint computing task to each first terminal, optionally, the first network element may further perform at least one of the following:

[0163] The first network element receives a task processing result corresponding to the task information and sent by at least one second terminal, and provides the task processing result to a service server corresponding to the joint computing task.

[0164] In actual implementation, the first network element can serve as a connection bridge between the second terminal and the business server. The first network element will obtain the corresponding task processing results from at least one second terminal determined to participate in the joint computing task, and provide it to the business server corresponding to the joint computing task, that is, the first network element does not process the task processing results in any way and directly forwards them. It should be noted that the task processing results are calculated by the second terminal based on the target AI model determined by the indication information of the AI ​​model in the task information, and are received through the data transmission channel established by the second terminal. The data transmission channel corresponds to the session parameter information in the task information.

[0165] Optionally, a task processing result corresponding to the task information and sent by at least one second terminal is received, and based on the received task processing result, a final processing result of the joint computing task is determined, and the final processing result is provided to the business server.

[0166] In actual implementation, the first network element can also serve as a computing server for joint computing tasks, that is, the first network element calls the AI ​​model deployed by itself for joint computing tasks based on the task processing results received by each second terminal, determines the final processing result of the joint computing task, and finally provides the final processing result to the business server that issued the task processing request to perform other subsequent operations.

[0167] By using the embodiment of the present application, the first network element can select a second terminal whose terminal information meets at least one of the task type and terminal constraint conditions from the wireless communication system according to the task type of the joint computing task and different terminal constraint conditions. In this way, the accuracy of selecting terminals participating in the joint computing task can be improved. And through the data channel constructed based on the PDU session parameters associated with the AI ​​model information and the task type, the business processing results of each second terminal are obtained, and finally the target processing results corresponding to the joint computing task are obtained based on the business processing results. In this way, the joint computing task is sent to each terminal, which can improve the task processing efficiency and the accuracy of the final result.

[0168] Next, the method for joint processing of services based on artificial intelligence provided by an embodiment of the present application is described by taking a terminal in a wireless communication system as an example. Figure 4 , Figure 4 is another flowchart of a service joint processing method based on artificial intelligence provided by an embodiment of the present application, such as Figure 4 As shown in , the method may include the following steps S201 to S203.

[0169] Step S201: receiving relevant information of an artificial intelligence-based joint computing task sent by a network node.

[0170] It should be noted that the joint computing task is initiated by a network node (i.e. the aforementioned first network element), which supports artificial intelligence services. The relevant information includes task information and session parameter information. The task information includes indication information of the artificial intelligence AI model.

[0171] As an optional solution of the present application, after receiving the relevant information of the joint computing task sent by the first network element, the terminal may also send response information to the network node, where the response information is used to instruct the terminal to participate in the joint computing task, or to instruct the terminal not to participate in the joint computing task;

[0172] Optionally, when the terminal determines to participate in the joint computing task, the terminal may execute step S202.

[0173] Step S202: Based on the session parameter information, a session establishment request is sent, and a data transmission channel between data networks corresponding to the joint computing task is established.

[0174] In actual implementation, taking the 5G communication network as an example, the session parameter information refers to the PDU session parameter information. Each terminal participating in the joint computing task initiates a PDU session establishment request to the session management network element SMF in the 5G core network based on the PDU session parameter information. SMF establishes a data transmission channel between the terminal and the data network corresponding to the joint computing task based on the network slice information, DNN information, business continuity information, etc., and AI model information included in the PDU session parameter information, so as to transmit business data related to the joint computing task between the terminal and the data network, assist the terminal to complete the corresponding joint computing task based on the AI ​​model deployed by itself, obtain the task processing result of the joint computing task, and provide the task processing result to the business server that finally executes the joint computing task. The business server can be the first network element or other server nodes.

[0175] Step S203: interact with the data network through the data transmission channel, and call the target AI model corresponding to the indication information of the AI ​​model to participate in the joint computing task.

[0176] In actual implementation, the target AI model is determined based on the AI ​​model information, and through the task information and the target AI model, it interacts with the data network corresponding to the joint computing task through the data transmission channel, thereby realizing the calculation of the joint computing task, obtaining the task processing result corresponding to the terminal, and providing the task processing result to the business server that ultimately executes the joint computing task.

[0177] It should be noted that the data transmission channel corresponds to the session parameter information, and the terminal can interact with the data network through the data transmission channel. The terminal determines the target AI model corresponding to the AI ​​model information locally based on the AI ​​model information carried by the joint computing task, and calls the target AI model to interact with the data network associated with the joint computing task through the data transmission channel.

[0178] In actual implementation, the terminal sends the task processing results corresponding to the joint computing task to the first network element through the wireless communication network. The first network element can directly provide the received multiple task processing results to the service server that finally performs the joint processing task; the first network element can also process the received multiple task processing results again to obtain the final processing result of the joint processing task, and then provide the final processing result to the service server. In actual implementation, whether the first network element can determine the final processing result based on the task processing result can be determined according to the specific form, computing resources, storage resources, etc. of the first network element. For example, when the first network element is an independent electronic device in a wireless network and does not have the computing power to process the joint computing task, the first network element can directly provide the received multiple task processing results to the service processor that finally processes the joint computing task, that is, at this time, the first network element and the service server are two independent electronic devices; when the first network element and the service server belong to different functional modules of the same electronic device, the first network element can determine the final processing result of the joint computing task based on the multiple task processing results, and then provide it to the service server.

[0179] Optionally, the terminal can also send a session release request to release the data transmission channel. The session release request is used to release resources related to the session. In the 5G communication network, the specific processing process of the PDU session release request is the same as the PDU session release process in the existing communication system.

[0180] In the application of the embodiment of the present application, the terminal only needs to call the target AI model that is locally deployed and adapted to the AI ​​model information according to the relevant information of the joint computing task, determine the corresponding business processing results and send them to the first network element through the corresponding data transmission channel, without sharing local data, and can ensure the security and privacy of the data. At the same time, the terminal participates in the joint computing task, which can effectively improve the processing efficiency of the task.

[0181] In order to better understand and illustrate the practical value of the solution provided by the embodiment of the present application, the optional implementation methods of the solution provided by the present application will be further described below in combination with specific practical scenarios.

[0182] In actual applications, there are multiple scenarios for joint computing of terminals for artificial intelligence services in mobile networks. In the embodiments of the present application, the scenario and implementation of jointly predicting the driving trajectory of unmanned vehicles by combining computing resources of multiple vehicles in a smart transportation scenario based on a 5G communication network are used as an example to illustrate.

[0183] See also Figure 5 , Figure 5It is an example diagram of the service joint processing method based on artificial intelligence in the embodiment of the present application. In the driving trajectory prediction scenario, the first network element is a newly added network element in the 5G core network that can support AI services and can be called New-NF. The service based on artificial intelligence is a predicted driving trajectory service under the federated learning architecture, that is, predicting the vehicle driving trajectory of the vehicle or other vehicles in the future (such as a few seconds) under the traffic road environment (such as straight roads, curves, intersections, etc.). The terminal UE (that is, the first terminal in the previous text) is a vehicle in smart transportation or a vehicle-mounted terminal carried by the vehicle. The terminal can support a trajectory prediction AI model for predicting the driving trajectory. The AI ​​model can predict the vehicle driving conditions in the next few seconds, that is, the route position and speed, etc., based on the collected historical motion trajectory, road information and other environmental information. In addition, in the entire smart transportation system based on wireless communication, other network elements in the 5G core network may also be included, such as PCF, NWDAF, AMF, SMF. Optionally, the first network element may also be the above-mentioned existing network element that additionally supports trajectory prediction AI services.

[0184] The first network element in the 5G communication network generates a joint computing task for determining a vehicle's driving trajectory. The joint computing task is an AI joint computing task based on artificial intelligence under a federated learning framework.

[0185] The following will describe the artificial intelligence-based service joint processing method provided in the embodiment of the present application in combination with steps S301 to S305. This method is actually also a method for wireless networks to support joint computing.

[0186] Step S301: The first network element confirms the joint computing task.

[0187] In actual implementation, before the first network element initiates the joint computing task, it first determines the task type of the joint computing task, that is, the category to which the AI ​​joint computing task belongs. Optionally, the task type can refer to location-based calculations related to the terminal location information, such as predicting the terminal's motion trajectory, moving speed, etc.; it can also be content-based calculations related to the terminal's communication session content, such as predicting the terminal's bandwidth, predicting the type of service that the terminal accesses, etc. It can also be performance-based calculations related to the terminal's own performance, such as predicting the terminal's power consumption, etc. It can also be other calculations that the terminal can participate in based on its own capabilities.

[0188] For the joint computing task of predicting the driving trajectory, the corresponding task type is a location computing task related to the terminal location information. The terminal requirement information participating in the joint computing task mainly refers to the conditions that the terminal participating in the task needs to meet, such as the location of the terminal, the type of network slice or DNN that the terminal can access, the computing resources of the terminal, the security indicators of the terminal, etc. The parameters required to be returned for each vehicle participating in the joint computing mainly refer to the return information of the calculation results that the terminal participating in the task needs to obtain. The PDU session parameters for transmitting the content related to the AI ​​joint computing task are mainly the parameters of the PDU session that needs to be established when the terminal participates in the computing task, including network slice information, DNN information, business continuity information, etc.

[0189] For the joint computing task of determining the vehicle's driving trajectory, the purpose of this task is to select the vehicle participating in the joint computing based on the geographical location characteristics of the trajectory prediction. Therefore, the task type of this joint computing task is at least a location computing task related to the terminal location information; in this task, the vehicle required information participating in the joint computing task at least includes that the terminal's location is within the specific area where trajectory prediction is required.

[0190] Step S302: Determine a first terminal that participates in the joint computing task.

[0191] In actual implementation, the first network element determines the first terminal participating in the joint computing task based on the terminal information obtained. Specifically, after the first network element confirms the AI ​​joint computing task, it will send a request to other network elements in the wireless network based on the terminal requirement information for participating in the joint computing task in the joint computing task, and confirm the first terminal that can participate in the joint computing task based on the terminal information returned by the corresponding other network elements. It should be noted that the first terminal is not necessarily the terminal that ultimately participates in the joint computing task. The first terminal is a terminal that meets the terminal requirement information for participating in the joint computing task, that is, a terminal that is qualified to participate in the joint computing task, that is, a candidate terminal.

[0192] As an example, in a 5G communication network, the first network element may obtain terminal information located at a specific location from the mobility management network element AMF, obtain terminal information with specific computing resources from the network storage network element UDM, etc. It is understandable that the first network element may confirm the terminal information that can support the joint computing task based on at least one terminal information returned from the above other network elements.

[0193] For the joint computing task of determining the vehicle's driving trajectory, the first network element can obtain the candidate vehicles appearing in the specific location area through the terminal information returned by at least one of the SMF and AMF in the 5G core network. As the first terminal that can participate in the joint computing task of the vehicle's driving trajectory, the first terminal can include some or all of the vehicles in the specific location area. The specific location area is used to indicate the area associated with the location of the unmanned vehicle.

[0194] Step S303: Sending the joint computing task to the first terminal.

[0195] In actual implementation, the first network element can send a joint computing task to the first terminal. The sending of the joint computing task can be in the network configuration information update process, or the mobility management process, or other custom processes that can reach the terminal. It should be noted that the custom process can be used to characterize the process of transmitting joint computing tasks that can support artificial intelligence in a wireless network. The custom process belongs to the process of the control plane in wireless communication. The joint computing task can also be sent by using different processes to transmit specific parameters, such as parameter 1 is sent using process 1, parameter 2 is sent using process 2, etc.

[0196] It should be noted that the relevant information of the joint computing task can be sent as an independent parameter during the transmission process in the wireless network, or the joint computing task can be sent as a container, that is, the joint computing task sent by the first network element carries a container, and the container includes various information of the joint computing task. Among them, the relevant information includes at least task information and PDU session parameter information, and the task information includes at least task identification, task type, associated AI model information, and relevant information of the business computing result (such as format information, etc.). According to the actual situation, it can also include result requirement information for the business processing result returned by the terminal. The reason why the result requirement information is optional is that the terminal also configures the corresponding result requirement information when deploying the AI ​​model (that is, the terminal itself can have clearly defined the information that needs to be returned). At this time, there is no need to carry the result requirement information again in the relevant information of the joint computing task. Another situation is that the AI ​​model information in the task information also includes the corresponding result requirement information. At this time, there is no need to set a separate parameter for the result requirement information. In addition, the validity information of the joint computing task can also be included. It can be that the joint computing task fails to be completed within the target time period, and the joint computing task can be deemed to have failed. At this time, the joint computing task can be initiated again.

[0197] As an example, in a 5G communication network, for a joint computing task of determining a vehicle's driving trajectory, a first network element sends task information to a first terminal based on a control plane connection in a wireless network. Specifically, the first network element sends task information to a candidate vehicle (i.e., the first terminal) that appears in a specific location area through a connection composed of an AMF service interface and an AN.

[0198] Step S304: the first terminal sends response information to the first network element, where the response information is used to indicate whether the first terminal participates in the joint computing task.

[0199] In actual implementation, after the first terminal receives the AI ​​joint computing task, it can confirm whether to participate in the joint computing task according to its own situation, and send the response information indicating whether to participate in the joint computing task to the first network element. Optionally, the situation of the first terminal includes its own computing resources, power information, user's wishes, etc. After the first terminal determines to participate in the joint computing task, the first terminal is the terminal that finally participates in the joint computing task. The terminal at this time is also the second terminal mentioned above. It can be understood that the second terminal can be part or all of the first terminal.

[0200] Step S305: The second terminal initiates a PDU session establishment request according to the PDU session parameters.

[0201] In actual implementation, each second terminal (determine part or all of the first terminals participating in the joint computing task) initiates a PDU session establishment request to the SMF according to the PDU session parameters corresponding to the joint computing task. The SMF establishes a session with the UPF to establish a user plane connection according to the network slice information, DNN information, business continuity information, AI model information, etc. included in the PDU session parameters. The SMF initiates a wireless resource request to the base station; after receiving the request, the base station sets the corresponding wireless resources and replies to the SMF's request; after receiving the reply, the SMF updates the UPF to establish a data transmission channel from the UPF to the base station; and finally generates a data transmission channel between UE<->AN<->UPF. The UE reaches the UPF through the data transmission channel to connect to the service server (target DN), and can transmit the task information and AI model information to the associated service server through the data transmission channel. After the second terminal executes the joint computing task, the obtained service processing result is again transmitted through the transmission channel to the target server that finally executes the joint computing task. The target server can be the first network element or other server nodes. The target server generates a predicted driving trajectory of the unmanned vehicle in the next few seconds based on the trajectory data returned by each second terminal in the next few seconds, so that the unmanned vehicle can travel based on the predicted driving trajectory.

[0202] Optionally, after the PDU session is established, when the second terminal decides to exit the joint computing task, the second terminal can also initiate a PDU session release process to release the PDU session connection. In actual implementation, when the second terminal (i.e., other vehicles) participating in the joint computing task does not want to continue participating in the joint computing, it can send a session release request for the PDU session to the SMF network element in the 5G core network, so that the SMF network element initiates the PDU session release process, thereby releasing the PDU session associated with the current PDU session parameters.

[0203] It should be noted that this embodiment is described based on the system architecture of a 5G communication network. Accordingly, if it is applied in other mobile communication systems, such as 6G, the corresponding functions and processes are executed by network elements and processes with similar functions in the system.

[0204] By applying the embodiments of the present application, the terminal, the first network element, and the service server can work with the assistance of the 5G communication network to perform joint tasks based on AI services. Among them, based on the specific characteristics of the terminal (vehicle), the terminal that meets the terminal requirement information is selected for joint calculation, which can ensure the accuracy of the terminals participating in the joint calculation. In addition, the terminal uses the AI ​​model locally to determine the corresponding business processing results, which can effectively ensure the security and privacy of the data; the participation of terminals that meet the requirements in the joint calculation can greatly improve the processing efficiency of the task.

[0205] Based on the same principle as the method provided in the embodiment of the present application, the embodiment of the present application also provides a service joint processing device based on artificial intelligence, see Fig. 6A , Fig. 6A is a schematic diagram of an artificial intelligence service joint processing device provided in an embodiment of the present application, and the device is a device to which the first network element belongs, such as Fig. 6A As shown, the service joint processing device 1000 based on artificial intelligence includes a task determination module 110, a terminal determination module 120, and a task sending module 130, wherein:

[0206] A task determination module 110, used to determine the artificial intelligence AI-based joint computing task to be executed;

[0207] The terminal determination module 120 is further configured to determine at least one first terminal participating in the joint computing task;

[0208] The task sending module 130 is used to send relevant information of the joint computing task to each of the first terminals, so that at least one second terminal participates in the joint computing task based on the relevant information, and the at least one second terminal is part or all of the at least one first terminal; wherein the relevant information includes task information and session parameter information, the task information includes indication information of the AI ​​model, the indication information of the AI ​​model is used to indicate the target AI model called by the terminal to participate in the joint computing task, and the session parameter information is used to establish a data transmission channel between the terminal and the data network corresponding to the joint computing task.

[0209] Optionally, the terminal determination module is further used to determine the terminal requirement information participating in the joint computing task;

[0210] Acquiring terminal information of at least one third terminal;

[0211] Based on the terminal information of each of the third terminals, at least one first terminal that meets the terminal requirement information is determined from the at least one third terminal.

[0212] Optionally, whether a first terminal participates in the joint computing task depends on the first terminal.

[0213] Optionally, whether a first terminal participates in the joint computing task may be determined based on at least one of the following:

[0214] The location information of the first terminal, and the resource information of the first terminal or the intention of the user of the first terminal.

[0215] Optionally, the terminal determination module is further used to send a first request to a target network element, where the first request is used to request terminal information, and the target network element is associated with at least one of a task type of the joint computing task or the terminal requirement information;

[0216] receiving terminal information of at least one third terminal sent by the target network element in response to the first request.

[0217] Optionally, the terminal requires that the information be associated with a task type of the joint computing task.

[0218] Optionally, the first request includes a terminal constraint condition, and the terminal constraint condition is associated with at least one of the task type or the terminal requirement information;

[0219] The terminal information of the at least one first terminal is determined by the target network element based on the terminal constraint condition.

[0220] Optionally, the target network element is associated with the task type;

[0221] Optionally, the task type includes at least one of the following:

[0222] Tasks related to the performance of the terminal; Tasks related to the location of the terminal; Tasks related to the session of the terminal;

[0223] Optionally, the target network element satisfies at least one of the following:

[0224] The target network elements corresponding to the tasks related to the performance of the terminal include network storage network elements;

[0225] The target network elements corresponding to the tasks related to the location of the terminal include a mobility management network element;

[0226] The target network elements corresponding to the tasks related to the session of the terminal include the session management network elements.

[0227] Optionally, the terminal determination module is further used to receive response information sent by each of the first terminals, where the response information is used to instruct the first terminal to participate in the joint computing task, or to instruct the first terminal not to participate in the joint computing task.

[0228] Optionally, the task sending module is further used to send the task information to each first terminal through a base station.

[0229] Optionally, the sending the task information of the joint computing task to each of the first terminals includes any one of the following:

[0230] Sending first information to each of the first terminals, where the first information includes a container, and the container includes various information of the task information;

[0231] Sending second information to each of the first terminals, where the second information includes each item of information in the task information.

[0232] Optionally, the network node is a newly added network element in the wireless communication system, or is any one of the following in the wireless network system: a network data analysis network element, a mobility management network element, and a session management network element.

[0233] Optionally, the indication information of the AI ​​model includes at least one of the task type or AI model information of the joint computing task;

[0234] Optionally, the task information further includes at least one of the following:

[0235] Task instruction information, task validity information, and first instruction information;

[0236] Among them, the indication information of the task is used to indicate the subtask of the joint computing task executed by the terminal; the effective information of the task is used to indicate the execution time information of the task; and the first indication information is used to indicate information related to the return of the task processing result.

[0237] Optionally, the artificial intelligence-based service joint processing device further includes a result receiving module, and the result receiving module is used to perform at least one of the following:

[0238] receiving a task processing result corresponding to the task information sent by the at least one second terminal, and providing the task result to a service server corresponding to the joint computing task;

[0239] Receive the task processing result corresponding to the task information sent by the at least one second terminal, determine the final processing result of the joint processing task based on the received task processing result, and provide the final processing result to the service server.

[0240] Optionally, the task information also includes result requirement information for the task processing result.

[0241] In addition, the present application also provides a service joint processing device based on artificial intelligence, see Figure 6B , Figure 6B is another schematic diagram of an artificial intelligence service joint processing device provided in an embodiment of the present application, the device is a device to which a terminal belongs, such as Figure 6B As shown, the artificial intelligence-based service joint processing device 1100 includes an information receiving module 111, a request sending module 112 and a data interaction module 113, wherein:

[0242] An information receiving module 111 is used to receive relevant information of an artificial intelligence-based joint computing task sent by a network node, wherein the network node supports artificial intelligence services, the relevant information includes task information and session parameter information, and the task information includes indication information of an artificial intelligence AI model;

[0243] A request sending module 112, configured to send a session establishment request based on the session parameter information to establish a data transmission channel between the data networks corresponding to the joint computing task;

[0244] The data interaction module 113 is used to interact with the data network through the data transmission channel, and call the target AI model corresponding to the indication information of the AI ​​model to participate in the joint computing task.

[0245] The device of the embodiment of the present application can execute the business joint processing method based on artificial intelligence provided by the embodiment of the present application. The implementation principle is similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0246] An electronic device is also provided in an embodiment of the present application, the electronic device includes at least one processor, the processor is configured to execute the steps of the service joint processing method based on artificial intelligence provided in any optional embodiment of the present application, and optionally, the electronic device may also include a transceiver and / or a memory coupled to the processor, the memory stores a computer program, and the processor can implement the solution provided in any optional embodiment of the present application when running the computer program. Optionally, the electronic device may be a terminal, or an electronic device corresponding to the first network element, or a service server.

[0247] Figure 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 7 As shown, the electronic device may be a server or a user terminal, and the electronic device may be used to implement the artificial intelligence-based business joint processing method provided in any embodiment of the present application.

[0248] like Figure 7 As shown in FIG. 1 , the electronic device 2000 may mainly include at least one processor 2001 ( Figure 7 2002, a communication module 2003 and an input / output interface 2004, etc. Optionally, the components can be connected and communicated through a bus 2005. It should be noted that: Figure 7 The structure of the electronic device 2000 shown in the figure is merely illustrative and does not constitute a limitation on the electronic device to which the method provided in the embodiment of the present application is applicable.

[0249] Among them, the memory 2002 can be used to store operating systems and applications, etc. The application may include a computer program that implements the method shown in the embodiment of the present application when called by the processor 2001, and may also include a program for implementing other functions or services. The memory 2002 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and computer programs, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0250] The processor 2001 is connected to the memory 2002 via the bus 2005, and implements the corresponding functions by calling the application program stored in the memory 2002. Among them, the processor 2001 can be a CPU (Central Processing Unit), a general processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof, which can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 2001 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0251] The electronic device 2000 can be connected to the network through the communication module 2003 (which may include but is not limited to components such as a network interface) to communicate with other devices (such as a user terminal or a server, etc.) through the network to achieve data interaction, such as sending data to other devices or receiving data from other devices. Among them, the communication module 2003 may include a wired network interface and / or a wireless network interface, etc., that is, the communication module may include at least one of a wired communication module or a wireless communication module.

[0252] The electronic device 2000 can be connected to the required input / output devices, such as a keyboard, a display device, etc., through the input / output interface 2004. The electronic device 2000 itself can have a display device, and can also be connected to other display devices through the interface 2004. Optionally, a storage device, such as a hard disk, can also be connected through the interface 2004, so that data in the electronic device 2000 can be stored in the storage device, or data in the storage device can be read, and data in the storage device can also be stored in the memory 2002. It can be understood that the input / output interface 2004 can be a wired interface or a wireless interface. Depending on the actual application scenario, the device connected to the input / output interface 2004 can be a component of the electronic device 2000, or it can be an external device connected to the electronic device 2000 when needed.

[0253] The bus 2005 for connecting the components may include a path to transmit information between the above components. The bus 2005 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. According to different functions, the bus 2005 may be divided into an address bus, a data bus, a control bus, etc.

[0254] Optionally, for the solution provided in the embodiments of the present application, the memory 2002 can be used to store a computer program for executing the solution of the present application, and run by the processor 2001. When the processor 2001 runs the computer program, the actions of the method or device provided in the embodiments of the present application are implemented.

[0255] Based on the same principle as the method provided in the embodiment of the present application, the embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the corresponding content of the aforementioned method embodiment can be implemented.

[0256] An embodiment of the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the corresponding content of the aforementioned method embodiment can be implemented.

[0257] It should be noted that the terms "first", "second", "third", "fourth", "1", "2", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than that shown or described in the drawings.

[0258] It should be understood that, although each operation step is indicated by arrows in the flowchart of the embodiment of the present application, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be performed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages may be executed at the same time, and each sub-step or stage in these sub-steps or stages may also be executed at different times respectively. In different scenarios of execution time, the execution order of these sub-steps or stages may be flexibly configured according to demand, and the embodiment of the present application does not limit this.

[0259] The above is only an optional implementation method for some implementation scenarios of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present application, other similar implementation methods based on the technical ideas of the present application are also within the protection scope of the embodiments of the present application.

Claims

1. A business joint processing method based on artificial intelligence, characterized in that: Applied to a wireless communication system, the method is executed by a network node, the network node supports artificial intelligence services, and the method includes: Determine the joint computing tasks based on artificial intelligence (AI) to be performed; Determining at least one first terminal participating in the joint computing task; Sending relevant information of the joint computing task to each of the first terminals, so that at least one second terminal participates in the joint computing task based on the relevant information, the at least one second terminal being part or all of the at least one first terminal; Among them, the relevant information includes task information and session parameter information, the task information includes indication information of the AI ​​model, the indication information of the AI ​​model is used to indicate the target AI model called by the terminal to participate in the joint computing task, and the session parameter information is used for the terminal to establish a data transmission channel with the data network corresponding to the joint computing task.

2. The method according to claim 1, characterized in that The method further comprises: Determining required information of terminals participating in the joint computing task; Acquiring terminal information of at least one third terminal; Based on the terminal information of each of the third terminals, at least one first terminal that meets the terminal requirement information is determined from the at least one third terminal.

3. The method according to claim 2, characterized in that The acquiring terminal information of at least one third terminal includes: Sending a first request to a target network element, wherein the first request is used to request terminal information, and the target network element is associated with at least one of a task type of the joint computing task or the terminal requirement information; receiving terminal information of at least one third terminal sent by the target network element in response to the first request.

4. The method according to claim 3, characterized in that The first request includes a terminal constraint condition, and the terminal constraint condition is associated with at least one of the task type or the terminal requirement information; The terminal information of the at least one third terminal is determined by the target network element based on the terminal constraint condition.

5. The method according to claim 3, characterized in that: The task type includes at least one of the following: Tasks related to the performance of the terminal; Tasks related to the location of the terminal; Tasks related to the session of the terminal; The target network element satisfies at least one of the following conditions: The target network elements corresponding to the tasks related to the performance of the terminal include network storage network elements; The target network elements corresponding to the tasks related to the location of the terminal include a mobility management network element; The target network elements corresponding to the tasks related to the session of the terminal include the session management network elements.

6. The method according to claim 1, characterized in that The method further comprises: Response information sent by each of the first terminals is received, where the response information is used to instruct the first terminal to participate in the joint computing task, or to instruct the first terminal not to participate in the joint computing task.

7. The method according to claim 1, characterized in that The sending the relevant information of the joint computing task to each of the first terminals includes any one of the following: Sending first information to each of the first terminals, where the first information includes a container, and the container includes various information of the related information; Sending second information to each of the first terminals, where the second information includes each item of information in the related information.

8. The method according to claim 1, characterized in that: The network node is a newly added network element in the wireless communication system; or, The network node is any one of the following in a wireless communication system: Network data analysis network element, mobility management network element, session management network element, and policy control network element.

9. The method according to claim 1, characterized in that: The method further comprises at least one of the following: receiving a task processing result corresponding to the task information sent by the at least one second terminal, and providing the task processing result to a service server corresponding to the joint computing task; Receive the task processing result corresponding to the task information sent by the at least one second terminal, determine the final processing result of the joint processing task based on the received task processing result, and provide the final processing result to the service server.

10. The method according to any one of claims 1 to 9, characterized in that: The indication information of the AI ​​model includes at least one of the task type or AI model information of the joint computing task.

11. The method according to any one of claims 1 to 9, characterized in that: The task information also includes at least one of the following: Task instruction information, task validity information, and first instruction information; Among them, the indication information of the task is used to indicate the subtask of the joint computing task executed by the terminal; the effective information of the task is used to indicate the execution time information of the task; and the first indication information is used to indicate information related to the return of the task processing result.

12. A task joint processing method based on artificial intelligence, characterized in that: Applied to a wireless communication system, the method is executed by a terminal in the wireless communication system, and the method includes: Receiving relevant information of an artificial intelligence-based joint computing task sent by a network node, the network node supporting artificial intelligence services, the relevant information including task information and session parameter information, the task information including indication information of an artificial intelligence AI model; Based on the session parameter information, a session establishment request is sent, and a data transmission channel between data networks corresponding to the joint computing task is established; Interact with the data network through the data transmission channel, and call the target AI model corresponding to the indication information of the AI ​​model to participate in the joint computing task.

13. The method according to claim 12, characterized in that The method further comprises: Sending response information to the network node, where the response information is used to instruct the terminal to participate in the joint computing task, or to instruct the terminal not to participate in the joint computing task; The sending of a session establishment request based on the session parameter information includes: In a case where the terminal determines to participate in the joint computing task, a session establishment request is sent based on the session parameters.

14. A service joint processing device based on artificial intelligence, characterized in that: The device comprises: A task determination module, used to determine the joint computing tasks to be performed based on artificial intelligence AI; A terminal determination module, configured to determine at least one first terminal that participates in the joint computing task; a task sending module, configured to send relevant information of the joint computing task to each of the first terminals, so that at least one second terminal participates in the joint computing task based on the relevant information, wherein the at least one second terminal is part or all of the at least one first terminal; Among them, the relevant information includes task information and session parameter information, the task information includes indication information of the AI ​​model, the indication information of the AI ​​model is used to indicate the target AI model called by the terminal to participate in the joint computing task, and the session parameter information is used for the terminal to establish a data transmission channel with the data network corresponding to the joint computing task.

15. A service joint processing device based on artificial intelligence, characterized in that: The device comprises: An information receiving module, configured to receive relevant information of an artificial intelligence-based joint computing task sent by a network node, wherein the network node supports artificial intelligence services, the relevant information includes task information and session parameter information, and the task information includes indication information of an artificial intelligence AI model; A request sending module, used to send a session establishment request based on the session parameter information to establish a data transmission channel between the data networks corresponding to the joint computing task; A data interaction module is used to interact with the data network through the data transmission channel, and call the target AI model corresponding to the indication information of the AI ​​model to participate in the joint computing task.

16. A network node, characterized in that: The network node comprises a transceiver and a processor coupled to the transceiver, wherein the processor is configured to perform the method of any one of claims 1 to 11 or to perform the method of any one of claims 12 to 13.

17. A terminal, characterized in that: The terminal includes a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the method according to any one of claims 1 to 11 or the method according to any one of claims 12 to 13 when running the computer program.

18. A computer-readable storage medium, characterized in that: The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 11 or the method according to any one of claims 12 to 13.

Images