Communication method, apparatus and system

Abstract

Embodiments of the present application relate to the technical field of artificial intelligence, and provide a communication method, apparatus, and system. The method comprises: when it is determined that a first subnet has been established, an agent instance corresponding to a first terminal determining a first user plane network element for the first terminal and a second terminal to establish the first subnet; then sending a first request message to an agent instance corresponding to the second terminal, the first request message being used for deciding to create a local agent instance corresponding to the second terminal on a first artificial intelligence proxy function network element; and finally sending a first rule to the first user plane network element to instruct the first user plane network element to send, to the first artificial intelligence proxy function network element, data requiring multimodal conversion in the first subnet. On the basis of the first rule, the local agent instance corresponding to the second terminal enables the first terminal and the second terminal communicating with each other without relying on a same protocol to implement conversion between different protocols and different modalities between terminals by means of the local agent instance corresponding to the second terminal, thereby implementing cross-ecological interconnection of the terminals.

Description

A communication method, apparatus and system

[0001] This application claims priority to Chinese Patent Application No. 202410980199.2, filed on July 19, 2024, entitled "A Communication Method, Apparatus and System", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of artificial intelligence technology, and in particular to a communication method, apparatus and system. Background Technology

[0003] An "agent" refers to a computational entity that resides in a specific environment, can function autonomously and continuously, and possesses characteristics such as residency, responsiveness, sociality, and initiative. In an agent network composed of multiple different agents, there is end-to-end (E2E) interoperability between terminals, and terminals can access the network and establish sessions using digital identities, create subnets as needed, and possess secure and controllable characteristics.

[0004] In existing technologies, virtual subnets can be created in wide-area communication networks. However, in some scenarios, if two terminals use different communication protocols, they may be unable to communicate. Furthermore, within the created virtual subnet, if the modal information supported by different agents is inconsistent, the agents cannot collaborate. In short, virtual subnets created by existing technologies cannot support cross-modal communication and cross-ecosystem interconnection among multiple agents. Summary of the Invention

[0005] This application provides a communication method, device, and system that enables multimodal conversion and autonomous collaboration among intelligent agents, thereby achieving cross-ecosystem interconnection of various terminals.

[0006] The technical solution is as follows:

[0007] In a first aspect, embodiments of this application provide a communication method, the method comprising: an intelligent agent instance corresponding to a first terminal determining to establish a first subnet; the intelligent agent instance corresponding to the first terminal determining a first user plane network element, the first user plane network element being used by the first terminal and the second terminal to establish the first subnet; the intelligent agent instance corresponding to the first terminal sending a first request message to the intelligent agent instance corresponding to the second terminal, the first request message being used by the intelligent agent instance corresponding to the second terminal to decide to create a local intelligent agent instance corresponding to the second terminal on a first artificial intelligence agent function network element; and the intelligent agent instance corresponding to the first terminal sending a first rule to the first user plane network element, the first rule being used to instruct the first user plane network element to send data requiring multimodal conversion in the first subnet to the first artificial intelligence agent function network element.

[0008] In this application, after the intelligent agent instance corresponding to the first terminal determines to establish a first subnet between the first terminal and the second terminal, a first user plane network element is determined. The first user plane network element can support the establishment of the first subnet by the first terminal and the second terminal. Then, the intelligent agent instance corresponding to the first terminal sends a first request message to the intelligent agent instance corresponding to the second terminal, instructing the intelligent agent instance corresponding to the second terminal to decide to create a local intelligent agent instance corresponding to the second terminal on the first artificial intelligence agent function network element. The intelligent agent instance corresponding to the first terminal sends a first rule to the first user plane network element, instructing the first user plane network element to send the data requiring multimodal conversion in the first subnet to the first artificial intelligence agent function network element. In this way, the local intelligent agent instance corresponding to the second terminal in the first artificial intelligence agent function network element can, based on the first rule, enable the first terminal and the second terminal to achieve conversion between different protocols and different modes without relying on the same protocol for communication, thereby realizing cross-ecosystem interconnection of various terminals.

[0009] In one possible implementation, the method provided in this application further includes: the intelligent agent instance corresponding to the first terminal obtaining the address information of the local intelligent agent instance corresponding to the second terminal from the intelligent agent instance corresponding to the second terminal; the intelligent agent instance corresponding to the first terminal determining a first rule based on the address information of the local intelligent agent instance corresponding to the second terminal; and the intelligent agent instance corresponding to the first terminal sending the address information of the local intelligent agent instance corresponding to the second terminal to the first terminal.

[0010] In one possible implementation, the method provided in this application further includes: an intelligent agent instance corresponding to the first terminal determining a first artificial intelligence agent proxy function network element; the intelligent agent instance corresponding to the first terminal instructing the first artificial intelligence agent function network element to create a local intelligent agent instance corresponding to the first terminal; the intelligent agent instance corresponding to the first terminal determining a first rule based on the address information of the local intelligent agent instance corresponding to the first terminal; and the intelligent agent instance corresponding to the first terminal sending the address information of the local intelligent agent instance corresponding to the first terminal to the first terminal.

[0011] In one possible implementation, the first request message includes: the identifier of the first AI agent function network element and the address information of the local intelligent agent instance corresponding to the first terminal.

[0012] In one possible implementation, the method provided in this application further includes: an intelligent agent instance corresponding to the first terminal sending a second request message to a first control plane network element, the second request message being used to request the first control plane network element to determine a first user plane network element. The intelligent agent instance corresponding to the first terminal receives the identifier of the first user plane network element from the first control plane network element.

[0013] In one possible implementation, the method provided in this application further includes: the intelligent agent instance corresponding to the first terminal sending a second request message to the first control plane network element. The second request message is used to request the first control plane network element to determine the first artificial intelligence agent proxy function network element, and to request the first artificial intelligence agent proxy function network element to create a local intelligent agent instance corresponding to the first terminal.

[0014] In one possible implementation, the method provided in this application embodiment further includes: the intelligent agent instance corresponding to the first terminal sends a third request message to the first control plane network element, the third request message being used to request the first control plane network element to send a first rule to the first user plane network element.

[0015] In one possible implementation, the method provided in this application further includes: an agent instance corresponding to the first terminal determining a second user plane network element. The second user plane network element is used by the first terminal and the second terminal to establish a first subnet.

[0016] In one possible implementation, the method provided in this application further includes: an intelligent agent instance corresponding to the first terminal determining a second artificial intelligence agent function network element; the intelligent agent instance corresponding to the first terminal creating a local intelligent agent instance corresponding to the first terminal within the second artificial intelligence agent function network element; the intelligent agent instance corresponding to the first terminal sending a second rule to the second user plane network element; the second rule including the address information of the local intelligent agent instance corresponding to the first terminal, and the second rule instructing the second user plane network element to send data requiring multimodal conversion in the first subnet to the second artificial intelligence agent function network element; and the intelligent agent instance corresponding to the first terminal sending the address information of the local intelligent agent instance corresponding to the first terminal to the first terminal.

[0017] In one possible implementation, the intelligent agent instance corresponding to the first terminal determines the establishment of the first subnet by: the intelligent agent instance corresponding to the first terminal receiving a first message from the first terminal, the first message including information from a diagram. The intelligent agent instance corresponding to the first terminal determines to establish the first subnet based on the information from the diagram.

[0018] In one possible implementation, the method provided in this application further includes: the intelligent agent instance corresponding to the first terminal determining information about a first sub-intention based on the information in the instruction diagram; the intelligent agent instance corresponding to the first terminal determining the capabilities of the intelligent agent instance required to achieve the intention based on the information about the first sub-intention; the intelligent agent instance corresponding to the first terminal sending a fourth request message to the intelligent agent registration function network element, the fourth request message being used to request an intelligent agent instance that satisfies the capabilities of the intelligent agent instance; and the intelligent agent instance corresponding to the first terminal receiving address information of at least one intelligent agent instance returned from the intelligent agent registration function network element, the at least one intelligent agent instance including the intelligent agent instance corresponding to the second terminal.

[0019] In one possible implementation, the method provided in this application further includes: the intelligent agent instance corresponding to the first terminal determining the information of the first sub-intention based on the information of the instruction diagram; the intelligent agent instance corresponding to the first terminal sending a fifth request message to the intelligent agent registration function network element, the fifth request message being used to request the address information of the intelligent agent instance corresponding to the second terminal; and the intelligent agent instance corresponding to the first terminal receiving the address information of the intelligent agent instance corresponding to the second terminal from the intelligent agent registration function network element.

[0020] In one possible implementation, the first request message includes information about the first sub-intent.

[0021] In one possible implementation, the method provided in this application further includes: the intelligent agent instance corresponding to the first terminal determines second sub-intention information based on the information in the instruction diagram. The intelligent agent instance corresponding to the first terminal determines first template information of the local intelligent agent instance corresponding to the first terminal based on the second sub-intention information. The intelligent agent instance corresponding to the first terminal sends the first template information, or an identifier of the first template information, to the first artificial intelligence agent function network element. Alternatively, the intelligent agent instance corresponding to the first terminal creates a local intelligent agent instance corresponding to the first terminal based on the first template information and sends the local intelligent agent instance corresponding to the first terminal to the first artificial intelligence agent function network element.

[0022] In one possible implementation, the method provided in this application further includes: the intelligent agent instance corresponding to the first terminal determines second sub-intention information based on the information in the instruction diagram. The intelligent agent instance corresponding to the first terminal determines first template information of the local intelligent agent instance corresponding to the first terminal based on the second sub-intention information. The intelligent agent instance corresponding to the first terminal sends the first template information, or an identifier of the first template information, to the second artificial intelligence agent function network element. Alternatively, the intelligent agent instance corresponding to the first terminal creates a local intelligent agent instance corresponding to the first terminal based on the first template information and sends the local intelligent agent instance corresponding to the first terminal to the second artificial intelligence agent function network element.

[0023] Secondly, embodiments of this application provide a communication method, the method comprising: an intelligent agent instance corresponding to a second terminal receiving a first request message from an intelligent agent instance corresponding to a first terminal, the first request message including first sub-intent information; the intelligent agent instance corresponding to the second terminal determining, based on the first sub-intent information, to create a local intelligent agent instance corresponding to the second terminal on a first artificial intelligence agent function network element; and the intelligent agent instance corresponding to the second terminal sending a sixth request message to the first artificial intelligence agent function network element, the sixth request message being used to instruct the deployment of the local intelligent agent instance corresponding to the second terminal on the first artificial intelligence agent function network element.

[0024] In one possible implementation, the sixth request message includes instantiation information of the local agent instance corresponding to the second terminal, which is used to create the local agent instance corresponding to the second terminal.

[0025] In one possible implementation, the first request message includes the identifier of the first user plane network element. The method provided in this application embodiment includes: the intelligent agent instance corresponding to the second terminal determines the first artificial intelligence agent function network element based on the first user plane network element.

[0026] In one possible implementation, the first request message includes the identifier of the first artificial intelligence agent function network element and the address information of the local intelligent agent instance corresponding to the first terminal. The method provided in this application embodiment includes: the intelligent agent instance corresponding to the second terminal instructs the first artificial intelligence agent function network element to create a local intelligent agent instance corresponding to the second terminal.

[0027] In one possible implementation, the method provided in this application embodiment further includes: the intelligent agent instance corresponding to the second terminal sending the address information of the local intelligent agent instance corresponding to the second terminal to the second terminal.

[0028] In one possible implementation, the method provided in this application further includes: the intelligent agent instance corresponding to the second terminal determines the second template information of the local intelligent agent instance corresponding to the second terminal based on the first sub-intention information. The intelligent agent instance corresponding to the second terminal sends the second template information, or an identifier of the second template information, to the first artificial intelligence agent function network element. Alternatively, the intelligent agent instance corresponding to the second terminal creates a local intelligent agent instance corresponding to the second terminal based on the second template information and sends the local intelligent agent instance corresponding to the second terminal to the first artificial intelligence agent function network element.

[0029] Thirdly, embodiments of this application provide a communication method, the method comprising: a first artificial intelligence agent function network element receiving a sixth request message from an intelligent agent instance corresponding to a second terminal. The sixth request message is used to instruct the first artificial intelligence agent function network element to create a local intelligent agent instance corresponding to the second terminal. The first artificial intelligence agent function network element creates a local intelligent agent instance corresponding to the second terminal. The first artificial intelligence agent function network element receives data requiring multimodal conversion from a first subnet.

[0030] In one possible implementation, the method provided in this application further includes: a first artificial intelligence agent function network element receiving second template information, or an identifier of the second template information, from a local intelligent agent instance corresponding to the second terminal. The second template information is used to create a local intelligent agent instance corresponding to the second terminal.

[0031] In one possible implementation, the method provided in this application embodiment further includes: the first artificial intelligence agent function network element creating a local intelligent agent instance corresponding to the first terminal.

[0032] In one possible implementation, the method provided in this application further includes: a first artificial intelligence agent function network element receiving first template information, or an identifier of the first template information, from an intelligent agent instance corresponding to a first terminal. The first template information is used to create a local intelligent agent instance corresponding to the first terminal.

[0033] Fourthly, embodiments of this application provide a communication device that can implement the methods in the first aspect or any possible implementation of the first aspect, and therefore can also achieve the beneficial effects of the first aspect or any possible implementation of the first aspect. The communication device can be an intelligent agent instance corresponding to a first terminal, or it can be a device that supports the intelligent agent instance corresponding to the first terminal in implementing the methods in the first aspect or any possible implementation of the first aspect. The device can implement the above methods through software, hardware, or by hardware executing corresponding software.

[0034] Fifthly, embodiments of this application provide a communication device that can implement the methods in the second aspect or any possible implementation of the second aspect, and therefore can also achieve the beneficial effects of the second aspect or any possible implementation of the second aspect. The communication device can be an intelligent agent instance corresponding to a second terminal, or it can be a device that supports the intelligent agent instance corresponding to the second terminal in implementing the methods in the second aspect or any possible implementation of the second aspect. The device can implement the above methods through software, hardware, or by hardware executing corresponding software.

[0035] Sixthly, embodiments of this application provide a communication device that can implement the methods in the third aspect or any possible implementation of the third aspect, and thus also achieve the beneficial effects of the third aspect or any possible implementation of the third aspect. This communication device can be a first artificial intelligence agent function network element, or an apparatus that supports the first artificial intelligence agent function network element in implementing the methods in the third aspect or any possible implementation of the third aspect. This device can implement the above methods through software, hardware, or by hardware executing corresponding software.

[0036] In a seventh aspect, embodiments of this application provide a computer-readable storage medium storing a computer program or instructions that, when executed on a computer, cause the computer to perform the methods described in any of the possible implementations of the first aspect.

[0037] Eighthly, embodiments of this application provide a computer-readable storage medium storing a computer program or instructions that, when executed on a computer, cause the computer to perform the methods described in any of the possible implementations of the second aspect.

[0038] Ninthly, embodiments of this application provide a computer-readable storage medium storing a computer program or instructions that, when executed on a computer, cause the computer to perform the methods described in any of the possible implementations of the third aspect to the third aspect.

[0039] In a tenth aspect, embodiments of this application provide a computer program product including instructions that, when executed on a computer, cause the computer to perform the methods described in the first aspect or various possible implementations of the first aspect.

[0040] Eleventhly, embodiments of this application provide a computer program product including instructions that, when executed on a computer, cause the computer to perform the methods described in the second aspect or various possible implementations of the second aspect.

[0041] In a twelfth aspect, embodiments of this application provide a computer program product including instructions that, when executed on a computer, cause the computer to perform the methods described in the third aspect or various possible implementations of the third aspect.

[0042] In a thirteenth aspect, embodiments of this application provide a communication device comprising: at least one processor. The at least one processor is coupled to a memory, and when the communication device is in operation, the processor executes computer execution instructions or programs stored in the memory to cause the communication device to perform a method as described in the first aspect or any of the various possible designs of the first aspect.

[0043] In a fourteenth aspect, embodiments of this application provide a communication device comprising: at least one processor. The at least one processor is coupled to a memory, and when the communication device is in operation, the processor executes computer execution instructions or programs stored in the memory to cause the communication device to perform a method as described in the second aspect above, or any of the various possible designs of the second aspect.

[0044] In a fifteenth aspect, embodiments of this application provide a communication device comprising: at least one processor. The at least one processor is coupled to a memory, and when the communication device is in operation, the processor executes computer execution instructions or programs stored in the memory to cause the communication device to perform a method as described in the third aspect above, or any of the various possible designs of the third aspect.

[0045] It should be understood that the memory described in any of aspects thirteen to fifteen can also be replaced by a storage medium, and the embodiments of this application do not limit this.

[0046] In one possible implementation, the memory described in any of aspects thirteen to fifteen can be internal to the communication device. Of course, the memory can also be located external to the communication device, but at least one processor can still execute computer execution instructions or programs stored in the memory.

[0047] In a sixteenth aspect, embodiments of this application provide a communication device comprising one or more modules for implementing the methods of any one of the first, second, and third aspects described above. The one or more modules may correspond to the various steps in the methods of any one of the first, second, and third aspects described above.

[0048] In a seventeenth aspect, embodiments of this application provide a chip system including a processor. The processor reads and executes a computer program stored in a memory to perform the methods of the first aspect and any possible implementation thereof. Optionally, the chip system may be a single chip or a chip module composed of multiple chips. Optionally, the chip system further includes a memory, which is connected to the processor via circuitry or wiring. Further optionally, the chip system includes a communication interface. The communication interface is used to communicate with other modules outside the chip.

[0049] In an eighteenth aspect, embodiments of this application provide a chip system including a processor. The processor reads and executes a computer program stored in a memory to perform the methods in the second aspect and any possible implementation thereof. Optionally, the chip system may be a single chip or a chip module composed of multiple chips. Optionally, the chip system further includes a memory, which is connected to the processor via circuitry or wiring. Further optionally, the chip system includes a communication interface. The communication interface is used to communicate with other modules outside the chip.

[0050] In a nineteenth aspect, embodiments of this application provide a chip system including a processor. The processor reads and executes a computer program stored in a memory to perform the methods of the third aspect and any possible implementation thereof. Optionally, the chip system may be a single chip or a chip module composed of multiple chips. Optionally, the chip system further includes a memory, which is connected to the processor via circuitry or wiring. Further optionally, the chip system includes a communication interface. The communication interface is used to communicate with other modules outside the chip.

[0051] In a twentieth aspect, embodiments of this application provide a communication system comprising: a first terminal, a second terminal, a first artificial intelligence agent function network element, and an intelligent agent registration function network element. The intelligent agent instance corresponding to the first terminal is used to execute the methods in the first aspect and any possible implementation thereof. The intelligent agent instance corresponding to the second terminal is used to execute the methods in the second aspect and any possible implementation thereof. The first artificial intelligence agent function network element is used to execute the methods in the third aspect and any possible implementation thereof.

[0052] The agent registration function network element is used to store and register agent instances. The first terminal is used to send the user's task requirements. The second terminal is used to execute the user's task.

[0053] Any of the devices, computer storage media, computer program products, chips, or communication systems provided above are used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects of the corresponding solutions in the corresponding methods provided above, and will not be repeated here. Attached Figure Description

[0054] Figure 1 is a conceptual diagram of an agent network provided in an embodiment of this application;

[0055] Figure 2 is a schematic diagram of a networked drone and robot dog collaborating through an intelligent agent network to find lost items, according to an embodiment of this application.

[0056] Figure 3 is an example diagram of finding lost items provided in an embodiment of this application;

[0057] Figure 4 is a schematic diagram of a system architecture provided in an embodiment of this application;

[0058] Figure 5 is a schematic diagram of a communication method provided in an embodiment of this application;

[0059] Figure 6 is a schematic diagram of a process for two terminals to establish a virtual subnet for low-latency communication according to an embodiment of this application;

[0060] Figure 7 is a schematic diagram of a specific implementation method for two terminals to establish a virtual subnet for low-latency communication according to an embodiment of this application;

[0061] Figure 8 is a schematic diagram of another specific implementation method for two terminals to establish a virtual subnet for low-latency communication provided in an embodiment of this application;

[0062] Figure 9 is a schematic diagram of a multi-user plane communication process provided in an embodiment of this application;

[0063] Figure 10 is a schematic diagram of a process for at least three terminals to establish a virtual subnet for low-latency communication according to an embodiment of this application;

[0064] Figure 11 is a schematic diagram of a specific implementation method for establishing a virtual subnet for low-latency communication at least by a terminal according to an embodiment of this application;

[0065] Figure 12 is a schematic diagram of another specific implementation method for at least three terminals to establish a virtual subnet for low-latency communication provided in an embodiment of this application;

[0066] Figure 13 is a schematic diagram of another multi-user plane communication process provided in an embodiment of this application;

[0067] Figure 14 is a schematic diagram of a process for synchronizing local agent instances and agent instance information according to an embodiment of this application;

[0068] Figure 15 is a schematic diagram of a communication device provided in an embodiment of this application;

[0069] Figure 16 is a schematic diagram of the hardware structure of a communication device provided in an embodiment of this application;

[0070] Figure 17 is a schematic diagram of a chip structure provided in an embodiment of this application. Detailed Implementation

[0071] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B; "and / or" in this text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0072] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this embodiment, unless otherwise stated, "a plurality of" means two or more.

[0073] Furthermore, the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0074] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0075] It should be understood that in this application, "at least one (item)" means one or more. "More than one" means two or more. "At least two (items)" means two or three or more. "And / or" is used to describe the relationship between related objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural.

[0076] The character " / " generally indicates that the preceding and following objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any single or multiple items. For example, "at least one of a, b, or c" can be expressed as: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0077] Both "...when" and "if" indicate that a corresponding action will be taken under certain objective circumstances. They are not time limits, nor do they require a judgment action to be taken when the action is taken, nor do they imply any other limitations.

[0078] The steps involved in the communication method of an intelligent agent network provided in this application embodiment are merely examples. Not all steps are mandatory, nor are all contents of each piece of information or message required. They can be added or removed as needed during use.

[0079] In this application, the same step or a step or message with the same function can be referenced and learned from each other in different embodiments.

[0080] Before introducing the embodiments of this application, the relevant terms involved in the embodiments of this application are first defined as follows:

[0081] 1. Intelligent Agent: A computational entity that resides in a specific environment and can function autonomously and continuously. It possesses characteristics such as residency, responsiveness, sociality, and initiative. An intelligent agent can be any entity with a certain level of intelligence, such as software programs, robots, or sensors.

[0082] 2. Large Language Models (LLM): These are deep learning models trained on massive amounts of text data. They can not only generate natural language text, but also deeply understand the meaning of text and handle various natural language tasks, such as text summarization, question answering, and translation.

[0083] Referring to Figure 1, which is a conceptual diagram of an agent network provided in an embodiment of this application, Figure 1(a) is a conceptual diagram of the agent network. The agent network consists of multiple agents combined with large language models (LLMs).

[0084] Agents can perform functions such as planning, actions, tools, memory, and reflection. Each agent in a multi-agent system can independently perceive its environment, make decisions, and execute actions. Agents can communicate and collaborate to provide readily available, on-demand intelligent connectivity and information exchange services.

[0085] LLM can process language, encoding, images, videos, robots, and more. Based on this, intelligent agent networks can achieve intelligent connections with humans, machines, digital avatars, and embodied intelligence to complete information exchange.

[0086] As shown in Figure 1(b), humans, machines, digital assistants, and embodied intelligence can autonomously access the LLM-based agent network using their digital identities. After establishing a session, subnets can be created as needed, and their network behavior is secure and controllable. Humans (also known as natural persons) can interact with the agent network using natural language (such as text and voice), video, images, and touch; machines can interact with the agent network using machine commands and sensor data; digital assistants can interact with the agent network using intent expressions and semantic features; and embodied intelligence can interact with the agent network using model parameters and intelligent tasks. Centered on the agent network, autonomous and efficient collaboration among agents of different types, manufacturers, models, and intelligence levels can be achieved to jointly complete tasks. This enables efficient information transmission and accurate understanding of commands between agents to ensure efficient task closure, and provides necessary perception, intelligence, data empowerment, and support services for various agents.

[0087] For example, Figure 2 illustrates a networked drone and robot dog collaborating through an intelligent agent network to locate lost items. The specific method is implemented through specific network elements or devices within the intelligent agent network; here, a specific network element is used as an example. The specific process includes:

[0088] Step 1: The terminal sends a request message to a specific network element, and the specific network element receives the request message from the terminal.

[0089] Request messages are used to indicate the user's intent. For example, a request message might be used to request the search for a lost item (such as a wallet) in a predefined area (such as a park).

[0090] For example, a request message can be either voice or an image.

[0091] Step 2: A specific network element uses LLM to identify the user's intent in the request message and determines the task to be performed based on the intent.

[0092] For example, a specific network element can identify the intent in the request message (to find a lost item in a preset area) and determine that a lost item needs to be found in a preset area.

[0093] Step 3: A specific network element determines at least one subtask based on the task to be performed.

[0094] For example, finding lost items in a preset area can be broken down into subtask one (locating the lost items in the preset area) and subtask two (picking up the lost items based on their location).

[0095] Step 3: A specific network element determines the capability required to execute a subtask based on at least one subtask.

[0096] For example, based on sub-task one (locating lost items in a preset area), it is determined that the ability to fly and take pictures is required; based on sub-task two (picking up lost items based on location), the ability to move and grasp items is required.

[0097] Step 4: The specific network element determines the machine with the capability required to execute the subtask.

[0098] For example, based on flight capabilities and photography capabilities, a networked drone can be identified as the machine performing sub-task one; based on mobility and the ability to pick up objects, a robot dog can be identified as the machine performing sub-task two.

[0099] Step 5: A specific network element sends instruction information to the machine designated to perform the task, based on at least one sub-task. Correspondingly, the machine performing the task receives the instruction information from the specific network element. The instruction information is used to instruct the machine to perform an action.

[0100] For example, referring to Figure 3, a specific network element instructs the connected drone to patrol the park along a set path according to subtask one, and to identify and locate lost items; after locating the lost items, the specific network element instructs the robot dog to go to the located location to pick up the lost items according to subtask two.

[0101] Step 6: The specific network element sends a result report to the user based on the task execution status.

[0102] For example, the results report may include: the location of the lost item, the time taken to complete the task, the battery level of the connected drone, and the battery level of the robot dog.

[0103] In existing technologies, communication between intelligent agents in a network can fail if two terminals use different communication protocols. Furthermore, in a virtual subnet, if the modal information supported by different agents is inconsistent, the agents cannot collaborate. In short, existing technologies cannot support cross-modal communication and cross-ecosystem interconnection among multiple agents in a virtual subnet.

[0104] Based on this, embodiments of this application provide a communication method in which an agent instance determines to deploy a local agent instance according to the terminal's intent, and then instructs the control plane to select a suitable user plane to trigger the relevant terminal to establish a virtual subnet. In this way, by deploying a local agent instance to create a virtual subnet for agent components, multimodal data conversion and autonomous agent collaboration within the agent network are achieved.

[0105] The technical solution of this application can be applied to various communication systems, such as: Long Time Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication systems, Public Land Mobile Network (PLMN) systems, Device to Device (D2D) network systems or Machine to Machine (M2M) network systems, the 5th Generation (5G) system, and future network communication technologies, etc.

[0106] The network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0107] As shown in Figure 4, Figure 4 is a schematic diagram of a system architecture provided in an embodiment of this application. The system includes: a core network (CN), an access network (AN), and a terminal.

[0108] The core network is primarily responsible for handling the network's main service processes and data transmission, including: agent network, user plane, and control plane.

[0109] The intelligent agent network includes: intelligent session function (ISF) network element, artificial intelligence agent function (AIAF) network element, agent registration function (ARF) network element, and agent template repository (ATR).

[0110] ISF network elements are used to support terminals in creating intelligent sessions, selecting the AIAF function, and requesting the creation of the Agent instance corresponding to the terminal.

[0111] AIAF network elements are used for the creation and management of intelligent agent instances.

[0112] ARF network elements are used to store and register agent instances.

[0113] ATR is used to store agent templates.

[0114] The user plane includes: user plane function (UPF) network elements and at least one AIAF network element.

[0115] UPF network elements, as interfaces with the data network, perform functions such as user plane data forwarding, session / flow-based billing and statistics, and bandwidth limiting.

[0116] Control plane: Primarily responsible for transmitting control signaling to control the establishment, maintenance, and release of call flows. Specifically, the control plane carries signaling or control messages.

[0117] The access network is used to connect user terminal equipment to the core network. It is mainly responsible for connecting users' voice, data and other communication services to a wider network to realize the transmission of communication services.

[0118] The access network can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, NTN (non-terrestrial network) systems, or future-oriented evolution systems (such as 6G mobile communication systems). The access network can also be an open RAN (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system, or a communication system that integrates two or more of the above systems.

[0119] Access networks, sometimes also called access network equipment, RAN entities, or access nodes, are part of a communication system and are used to help terminals achieve wireless access.

[0120] Radio access network equipment: A device deployed in a radio access network that meets 4G standards and provides wireless communication functions for terminals, such as an evolved node B (eNB) in a long term evolution (LTE) system. eNBs can include various forms of macro base stations, micro base stations (also called small cells), relay stations, access points, wearable devices, and vehicle-mounted equipment. An eNB can also be a transmission and reception point (TRP).

[0121] Wireless access network equipment: A device deployed in a wireless access network that meets 5G standards and provides wireless communication functions for terminals, such as a next-generation base station (g nodeB, gNB). gNBs can include various forms of macro base stations, micro base stations (also known as small stations), relay stations, access points, wearable devices, and vehicle-mounted equipment. gNBs can also be transmission and reception points (TRPs) or transmission measurement functions (TMFs). gNBs can include central units (CUs) and distributed units (DUs) integrated on them.

[0122] In addition, wireless access network equipment can also be a radio network controller (RNC), a radio controller in a cloud radio access network (CRAN) system, a base station controller (BSC), a home base station (e.g., home evolved nodeB, or home node B, HNB), a baseband unit (BBU), a transmitting and receiving point (TRP), a transmitting point (TP), a mobile switching center, a base transceiver station (BTS) in a global system for mobile communication (GSM) or code division multiple access (CDMA) network, a node base station (NB) in a wideband code division multiple access (WCDMA) network, an evolved NB (eNB or eNodeB) in LTE, a base station device in a future network, or an access network device in a future evolved PLMN network, or a wearable device or vehicle-mounted device.

[0123] Terminals can include various handheld devices, in-vehicle devices, wearable devices, computing devices, or other processing devices connected to a wireless modem with wireless communication capabilities; they can also include subscriber units, cellular phones, smartphones, wireless data cards, personal digital assistant (PDA) computers, tablet computers, wireless modems, handheld devices, laptop computers, cordless phones, wireless local loop (WLL) stations, machine-type communication (MTC) terminals, user equipment (UE), mobile stations (MS), terminal devices, or relay user equipment, etc. Relay user equipment can be, for example, a 5G residential gateway (RG). For ease of description, the user equipment mentioned above is collectively referred to as a terminal in this application.

[0124] It should be understood that the terminal in the embodiments of this application can also be a terminal in various vertical industry application fields such as Internet of Things terminal devices, ports, smart factories, railway transportation, logistics, drones, and autonomous vehicles. For example, mobile robots, automated guided vehicles (AGVs), autonomous vehicles, control equipment and sensors on trains, and control equipment and sensors deployed in factories.

[0125] The system also includes a network exposure function (NEF) element, which is mainly used to support the exposure of capabilities and events.

[0126] Optionally, the system may also include third-party agent networks, such as 3rd Agent (MM LLM4) and 3rd Agent (MM LLM5).

[0127] This application also involves some network elements, such as access and mobility management function (AMF) network elements, session management function (SMF) network elements, and unified data function (UDM) network elements.

[0128] UDM network elements are mainly responsible for user contract management, access authorization, and authentication information generation.

[0129] The AMF (Agency Default Manager) network element primarily performs functions such as mobility management, access authentication, and authorization. It is also responsible for transmitting user policies between the terminal and the PCF (Programmable Default Manager) network element. The SMF (Session Default Manager) network element is mainly responsible for session management in the network architecture. Its functions include session establishment, modification, and release. For example, the session management network element assigns IP addresses to terminals or selects a UPF (User-Defined Default Manager) to provide packet forwarding functionality.

[0130] SMF network elements are mainly used for session management.

[0131] It should be noted that the AN, AMF, SMF, UDM, and UPF network elements mentioned in the embodiments of this application are merely names and do not limit the device itself. In 5G networks and other future networks, the network elements or entities corresponding to AN, AMF, SMF, UDM, and UPF network elements may also have other names, and the embodiments of this application do not impose specific limitations on them.

[0132] In the embodiments of this application, the specific structure of the execution subject of a communication method is not particularly limited, as long as communication can be performed according to the communication method of this application by running a program that records the code of a communication method of this application. For example, the execution subject of the communication method provided in the embodiments of this application can be a functional module in an artificial intelligence agent function network element that can call and execute a program, or a communication device applied in an artificial intelligence agent function network element, such as a chip, chip system, integrated circuit, etc. These chips, chip systems, and integrated circuits can be disposed inside the artificial intelligence agent function network element, or they can be independent of the artificial intelligence agent function network element, and this application does not impose any restrictions. The execution subject of the instruction communication method provided in the embodiments of this application can be a functional module in an intelligent agent registration function network element that can call and execute a program, or a communication device applied in an intelligent agent registration function network element, such as a chip, chip system, integrated circuit, etc. These chips, chip systems, and integrated circuits can be disposed inside the intelligent agent registration function network element, or they can be independent of the intelligent agent registration function network element, and this application does not impose any restrictions. The following embodiments describe an example of a communication method where the execution subject is an artificial intelligence agent function network element. Where there is no conflict, the solutions of the following embodiments can be used in combination.

[0133] As shown in Figure 5, Figure 5 illustrates a communication method provided in an embodiment of this application, the method comprising:

[0134] Step 501: Determine the intelligent agent instance corresponding to the first terminal and establish the first subnet.

[0135] Among them, the intelligent agent instance corresponding to the first terminal is the intelligent agent instance created by the first terminal in the artificial intelligence agent function network element.

[0136] For example, the first terminal sends its capabilities and the capabilities granted to it by the network to the AI ​​agent function network element. The AI ​​agent function network element then creates an agent instance (Agent1) based on the first terminal's capabilities, the capabilities granted to it by the network, and the subscription information. The agent instance (Agent1) corresponding to the first terminal includes both the first terminal's capabilities and the capabilities granted to it by the network.

[0137] The first subnet is a virtual subnet between the first terminal and at least one second terminal.

[0138] In one possible embodiment of this application, a first terminal sends a first message to an intelligent agent instance corresponding to the first terminal. Correspondingly, the intelligent agent instance corresponding to the first terminal receives the first message from the first terminal. The first message includes information from a diagram. Based on the information from the diagram, the intelligent agent instance corresponding to the first terminal determines to establish a first subnet.

[0139] It is worth noting that the first terminal sending the first message to the intelligent agent instance corresponding to the first terminal can also be considered as the first terminal sending the first message to the AI ​​agent function network element corresponding to the first terminal. Correspondingly, the AI ​​agent function network element corresponding to the first terminal receives the first message from the first terminal. Based on the information in the diagram, the AI ​​agent function network element corresponding to the first terminal determines to establish the first subnet.

[0140] It is understood that the intelligent agent instances corresponding to the first terminal in the following embodiments can all be equivalently described as the artificial intelligence agent function network elements corresponding to the first terminal, and are not limited in the embodiments of this application.

[0141] The information in the diagram can represent the user's intent. The user's intent indicates a task that multiple intelligent agents need to collaborate to complete, such as the first terminal performing real-time voice control on the second terminal.

[0142] As an example, the agent instance corresponding to the first terminal understands the user's intent and decomposes the task into a first subtask based on the intent. The agent instance corresponding to the first terminal sends the intent of the first subtask to the first control plane network element. The intent of the first subtask is used to instruct the establishment of a first subnet between the first terminal and the second terminal.

[0143] In one possible embodiment, the first message includes: an identifier of a first terminal, an identifier of a second terminal, and an identifier of a task of the first terminal. The task of the first terminal is used to fulfill the user's intent. The task of the first terminal is also used to instruct the establishment of a first subnet between the first terminal and the second terminal, and to instruct the deployment of a local intelligent agent instance.

[0144] Step 502: The first user plane network element is determined by the intelligent agent instance corresponding to the first terminal.

[0145] The first user plane network element is used by the first terminal and the second terminal to establish the first subnet.

[0146] In one possible implementation, the agent instance corresponding to the first terminal can directly determine the first user plane network element.

[0147] As an example, the agent instance corresponding to the first terminal determines the first user plane network element based on the user's intent.

[0148] In another possible implementation, the agent instance corresponding to the first terminal can determine the first user plane network element through the first control plane network element.

[0149] In one possible embodiment of this application, the specific method for determining the first user plane network element by the intelligent agent instance corresponding to the first terminal includes:

[0150] Step 1: The agent instance corresponding to the first terminal sends a second request message to the first control plane network element. Correspondingly, the first control plane network element receives the second request message from the agent instance corresponding to the first terminal.

[0151] The second request message is used to request the first control plane network element to determine the first user plane network element.

[0152] Among them, the first control plane network element can be a control plane (CP).

[0153] For example, the agent instance (Agent1) corresponding to the first terminal sends a request message to the control plane.

[0154] Step 2: The intelligent agent instance corresponding to the first terminal receives the identifier of the first user plane network element from the first control plane network element.

[0155] As an example, the first control plane determines the first user plane network element based on the second request message and sends the identifier of the first user plane network element to the intelligent agent instance corresponding to the first terminal.

[0156] Step 503: The agent instance corresponding to the first terminal sends a first request message to the agent instance corresponding to the second terminal. Correspondingly, the agent instance corresponding to the second terminal receives the first request message from the agent instance corresponding to the first terminal.

[0157] It is worth noting that the intelligent agent instance corresponding to the first terminal sending the first request message to the intelligent agent instance corresponding to the second terminal can also be regarded as the artificial intelligence agent function network element corresponding to the first terminal sending the first request message, and correspondingly, the artificial intelligence agent function network element corresponding to the second terminal receiving the first request message.

[0158] It is understood that the intelligent agent instances corresponding to the second terminal in the following embodiments can all be equivalently described as the artificial intelligence agent function network elements corresponding to the second terminal, and are not limited in the embodiments of this application.

[0159] The first request message is used for the decision of the intelligent agent instance corresponding to the second terminal to create a local intelligent agent instance corresponding to the second terminal on the first artificial intelligence agent function network element.

[0160] In one possible embodiment, the first request message includes the identifier of the first user plane network element.

[0161] The intelligent agent instance corresponding to the second terminal is located in the artificial intelligence agent function network element, including the capabilities of the second terminal and the capabilities granted to the second terminal by the network. The intelligent agent instance corresponding to the second terminal is used to create a local intelligent agent instance corresponding to the second terminal on the first artificial intelligence agent function network element.

[0162] For example, after the agent instance (Agent1) corresponding to the first terminal sends a first request message to the agent instance (Agent2) corresponding to the second terminal, Agent2 determines, based on the first request message, to deploy the local agent instance corresponding to the second terminal through the first user plane network element. When the first user plane network element and the first artificial intelligence agent function (L-AIAF) network element are not configured together, Agent2 determines to create the local agent instance (L-Agent2) corresponding to the second terminal on the L-AIAF network element that is closest to the location of the first user plane network element; when the first user plane network element and the L-AIAF network element are configured together, Agent2 determines to create L-Agent2 on the L-AIAF network element integrated with the first user plane network element.

[0163] In one possible embodiment of this application, the agent instance corresponding to the second terminal can be determined through an agent registration function network element. The agent registration function network element includes registration information for multiple agent instances, including the agent instance corresponding to the second terminal. The method includes:

[0164] Step 1: The intelligent agent instance corresponding to the first terminal determines the information of the first sub-intention based on the information in the instruction diagram.

[0165] The information in the first sub-intention includes the capabilities required to complete the task performed by the first sub-intention.

[0166] Step 2: The agent instance corresponding to the first terminal determines the capabilities of the agent instance required to achieve the intent based on the information of the first sub-intent.

[0167] Step 3: The agent instance corresponding to the first terminal sends a fourth request message to the agent registration function network element. Correspondingly, the agent registration function network element receives the fourth request message from the agent instance corresponding to the first terminal.

[0168] The fourth request message is used to request an agent instance that satisfies the capabilities of the agent instance.

[0169] Step 4: The agent registration function network element sends the address information of at least one agent instance to the agent instance corresponding to the first terminal. Correspondingly, the agent instance corresponding to the first terminal receives the address information of at least one agent instance returned by the agent registration function network element. The at least one agent instance includes the agent instance corresponding to the second terminal.

[0170] In another possible embodiment of this application, the agent instance corresponding to the second terminal is directly indicated by the first terminal. The first message sent by the first terminal to the agent instance corresponding to the first terminal includes the identifier of the second terminal. The specific method includes:

[0171] Step 1: The intelligent agent instance corresponding to the first terminal determines the information of the first sub-intention based on the information in the instruction diagram.

[0172] Step 2: The agent instance corresponding to the first terminal sends a fifth request message to the agent registration function network element. Correspondingly, the agent registration function network element receives the fifth request message from the agent instance corresponding to the first terminal. The fifth request message requests the address information of the agent instance corresponding to the second terminal.

[0173] Step 3: The agent registration function network element sends the address information of the agent instance corresponding to the second terminal to the agent instance corresponding to the first terminal. Correspondingly, the agent instance corresponding to the first terminal receives the address information of the agent instance corresponding to the second terminal from the agent registration function network element.

[0174] Step 504: The intelligent agent instance corresponding to the first terminal sends the first rule to the first user plane network element. Correspondingly, the first user plane network element receives the first rule from the intelligent agent instance corresponding to the first terminal.

[0175] The first rule is used to instruct the first user plane network element to send the data that needs to be converted into multiple modes in the first subnet to the first artificial intelligence agent function network element.

[0176] In one possible embodiment of this application, the intelligent agent instance corresponding to the first terminal sends a third request message to the first control plane network element. Correspondingly, the first control plane network element receives the third request message from the intelligent agent instance corresponding to the first terminal. The third request message is used to request the first control plane network element to send a first rule to the first user plane network element.

[0177] In one embodiment of this application, the third request message includes: address information of the first terminal, address information of the second terminal, address information of the local intelligent agent instance corresponding to the second terminal, and quality of service (QoS) information. The QoS information is used to instruct either the first terminal or the second terminal to send uplink data via a QoS stream.

[0178] For example, the third request message is intelligent switching service information, and the first control plane network element sends quality of service rules to the first terminal and the second terminal based on the intelligent service switching information.

[0179] For example, the first control plane network element sends a first rule to the first user plane network element based on the third request message. The first rule instructs the first user plane network element to forward data destined for the local agent instance (L-Agent2) corresponding to the second terminal to L-Agent2. The first rule also instructs data destined for either the first terminal or the second terminal to be forwarded internally within the first user plane network element.

[0180] In this application, after the intelligent agent instance corresponding to the first terminal determines to establish a first subnet between the first terminal and the second terminal, a first user plane network element is determined. The first user plane network element can support the establishment of the first subnet by the first terminal and the second terminal. Then, the intelligent agent instance corresponding to the first terminal sends a first request message to the intelligent agent instance corresponding to the second terminal, instructing the intelligent agent instance corresponding to the second terminal to decide to create a local intelligent agent instance corresponding to the second terminal on the first artificial intelligence agent function network element. The intelligent agent instance corresponding to the first terminal sends a first rule to the first user plane network element, instructing the first user plane network element to send the data requiring multimodal conversion in the first subnet to the first artificial intelligence agent function network element. In this way, the local intelligent agent instance corresponding to the second terminal in the first artificial intelligence agent function network element can, based on the first rule, enable the first terminal and the second terminal to achieve conversion between different protocols and different modes without relying on the same protocol for communication, thereby realizing cross-ecosystem interconnection of various terminals.

[0181] In one possible embodiment of this application, the above method further includes:

[0182] Step 1: The agent instance corresponding to the first terminal obtains the address information of the local agent instance corresponding to the second terminal from the agent instance corresponding to the second terminal.

[0183] In one possible implementation, the agent instance corresponding to the second terminal sends a confirmation message to the agent instance corresponding to the first terminal to confirm that a local agent instance corresponding to the second terminal has been created on the first AI agent function network element. The confirmation message includes the address information of the local agent instance corresponding to the second terminal.

[0184] Step 2: The agent instance corresponding to the first terminal determines the first rule based on the address information of the local agent instance corresponding to the second terminal.

[0185] For example, the intelligent agent instance (Agent1) corresponding to the first terminal determines the intelligent switching service information based on the address information of the local intelligent agent instance (L-Agent2) corresponding to the second terminal. The intelligent switching service information includes the address information of the first terminal, the address information of the second terminal, the address information of L-Agent2, and the quality of service information.

[0186] Step 3: The agent instance corresponding to the first terminal sends the address information of the local agent instance corresponding to the second terminal to the first terminal. Correspondingly, the first terminal receives the address information of the local agent instance corresponding to the second terminal from the agent instance corresponding to the first terminal.

[0187] In the above embodiments, the agent instance corresponding to the first terminal creates a first subnet between the first terminal and the second terminal; in other words, the first subnet only includes the first terminal and the second terminal. When the agent instance corresponding to the first terminal creates a first subnet between two or more terminals, for example, when the first subnet also includes a third terminal, the method provided in this application embodiment further includes:

[0188] Step 1: Determine the first AI agent agent network element corresponding to the first terminal's intelligent agent instance.

[0189] In one possible embodiment of this application, the intelligent agent instance corresponding to the first terminal sends a second request message to the first control plane network element. Correspondingly, the first control plane network element receives the second request message from the intelligent agent instance corresponding to the first terminal.

[0190] The second request message is used to request the first control plane network element to determine the first artificial intelligence agent agent function network element, and to request the first artificial intelligence agent agent function network element to create a local intelligent agent instance corresponding to the first terminal.

[0191] In one possible implementation, the first user plane network element and the first AI agent function network element are not combined. The first control plane network element sends a response message to the agent instance corresponding to the first terminal. The response message includes the identifier of the first user plane network element. Based on the identifier of the first user plane network element, the agent instance corresponding to the first terminal determines the nearest local agent instance to be deployed on the first user plane network element; that is, the agent instance corresponding to the first terminal determines the first AI agent function network element with the optimal location for the first user plane network element. The first AI agent function network element is used to deploy the local agent instance corresponding to the first terminal.

[0192] For example, the first control plane network element selects a first user plane network element for the first terminal, the second terminal, and the third terminal. This first user plane network element optimizes the routing among the three terminals. Then, the first control plane network element sends a response message to the agent instance (Agent1) corresponding to the first terminal, including the identifier of the first user plane network element. Agent1 then determines the first artificial intelligence agent function (L-AIAF) network element with the optimal location for the first user plane network element.

[0193] In another possible implementation, the first user plane network element and the first AI agent function network element are combined. The first control plane network element sends a response message to the intelligent agent instance corresponding to the first terminal. The response message includes the identifier of the first user plane network element. The intelligent agent instance corresponding to the first terminal can determine the first AI agent function network element based on the identifier of the first user plane network element.

[0194] For example, the first control plane network element sends a response message to Agent1, which includes the identifier of the first user plane network element. Since the first user plane network element and the L-AIAF network element are configured together, Agent1 can identify the L-AIAF network element based on the identifier of the first user plane network element.

[0195] Step 2: The intelligent agent instance corresponding to the first terminal instructs the first artificial intelligence agent function network element to create a local intelligent agent instance corresponding to the first terminal.

[0196] In one possible implementation, the agent instance corresponding to the first terminal sends a request message to the first AI agent function network element. This request message instructs the creation of a local agent instance corresponding to the first terminal. The local agent instance corresponding to the first terminal is used for group management of the local agent instances corresponding to the second and third terminals, respectively.

[0197] The request message includes instantiation information of the local intelligent agent instance corresponding to the first terminal, which is used to create the local intelligent agent instance corresponding to the first terminal.

[0198] For example, the request message includes the instantiation information of the local intelligent agent instance (L-Agent1) corresponding to the first terminal, the task identifier, and the subscribed event.

[0199] In one possible embodiment of this application, the instantiation information of the local intelligent agent instance (L-Agent1) corresponding to the first terminal can be the first template information. The method provided in this application embodiment further includes:

[0200] Step a: The intelligent agent instance corresponding to the first terminal determines the second sub-intention information based on the information in the instruction diagram.

[0201] Step b: The agent instance corresponding to the first terminal determines the first template information of the local agent instance corresponding to the first terminal based on the second sub-intention information.

[0202] Step c1: The intelligent agent instance corresponding to the first terminal sends the first template information, or the identifier of the first template information, to the first artificial intelligence agent function network element.

[0203] Among them, the first artificial intelligence agent function network element creates a local intelligent agent instance corresponding to the first terminal based on the first template information or the identifier of the first template information.

[0204] Step c2: The intelligent agent instance corresponding to the first terminal creates a local intelligent agent instance corresponding to the first terminal based on the first template information, and sends the local intelligent agent instance corresponding to the first artificial intelligence agent function network element.

[0205] Group management refers to the ability of the local agent instance corresponding to the first terminal to allocate data to the local agent instances corresponding to the second and third terminals, respectively.

[0206] In another possible implementation, the agent instance corresponding to the first terminal sends a request message to the first control plane network element, requesting local agent instantiation. The first control plane network element then sends a request message to the first user plane network element, requesting the creation of a local agent instance corresponding to the first terminal in the first artificial intelligence agent function network element.

[0207] For example, Agent1 sends a request message to the first control plane network element. This request message includes the instantiation information of the local intelligent agent instance (L-Agent1) corresponding to the first terminal, the task identifier, the subscribed events, and the identifier of the first user plane network element. Since the first user plane network element and the L-AIAF network element are combined, the first control plane network element further sends a request message to the first user plane network element, including the instantiation information of L-Agent1, the task identifier, and the subscribed events. The L-AIAF network element then deploys L-Agent1 based on its instantiation information.

[0208] Step 3: The agent instance corresponding to the first terminal determines the first rule based on the address information of the local agent instance corresponding to the first terminal.

[0209] Step 4: The agent instance corresponding to the first terminal sends the address information of the local agent instance corresponding to the first terminal to the first terminal. Correspondingly, the first terminal receives the address information of the local agent instance corresponding to the first terminal from the agent instance corresponding to the first terminal.

[0210] In one possible embodiment of this application, the first request message includes: the identifier of the first artificial intelligence agent function network element and the local intelligent agent instance corresponding to the first terminal.

[0211] In this embodiment, the first user plane network element is used by the first terminal and the second terminal to create corresponding local intelligent agent instances on the first artificial intelligence agent function network element. Optionally, in addition to the first user plane network element, a second user plane network element may also be included.

[0212] In one possible embodiment of this application, the method further includes: an agent instance corresponding to the first terminal determining a second user plane network element. The second user plane network element is used by the first terminal and the second terminal to establish a first subnet.

[0213] In one possible implementation, the agent instance corresponding to the first terminal determines the first user plane network element and the second user plane network element through the first control plane network element.

[0214] In one possible embodiment of this application, when the agent instance corresponding to the first terminal creates a first subnet between two or more terminals, for example, if the first subnet also includes a third terminal, the method provided in this application embodiment further includes:

[0215] Step 1: The intelligent agent instance corresponding to the first terminal determines the second artificial intelligence agent function network element.

[0216] Among them, the second artificial intelligence agent function network element creates a local intelligent agent instance corresponding to the first terminal.

[0217] Step 2: The intelligent agent instance corresponding to the first terminal creates a local intelligent agent instance corresponding to the first terminal in the second artificial intelligence agent function network element.

[0218] In one possible embodiment of this application, the method for creating a local agent instance corresponding to the first terminal by the second artificial intelligence agent function network element includes:

[0219] Step a: The intelligent agent instance corresponding to the first terminal determines the second sub-intention information based on the information in the instruction diagram.

[0220] Step b: The agent instance corresponding to the first terminal determines the first template information of the local agent instance corresponding to the first terminal based on the second sub-intention information.

[0221] Step c: The intelligent agent instance corresponding to the first terminal sends the first template information, or the identifier of the first template information, to the second artificial intelligence agent function network element. Alternatively, the intelligent agent instance corresponding to the first terminal creates a local intelligent agent instance corresponding to the first terminal based on the first template information, and sends the local intelligent agent instance corresponding to the first terminal to the second artificial intelligence agent function network element.

[0222] Step 3: The agent instance corresponding to the first terminal sends the second rule to the second user plane network element. Correspondingly, the second user plane network element receives the second rule from the agent instance corresponding to the first terminal.

[0223] The second rule includes the address information of the local intelligent agent instance corresponding to the first terminal. The second rule is used to instruct the second user plane network element to send the data requiring multimodal conversion in the first subnet to the second artificial intelligence agent function network element.

[0224] Step 4: The agent instance corresponding to the first terminal sends the address information of the local agent instance corresponding to the first terminal to the first terminal.

[0225] This application provides a communication method, which includes: an intelligent agent instance corresponding to a second terminal sending a sixth request message to a first artificial intelligence agent function network element, the sixth request message being used to instruct the first artificial intelligence agent function network element to deploy a local intelligent agent instance corresponding to the second terminal.

[0226] The sixth request message includes instantiation information for the local agent instance corresponding to the second terminal. This instantiation information is used to create the local agent instance corresponding to the second terminal.

[0227] In one possible embodiment of this application, the method for creating a local agent instance corresponding to the second terminal further includes:

[0228] The agent instance corresponding to the second terminal determines the second template information of the local agent instance corresponding to the second terminal based on the first sub-intention information. The agent instance corresponding to the second terminal sends the second template information, or the identifier of the second template information, to the first artificial intelligence agent function network element. Alternatively, it creates a local agent instance corresponding to the second terminal based on the second template information and sends the local agent instance corresponding to the second terminal to the first artificial intelligence agent function network element.

[0229] In one possible embodiment of this application, the first request message includes the identifier of the first user plane network element, and the method includes: the intelligent agent instance corresponding to the second terminal determines the first artificial intelligence agent function network element based on the first user plane network element.

[0230] As an example, the intelligent agent instance corresponding to the second terminal determines the local intelligent agent instance to be deployed near the first user plane network element based on the identifier of the first user plane network element, and determines the first artificial intelligence agent function network element with the optimal location for the first user plane network element.

[0231] In one possible embodiment of this application, the first request message includes the identifier of the first artificial intelligence agent function network element and the address information of the local intelligent agent instance corresponding to the first terminal. The method includes: the intelligent agent instance corresponding to the second terminal instructs the first artificial intelligence agent function network element to create a local intelligent agent instance corresponding to the second terminal.

[0232] For example, if the first request message includes the identifier of the L-AIAF network element and the address information of L-Agent1, then Agent2 instructs L-AIAF to create L-Agent2.

[0233] In one possible embodiment of this application, the method further includes: the intelligent agent instance corresponding to the second terminal sending the address information of the local intelligent agent instance corresponding to the second terminal to the second terminal.

[0234] For example, Agent2 sends the address information of L-Agent2 to the second terminal.

[0235] This application provides a communication method, the method including:

[0236] Step 1: The first AI agent function network element receives the sixth request message from the intelligent agent instance corresponding to the second terminal.

[0237] For example, the agent instance corresponding to the second terminal sends a sixth request message to the first AI agent function network element. This sixth request message instructs the first AI agent function network element to create a local agent instance corresponding to the second terminal.

[0238] Step 2: The first AI agent function network element creates a local intelligent agent instance corresponding to the second terminal.

[0239] Step 3: The first AI agent function network element receives data from the first subnet that requires multimodal conversion.

[0240] For specific implementation details, please refer to the above embodiments, which will not be repeated here.

[0241] In one possible embodiment of this application, the method includes: a first artificial intelligence agent function network element receiving second template information, or an identifier of the second template information, from a local intelligent agent instance corresponding to a second terminal. The second template information is used to create a local intelligent agent instance corresponding to the second terminal.

[0242] It is understandable that the specific method by which the first AI agent function network element creates the local intelligent agent instance corresponding to the second terminal based on the instantiation information of the local intelligent agent instance corresponding to the second terminal is the same as the method by which the first AI agent function network element creates the local intelligent agent instance corresponding to the first terminal based on the instantiation information of the local intelligent agent instance corresponding to the first terminal, and will not be described again here.

[0243] The following describes the specific implementation of the creation of a virtual subnet between terminals based on an intelligent agent network by the intelligent agent instance corresponding to the first terminal in the embodiments of this application. The intelligent agent instance corresponding to the first terminal is referred to as the first intelligent agent instance, the intelligent agent instance corresponding to the second terminal is referred to as the second intelligent agent instance, and the first artificial intelligence agent function network element is referred to as the local artificial intelligence agent function network element. The specific implementation methods are divided into two scenarios: a "one-to-one" scenario and a "one-to-many" scenario. The implementation methods for each scenario are described below.

[0244] Scenario 1: One-to-one scenario (including first terminal and second terminal)

[0245] As shown in Figure 6, Figure 6(a) is a schematic diagram illustrating a process for two terminals to establish a virtual subnet for "one-to-one" low-latency communication according to an embodiment of this application. The following description uses Terminal 1 as the first terminal and Terminal 2 as the second terminal as an example. The specific method includes:

[0246] Step 601: Terminal 1 registers for intelligent session, and the intelligent agent network instantiates the intelligent agent of Terminal 1, creating the first intelligent agent instance for Terminal 1 in the artificial intelligence agent function network element.

[0247] Step 602: Terminal 2 registers for intelligent session, and the intelligent agent network instantiates the intelligent agent of Terminal 2, creating a second intelligent agent instance for Terminal 2 in the artificial intelligence agent function network element.

[0248] As an example, as shown in Figure 6(b), steps 1 and 2 indicate that terminal 1 creates Agent1 in the AI ​​agent function network element, and terminal 2 creates Agent2 in the AI ​​agent function network element.

[0249] Step 603: Terminal 1 sends an intent to the first intelligent agent instance. Correspondingly, the first intelligent agent instance receives the intent from Terminal 1.

[0250] Step 604: The first intelligent agent instance determines to create a virtual subnet based on the intent of terminal 1.

[0251] As an example, as shown in Figure 6(b), step 3 is for Agent 1 to determine the creation of a virtual subnet based on the intent.

[0252] Step 605: The first intelligent agent instance sends indication information to the first control plane network element. Correspondingly, the first control plane network element receives the indication information from the first intelligent agent instance. The indication information is used to instruct the first network element to determine the first user plane.

[0253] Among them, the first control plane network element is the control plane, and the first user plane is the user plane with the optimal path.

[0254] Step 606: The first control plane network element determines the first user plane according to the instruction information.

[0255] As an example, as shown in Figure 6(b), step 4 is the process by which Agent1 instructs the first control plane element (CP) to determine the first user plane (UP3).

[0256] In one embodiment, the first intelligent agent instance instructs terminal 1 and terminal 2 to establish corresponding user planes on the first user plane. For example, as shown in Figure 6(b), terminal 1 establishes UP1 on UP3, and UP1 is used for data transmission between terminal 1 and AIAF network elements; terminal 2 establishes UP2 on UP3, and UP2 is used for data transmission between terminal 2 and AIAF network elements.

[0257] Step 607: The first intelligent agent instance sends a first instruction message to the second intelligent agent instance. Correspondingly, the second intelligent agent instance receives the first instruction message from the first intelligent agent instance.

[0258] The first instruction information is used to instruct the second intelligent agent instance to create a first local intelligent agent instance on the local artificial intelligence agent function network element.

[0259] Step 608: The second intelligent agent instance creates a first local intelligent agent instance on the local artificial intelligence agent function network element according to the first instruction information.

[0260] As an example, as shown in Figure 6(b), step 5 involves Agent1 instructing Agent2 to create a first local agent instance (L-Agent2) on the L-AIAF network element, and the L-AIAF network element then returns the address information of L-Agent2 to Agent2.

[0261] Step 609: The first intelligent agent instance sends second instruction information to the first control plane network element. Correspondingly, the first control plane network element receives the second instruction information from the first intelligent agent instance.

[0262] The second instruction information is used to instruct the first control plane network element to send intelligent switching rules to the first user plane and to send the data that needs to be intelligently switched to the first local intelligent agent instance.

[0263] Step 610: The first control plane network element sends intelligent switching rules to the first user plane. Correspondingly, the first user plane receives the intelligent switching rules from the first control plane network element.

[0264] As an example, as shown in Figure 6(b), step 6 is Agent1 instructing CP to configure smart switching rules.

[0265] Step 611: The second agent instance sends a third instruction to the first agent instance. Correspondingly, the first agent instance receives the third instruction from the second agent instance.

[0266] The third instruction information is used to instruct the first intelligent agent instance to send the address information of the first local intelligent agent instance to the first terminal.

[0267] Step 612: The first intelligent agent instance sends the address information of the first local intelligent agent instance to terminal 1 according to the third instruction information. Correspondingly, terminal 1 receives the address information of the first local intelligent agent instance from the first intelligent agent instance.

[0268] Step 613: The second intelligent agent instance sends the address information of the first local intelligent agent instance to terminal 2. Correspondingly, terminal 2 receives the address information of the first local intelligent agent instance from the second intelligent agent instance.

[0269] As an example, as shown in Figure 6(b), step 7 is Agent1 sending the address information of L-Agent2 to terminal 1 through UP1, and step 8 is Agent2 sending the address information of L-Agent2 to terminal 2 through UP2.

[0270] Optionally, in the first user plane, the data to be processed includes: data processed by the first local agent instance, i.e., data that needs to be intelligently exchanged (such as multimodal conversion), as shown in step 9 of Figure 6(b); and data that is directly forwarded in groups, i.e., data that does not need to go through the local agent instance and is directly forwarded between terminals, as shown in step 6 of Figure 6(b).

[0271] In one possible embodiment of this application, the local AI agent function network element and the first user plane can be configured together or not. The specific implementation of the two configuration methods is described below.

[0272] In one possible implementation, as shown in Figure 7, which illustrates a specific implementation method for two terminals establishing a virtual subnet for "one-to-one" low-latency communication when the local AI agent function network element and the first user plane are not merged, according to an embodiment of this application, taking UE1 as the first terminal and UE2 as the second terminal, the method includes:

[0273] Step 701: After the first terminal (UE1) performs the smart registration service, the smart agent network creates a first smart agent instance (Agent1) for the first terminal (UE1).

[0274] Agent1 includes the terminal capabilities of UE1 and the capabilities granted to UE1 by the network.

[0275] Step 702: After the second terminal (UE2) performs the smart registration service, the smart agent network creates a second smart agent instance (Agent2) for the second terminal (UE2).

[0276] Agent2 includes the terminal capabilities of UE2 and the capabilities granted to UE2 by the network.

[0277] Step 703: UE1 sends an intent to Agent1. Correspondingly, Agent1 receives the intent from UE1. The intent is used to indicate the task that UE1 needs to perform.

[0278] For example, the intent is to indicate that UE1 performs real-time voice control on UE2.

[0279] Step 704: Agent1 sends a first request message to the first control plane network element (CP). Correspondingly, the first control plane network element (CP) receives the first request message from Agent1. The first request message instructs the CP to establish a virtual subnet for UE1 and UE2.

[0280] The first request message includes, but is not limited to: the identifier of UE1, the identifier of UE2, and the task identifier.

[0281] Step 705: CP determines the first user plane (UP3) based on the first request message.

[0282] Among them, UP3 is the user plane with the optimal path; in other words, UP3 optimizes the route between UE1 and UE2.

[0283] Step 706: CP triggers UE1 to establish a Protocol Data Unit (PDU) session and causes UE1 to establish its corresponding user plane (UP1). CP triggers UE2 to establish a PDU session and causes UE2 to establish its corresponding user plane (UP2).

[0284] Step 707: CP sends a first response message to Agent1. Correspondingly, Agent1 receives the first response message from CP.

[0285] The first response message includes, but is not limited to, the identifier of UP3.

[0286] Step 708: Agent1 determines the local artificial intelligence agent function network element (L-AIAF) based on the first response message. Among them, the L-AIAF is the optimal L-AIAF for UP3.

[0287] Step 709: Agent1 sends an agent instance request message to the ARF network element. Correspondingly, the ARF network element receives the agent instance request message from Agent1. The agent instance request message is used to request an agent instance.

[0288] Step 710: The ARF network element sends the address information of Agent2 to Agent1 based on the agent instance request message. Correspondingly, Agent1 receives the address information of Agent2 from the ARF network element.

[0289] Step 711: Agent1 sends a fourth request message to Agent2. Correspondingly, Agent2 receives the fourth request message from Agent1. The fourth request message instructs the creation of a first local agent instance (L-Agent2).

[0290] The fourth request message includes, but is not limited to, the identifier of UP3 and the task identifier.

[0291] Step 712: Agent2 determines the local artificial intelligence agent function network element (L-AIAF) based on the identifier of UP3.

[0292] Among them, L-AIAF is the optimal L-AIAF position for UP3.

[0293] Step 713: Agent2 sends a fifth request message to L-AIAF. Correspondingly, L-AIAF receives the fifth request message from Agent2. The fifth request message is used to request L-AIAF to instantiate the agent.

[0294] For example, the fifth request message includes, but is not limited to: L-Agent2 instantiation information, task identifier, and subscription events.

[0295] Step 714: L-AIAF creates L-Agent2 based on the fifth request message.

[0296] Step 715: L-AIAF sends L-Agent2's address information to Agent2. Correspondingly, Agent2 receives L-Agent2's address information from L-AIAF.

[0297] Step 716: Agent2 sends a second response message to Agent1. Correspondingly, Agent1 receives the second response message from Agent2. The second response message instructs Agent1 to send the address information of L-Agent2 to UE1.

[0298] The second response message includes the address information of L-Agent2.

[0299] Step 717: Agent1 sends the address information of L-Agent2 to UE1. Correspondingly, UE1 receives the address information of L-Agent2 from Agent1.

[0300] Step 718: Agent2 sends the address information of L-Agent2 to UE2. Correspondingly, UE2 receives the address information of L-Agent2 from Agent2.

[0301] Step 719: Agent1 sends a second request message to CP. Correspondingly, CP receives the second request message from Agent1. The second request message includes second information, which instructs CP to send intelligent switching rules to UP3. The intelligent switching rules instruct L-Agent2 to perform data exchange between UE1 and UE2 within the virtual subnet.

[0302] The intelligent switching rules include, but are not limited to: UE1's address information, UE2's address information, L-Agent2's address information, and QoS information. The QoS information includes a first QoS rule and a second QoS rule. The first QoS rule is used to instruct UE1 to send uplink data through the QoS flow, and the second QoS rule is used to instruct UE2 to send uplink data through the QoS flow.

[0303] Step 720: The CP sends the first QoS rule to UE1. Correspondingly, UE1 receives the first QoS rule from the CP.

[0304] Step 721: CP sends the second QoS rule to UE2. Correspondingly, UE2 receives the second QoS rule from CP.

[0305] Step 722: CP sends the smart switching rules to UP3. Correspondingly, UP3 receives the smart switching rules from CP.

[0306] As an example, the smart switching rule instructs UP3 to forward data destined for L-Agent2 to L-Agent2, and to forward data destined for UE1 or UE2 within UP3.

[0307] For example, UP3 sends data to L-Agent2 with L-Agent2 as the destination address. Correspondingly, L-Agent2 receives data from UP3 with L-Agent2 as the destination address.

[0308] For example, after L-Agent2 converts the data into underlying data for UE2 to perform actions, it sends the underlying data to UP3. UP3 then sends the underlying data with the destination address of UE2 to UE2 according to the smart switching rules. Correspondingly, UE2 receives the underlying data from UP3 with the destination address of UE2.

[0309] In another possible implementation, as shown in Figure 8, which illustrates a specific implementation method for two terminals establishing a virtual subnet for "one-to-one" low-latency communication when the local AI agent function network element and the first user plane are combined, according to an embodiment of this application, the method includes:

[0310] Steps 801 to 810 are the same as steps 701 to 711 in the above embodiments, and will not be repeated here. The difference is that when the local artificial intelligence agent function network element and the first user plane are combined, Agent1 does not need to determine L-AIAF.

[0311] Step 811: Agent2 sends a sixth request message to CP. Correspondingly, CP receives the sixth request message from Agent2. The sixth request message is used to request the creation of L-Agent2.

[0312] For example, the sixth request message includes, but is not limited to: the identifier of UP3 and the task identifier.

[0313] Step 812: CP sends a seventh request message to UP3. Correspondingly, UP3 receives the seventh request message from CP. The seventh request message requests the creation of L-Agent2 in the L-AIAF integrated on UP3.

[0314] For example, the seventh request message includes, but is not limited to: L-Agent2 instantiation information, task identifier, and subscription event.

[0315] Step 813: UP3 creates L-Agent2 based on L-AIAF according to the seventh request message.

[0316] Step 814: UP3 sends the address information of L-Agent2 to CP. Correspondingly, CP receives the address information of L-Agent2 from UP3.

[0317] Step 815: CP sends the address information of L-Agent2 to Agent2. Correspondingly, Agent2 receives the address information of L-Agent2 from CP.

[0318] Step 816: Agent2 sends a third response message to Agent1. Correspondingly, Agent1 receives the third response message from Agent2.

[0319] The third response message includes, but is not limited to, the address information of L-Agent2.

[0320] Step 817: Agent1 sends the address information of L-Agent2 to UE1. Correspondingly, UE1 receives the address information of L-Agent2 from Agent1.

[0321] Step 818: Agent2 sends the address information of L-Agent2 to UE2. Correspondingly, UE2 receives the address information of L-Agent2 from Agent2.

[0322] Steps 819 to 822 are the same as steps 718 to 721 in the above embodiments, and will not be repeated here.

[0323] In step 706 or 806 above, after the CP triggers UE1 and UE2 to establish a Protocol Data Unit session, the corresponding user planes (UP1 and UP2) are established on the same first user plane (UP3). Optionally, in this embodiment, the user planes corresponding to the terminals can also be established on different first user planes.

[0324] As an example, referring to Figure 9, in step 705 of the above embodiment, the CP can determine two first user planes UP3 and UP4 according to the first request message, then UE1 establishes UP1 on UP3 and UE2 establishes UP2 on UP4.

[0325] Scenario 2: One-to-many scenarios (including the first terminal, the second terminal, and the third terminal)

[0326] As shown in Figure 10, Figure 10 is a schematic diagram of a process for at least three terminals to establish a virtual subnet for "one to many" low-latency communication according to an embodiment of this application. The following description uses Terminal 1 as the first terminal, Terminal 2 as the second terminal, and Terminal 3 as the third terminal as an example. The method includes:

[0327] Steps 1001 to 1003 involve creating agent instances for the terminal, which will not be described in detail here.

[0328] As an example, as shown in Figure 10(b), steps 1, 2, and 3 represent that terminal 1 creates Agent1 in the AI ​​agent function network element, terminal 2 creates Agent2 in the AI ​​agent function network element, and terminal 3 creates Agent3 in the AI ​​agent function network element.

[0329] It is understood that the order of steps 1001 to 1003 is not limited, and agent instances can be created simultaneously or separately.

[0330] Steps 1004 to 1007 are the same as steps 603 to 606 in the above embodiments, and will not be repeated here.

[0331] The difference in the specific implementation is that: terminal 3 and terminal 2 establish UP2 on CP, and UP2 is used for data transmission between terminal 2 and terminal 3 and AIAF network elements.

[0332] Step 1008: The first intelligent agent instance sends a request message to the local AI agent function network element. Correspondingly, the local AI agent function network element receives the request message from the first intelligent agent instance. The request message requests the creation of a second local intelligent agent instance on the local AI agent function network element.

[0333] Step 1009: The local AI agent function network element creates a second local intelligent agent instance.

[0334] As an example, as shown in Figure 10(b), step 6 is Agent1 requesting the creation of a local second agent instance L-Agent1 in the L-AIAF network element.

[0335] Step 1010: The local AI agent function network element sends a response message to the first intelligent agent instance. Correspondingly, the first intelligent agent instance receives the response message from the local AI agent function network element. The response message is used to indicate information about the second local intelligent agent instance.

[0336] For example, the response message may include, but is not limited to, the address information of the second local agent instance and the capability information of the second local agent instance.

[0337] Step 1011: The first intelligent agent instance sends first instruction information to the second intelligent agent instance corresponding to terminal 2. Correspondingly, the second intelligent agent instance corresponding to terminal 2 receives the first instruction information from the first intelligent agent instance.

[0338] The first instruction information is used to instruct the second intelligent agent instance corresponding to terminal 2 to create the first local intelligent agent instance corresponding to terminal 2 on the local artificial intelligence agent function network element.

[0339] Step 1012: The first intelligent agent instance sends first instruction information to the second intelligent agent instance corresponding to terminal 3. Correspondingly, the second intelligent agent instance corresponding to terminal 3 receives the first instruction information from the first intelligent agent instance.

[0340] The first instruction information is used to instruct the second intelligent agent instance corresponding to terminal 3 to create the first local intelligent agent instance corresponding to terminal 3 on the local artificial intelligence agent function network element.

[0341] In this embodiment, the second local agent instance is used for group management. For example, it manages the first local agent instances corresponding to terminal 2 and terminal 3, respectively.

[0342] For example, as shown in Figure 10(b), L-Agent1 is used to manage the data of L-Agent2 and L-Agent3. L-Agent1 determines whether the data is sent to L-Agent2 or L-Agent3.

[0343] Step 1013: The second intelligent agent instance corresponding to terminal 2 and the second intelligent agent instance corresponding to terminal 3 respectively create a first local intelligent agent instance on the local artificial intelligence agent function network element according to the first instruction information.

[0344] As an example, as shown in Figure 10(b), step 7 is Agent1 instructing Agent2 to create a first local agent instance (L-Agent2) on the L-AIAF network element; step 8 is Agent1 instructing Agent3 to create a first local agent instance (L-Agent3) on the L-AIAF network element.

[0345] Steps 1014 and 1015 are the same as steps 609 and 610 in the above embodiments, and will not be repeated here.

[0346] Step 1016: The first intelligent agent instance sends the address information of the second local intelligent agent instance to terminal 1. Correspondingly, terminal 1 receives the address information of the second local intelligent agent instance from the first intelligent agent instance.

[0347] For example, as shown in Figure 10(b), step 10 is Agent1 sending the address information of L-Agent1 to terminal 1.

[0348] Step 1017: The second intelligent agent instance corresponding to terminal 2 sends the address information of the corresponding first local intelligent agent instance to terminal 2. Correspondingly, terminal 2 receives the address information of the corresponding first local intelligent agent instance from the second intelligent agent instance corresponding to terminal 2.

[0349] For example, as shown in Figure 14(b), step 11 is Agent2 sending the address information of L-Agent2 to terminal 2.

[0350] Step 1018: The second intelligent agent instance corresponding to terminal 3 sends the address information of the corresponding first local intelligent agent instance to terminal 3. Correspondingly, terminal 3 receives the address information of the corresponding first local intelligent agent instance from the second intelligent agent instance corresponding to terminal 3.

[0351] For example, as shown in Figure 10(b), step 12 is Agent3 sending the address information of L-Agent3 to terminal 3.

[0352] Optionally, as shown in Figure 10(b), step 13 involves data that needs to be intelligently exchanged, which is then intelligently exchanged between the first local agent instance and the second local agent instance; step 14 involves data that is directly forwarded between terminals.

[0353] In one possible embodiment of this application, the local AI agent function network element and the first user plane can be configured together or not. The specific implementation of the two configuration methods is described below.

[0354] In one possible implementation, as shown in Figure 11, Figure 11 is a schematic diagram of a specific implementation method for establishing a virtual subnet for "one to many" low-latency communication by at least three terminals, provided in this application embodiment, when the local artificial intelligence agent function network element and the first user plane are not merged. Taking UE1 as the first terminal and UE2 and UE3 as the second terminals as examples, the method includes:

[0355] Step 1101: After UE1 performs the smart registration service, the smart agent network creates the first smart agent instance (Agent1) for UE1.

[0356] Agent1 includes the terminal capabilities of UE1 and the capabilities granted to UE1 by the network.

[0357] Step 1102: After UE2 performs the smart registration service, the smart agent network creates a corresponding second smart agent instance (Agent2) for UE2.

[0358] Agent2 includes the terminal capabilities of UE2 and the capabilities granted to UE2 by the network.

[0359] Step 1103: After UE3 performs the intelligent registration service, the intelligent agent network creates a corresponding second intelligent agent instance (Agent3) for UE3.

[0360] Agent3 includes the terminal capabilities of UE3 and the capabilities that the network grants to UE3.

[0361] Steps 1104 to 1109 are the same as steps 703 to 708 in the above embodiments, and will not be repeated here.

[0362] Step 1110: Agent1 sends an agent instance request message to the ARF network element. Correspondingly, the ARF network element receives the agent instance request message from Agent1. The agent instance request message is used to request an agent instance.

[0363] Step 1111: Based on the agent instance request message, the ARF network element sends the address information of Agent2 and Agent3 to Agent1. Correspondingly, Agent1 receives the address information of Agent2 and Agent3 from the ARF network element.

[0364] Step 1112: Agent1 sends the eighth request message to L-AIAF. Correspondingly, L-AIAF receives the eighth request message from Agent1. The eighth request message is used to request L-AIAF to instantiate the agent.

[0365] For example, the eighth request message includes, but is not limited to, L-Agent1 instantiation information, task identifier, and subscription events.

[0366] Step 1113: L-AIAF creates a second local agent instance (L-Agent1) based on the eighth request message.

[0367] L-Agent1 is used for group management.

[0368] Step 1114: L-AIAF sends the address information of L-Agent1 to Agent1. Correspondingly, Agent1 receives the address information of L-Agent1 from L-AIAF.

[0369] Step 1115: Agent1 sends the intent for subtask 2 to Agent2. Correspondingly, Agent2 receives the intent for subtask 2 from Agent1. The intent for subtask 2 is used to instruct the creation of the first local agent instance.

[0370] The messages include, but are not limited to: the L-AIAF identifier, the task identifier, the address information of L-Agent1, and the capability information of L-Agent1.

[0371] Step 1116: Agent2 sends a ninth request message to L-AIAF. Correspondingly, L-AIAF receives the ninth request message from Agent2. The ninth request message is used to request L-AIAF to instantiate the agent.

[0372] For example, the ninth request message includes, but is not limited to: L-Agent2 instantiation information, task identifier, subscription event, L-Agent1 address information, and L-Agent1 capability information.

[0373] Step 1117: L-AIAF creates L-Agent2 based on the ninth request message.

[0374] For example, L-Agent2 can be used to control UE2 via voice in a virtual subnet.

[0375] Step 1118: L-AIAF sends L-Agent2's address information and L-Agent2's capability information to Agent2. Correspondingly, Agent2 receives L-Agent2's address information and L-Agent2's capability information from L-AIAF.

[0376] Step 1119: Agent2 sends a fourth response message to Agent1. Correspondingly, Agent1 receives the fourth response message from Agent2.

[0377] The fourth response message includes L-Agent2's address information and L-Agent2's capability information.

[0378] Steps 1120 to 1124 are similar to steps 1111 to 1119 above. The difference is that steps 1111 to 1119 are the process of Agent2 creating L-Agent2, while steps 1120 to 1124 are the process of Agent3 creating L-Agent3.

[0379] Step 1125: Agent1 sends the address information of L-Agent1 to UE1. Correspondingly, UE1 receives the address information of L-Agent1 from Agent1.

[0380] Step 1126: Agent2 sends the address information of L-Agent2 to UE2. Correspondingly, UE2 receives the address information of L-Agent2 from Agent2.

[0381] Step 1127: Agent3 sends the address information of L-Agent3 to UE3. Correspondingly, UE3 receives the address information of L-Agent3 from Agent3.

[0382] Step 1128: Agent1 sends a notification message to L-AIAF. Correspondingly, L-AIAF receives the notification message from Agent1.

[0383] The notification messages include, but are not limited to: L-Agent2's address information, L-Agent2's capability information, L-Agent3's address information, and L-Agent3's capability information.

[0384] Step 1129: Agent1 sends a second request message to CP. Correspondingly, CP receives the second request message from Agent1. The second request message includes second information, which instructs CP to send intelligent switching rules to UP3. The intelligent switching rules instruct L-Agent2 and L-Agent3 to perform data exchange between UE1, UE2, and UE3 within the virtual subnet.

[0385] The intelligent switching rules include, but are not limited to: address information of UE1, address information of L-Agent1, address information of UE2, address information of L-Agent2, address information of UE3, address information of L-Agent3, QoS information, and task identifier. The QoS information includes a first QoS rule, a second QoS rule, and a third QoS rule. The first QoS rule instructs UE1 to send uplink data through the QoS flow, the second QoS rule instructs UE2 to send uplink data through the QoS flow, and the third QoS rule instructs UE3 to send uplink data through the QoS flow.

[0386] Step 1130: The CP sends the first QoS rule to UE1. Correspondingly, UE1 receives the first QoS rule from the CP.

[0387] Step 1131: CP sends the second QoS rule to UE2. Correspondingly, UE2 receives the second QoS rule from CP.

[0388] Step 1132: CP sends the third QoS rule to UE3. Correspondingly, UE3 receives the third QoS rule from CP.

[0389] Step 1133: CP sends the smart switching rules to UP3. Correspondingly, UP3 receives the smart switching rules from CP.

[0390] As an example, the smart switching rule instructs UP3 to forward data destined for L-Agent1 to L-Agent1 first, while UP3 performs internal forwarding for data destined for UE2 or UE3.

[0391] For example, UE1 sends voice data to L-Agent1. L-Agent1 understands the intent based on the voice data and sends the voice data to L-Agent2 and L-Agent3 accordingly. L-Agent2 and L-Agent3, based on the intent, convert the voice data into underlying data for UE2 and UE3 before sending it to UP3. UP3 sends the underlying data with the destination address of UE2 to UE2 and the underlying data with the destination address of UE3 to UE3.

[0392] Optionally, L-Agent1 can process the information fed back by L-Agent2 and L-Agent3 locally, or notify UE1.

[0393] In another possible implementation, as shown in Figure 12, Figure 12 is a schematic diagram of a specific implementation method for establishing a virtual subnet for "one to many" low-latency communication by at least three terminals, provided in this application embodiment, when the local artificial intelligence agent function network element and the first user plane are combined. The method includes:

[0394] Steps 1201 to 1210 are similar to steps 1101 to 1111 in the above embodiments, except that the local artificial intelligence agent function network element and the first user plane are set together, and it is not necessary to determine L-AIAF. This will not be described in detail here.

[0395] Step 1211: Agent1 sends an eighth request message to CP, and CP then sends an eighth request message to UP3. Correspondingly, CP receives the eighth request message from Agent1, and UP3 receives the eighth request message from CP. The eighth request message is used to request L-AIAF in UP3 to instantiate the agent.

[0396] For example, the eighth request message includes, but is not limited to, L-Agent1 instantiation information, task identifier, and subscription events.

[0397] In step 1212, UP3, L-AIAF creates a second local agent instance (L-Agent1) based on the eighth request message.

[0398] Step 1213: L-AIAF sends the address information of L-Agent1 to CP, and CP then sends the address information of L-Agent1 to Agent1. Correspondingly, CP receives the address information of L-Agent1 from L-AIAF, and Agent1 then receives the address information of L-Agent1 from CP.

[0399] Step 1214: Agent1 sends the intent for subtask 2 to Agent2. Correspondingly, Agent2 receives the intent for subtask 2 from Agent1. The intent for subtask 2 is used to instruct the creation of the first local agent instance.

[0400] The messages include, but are not limited to: the L-AIAF identifier, the task identifier, the address information of L-Agent1, and the capability information of L-Agent1.

[0401] Step 1215: Agent2 sends a ninth request message to CP, and CP then sends a ninth request message to UP3. Correspondingly, CP receives the ninth request message from Agent2, and UP3 receives the ninth request message from CP. The ninth request message is used to request L-AIAF to instantiate the agent.

[0402] For example, the ninth request message includes, but is not limited to: L-Agent2 instantiation information, task identifier, subscription event, L-Agent1 address information, and L-Agent1 capability information.

[0403] In step 1216, L-AIAF in UP3 creates L-Agent2 based on the ninth request message.

[0404] Step 1217: UP3 sends the address information and capability information of L-Agent2 to CP, and CP then sends the address information and capability information of L-Agent2 to Agent2. Correspondingly, CP receives the address information and capability information of L-Agent2 from UP3, and Agent2 then receives the address information and capability information of L-Agent2 from CP.

[0405] Step 1218: Agent2 sends a fourth response message to Agent1. Correspondingly, Agent1 receives the fourth response message from Agent2. This fourth response message includes the address information and capability information of L-Agent2.

[0406] Steps 1219 to 1223 are similar to steps 1214 to 1218 above. The difference is that steps 1214 to 1218 are the process of Agent2 creating L-Agent2, while steps 1219 to 1223 are the process of Agent3 creating L-Agent3.

[0407] Steps 1224 to 1232 are the same as steps 1025 to 1033 in the above embodiments, and will not be repeated here.

[0408] In step 1106 or step 1206 above, after the CP triggers UE1, UE2, and UE3 to establish a protocol data unit session, the corresponding user planes (UP1 and UP2) are established on the same first user plane (UP3). Optionally, in this embodiment, the user planes corresponding to the terminals can also be established on different first user planes.

[0409] As an example, referring to Figure 13, in step 1505 of the above embodiment, the CP can determine two first user planes UP3 and UP4 according to the first request message. Then, UE1 establishes UP1 on UP3, and UE2 and UE3 establish UP2 on UP4.

[0410] Optionally, after creating a local agent instance, the local agent instance and the agent instance synchronize information. The method provided in this embodiment is shown in Figure 14, which is a flowchart illustrating the information synchronization between a local agent instance and an agent instance according to an embodiment of this application, specifically including:

[0411] Step 1401: The agent instance sends an instruction message to the local agent instance. Correspondingly, the local agent instance receives the instruction message from the agent instance. The instruction message is used by the local agent instance to trigger information synchronization.

[0412] Step 1402: The local agent instance triggers an event based on the instruction information. Event triggering is used to monitor events.

[0413] Event triggering includes, but is not limited to: periodic reporting and abnormal event reporting.

[0414] Step 1403: The local agent instance sends events and related events to the agent instance. Correspondingly, the agent instance receives events and related events from the local agent instance.

[0415] For example, a local agent instance sends a processing command to another agent instance; or there may be an abnormal situation on the terminal.

[0416] Step 1404: The agent instance processes the event and related events.

[0417] For example, when the event and related events are operation commands to be processed, the agent instance records the operation commands processed by the local agent instance.

[0418] For example, in cases where the event and related events are abnormal for the terminal, the agent instance will isolate the terminal that is experiencing the abnormality from the network.

[0419] Step 1405: The agent instance sends a response message to the local agent instance. Correspondingly, the local agent instance receives the response message from the agent instance. The response message instructs the agent instance to handle the event.

[0420] The above mainly describes the solutions of the embodiments of this application from the perspective of interaction between various network elements. It is understood that each network element, such as a terminal or network device, includes corresponding structures and / or software modules to perform the above functions in order to achieve them. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0421] This application embodiment can divide functional units according to the terminal device and network device described above. For example, each function can be divided into separate functional units, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0422] The method of the embodiments of this application has been described above with reference to Figures 5 to 14. The communication apparatus for executing the above method provided in the embodiments of this application is described below. Those skilled in the art will understand that the methods and apparatus can be combined with and referenced in each other, and the communication apparatus provided in the embodiments of this application can execute the steps performed by the artificial intelligence agent function network element in the above analysis method.

[0423] When using an integrated unit, FIG15 shows the communication device involved in the above embodiment, which may include a communication module 1501 and a processing module 1502.

[0424] In an alternative implementation, the communication device 150 may further include a storage module 1503 for storing the program code and data of the communication device.

[0425] The communication device 150 is an AI agent function network element, or a chip applied in an AI agent function network element. In this case, the communication module 1501 is used to support communication between the communication device and external network elements (e.g., an agent registration function network element). For example, the communication module 1501 is used to perform signal transmission and reception operations of the agent instance corresponding to the first terminal in the above method embodiment. The processing module 1502 is used to perform signal processing operations of the agent instance corresponding to the first terminal in the above method embodiment.

[0426] In one possible embodiment, the communication module 1501 is used to perform the receiving action executed by the intelligent agent instance corresponding to the first terminal in step 901 of FIG9 of the above embodiment. The communication module 1501 is also used to perform the sending actions executed by the intelligent agent instance corresponding to the first terminal in steps 902, 903, and 904 of FIG9 of the above embodiment.

[0427] In one possible embodiment, the processing module 1502 is used to execute the processing action performed by the intelligent agent instance corresponding to the first terminal in step 902 of FIG9 of the above embodiment.

[0428] The processing module 1502 can be a processor or controller, such as a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, etc. The communication module can be a transceiver, transceiver circuitry, or communication interface, etc. The storage module can be a memory.

[0429] When the processing module 1502 is a processor 1601 or a processor 1605, the communication module 1501 is a transceiver 1603, and the storage module 1503 is a memory 1602, the communication device involved in this application can be the communication device shown in FIG16.

[0430] Figure 16 shows a schematic diagram of the hardware structure of a communication device provided in an embodiment of this application. The hardware structure of the terminal device and network device in this embodiment can be referred to the structure shown in Figure 16. The communication device includes a processor 1601, a communication line 1604, and at least one transceiver (Figure 16 is only an example illustrating the inclusion of transceiver 1603).

[0431] The processor 1601 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application.

[0432] Communication line 1604 may include a path for transmitting information between the aforementioned components.

[0433] Transceiver 1603 is a device that uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0434] Optionally, the communication device may also include a memory 1602.

[0435] Memory 1602 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 1602 may exist independently and be connected to processor 1601 via communication line 1604. Memory 1602 may also be integrated with processor 1601.

[0436] The memory 1602 stores computer execution instructions for implementing the scheme of this application, and its execution is controlled by the processor 1601. The processor 1601 executes the computer execution instructions stored in the memory 1602, thereby implementing the communication method provided in the following embodiments of this application.

[0437] Optionally, the computer execution instructions in the embodiments of this application may also be referred to as application code, and the embodiments of this application do not specifically limit this.

[0438] In a specific implementation, as one example, processor 1601 may include one or more CPUs, such as CPU0 and CPU1 in FIG16.

[0439] In a specific implementation, as one example, the communication device may include multiple processors, such as processor 1601 and processor 1602 in Figure 16. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, "processor" may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0440] This application also provides a communication device, including a radio resource control (RRC) signaling interaction module, a medium access control (MAC) signaling interaction module, and a physical layer (PHY) signaling and data interaction module. The RRC signaling interaction module is used to send and receive RRC signaling, the MAC signaling interaction module is used to send and receive MAC-CE signaling, and the PHY signaling and data interaction module is used to send and receive uplink / downlink control signaling and uplink / downlink data.

[0441] Figure 17 is a schematic diagram of the structure of chip 170 provided in an embodiment of this application. Chip 170 includes one or more (including two) processors 1710 and communication interfaces 1730.

[0442] Optionally, the chip 170 also includes a memory 1740, which may include read-only memory and random access memory, and provides operation instructions and data to the processor 1710. A portion of the memory 1740 may also include non-volatile random access memory (NVRAM).

[0443] In some implementations, memory 1740 stores elements such as execution modules or data structures, or subsets thereof, or extended sets thereof.

[0444] In this embodiment of the application, the corresponding operation is executed by calling the operation instructions stored in the memory 1740 (the operation instructions can be stored in the operating system).

[0445] The processor 1710 controls the processing operations of any one of the intelligent agent instances corresponding to the first terminal and the intelligent agent instances corresponding to the second terminal. The processor 1710 can also be called a central processing unit (CPU).

[0446] Memory 1740 may include read-only memory and random access memory, and provides instructions and data to processor 1710. A portion of memory 1740 may also include NVRAM. For example, in an application, memory 1740, communication interface 1730, and memory 1740 are coupled together via bus system 1720, which may include, in addition to data buses, power buses, control buses, and status signal buses, etc. However, for clarity, all buses are labeled as bus system 1720 in Figure 17.

[0447] The methods disclosed in the embodiments of this application can be applied to or implemented by the processor 1710. The processor 1710 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 1710 or by instructions in the form of software. The processor 1710 may be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 1740. Processor 1710 reads the information in memory 1740 and, in conjunction with its hardware, completes the steps of the above method.

[0448] In one possible implementation, the communication interface 1730 is used to execute the steps of receiving and sending data to the agent instance corresponding to the first terminal in the embodiment shown in FIG. 5. The processor 1710 is used to execute the steps of processing the agent instance corresponding to the first terminal in the embodiment shown in FIG. 5.

[0449] Alternatively, the communication interface 1730 is used to execute the steps of receiving and sending data to the intelligent agent instance corresponding to the second terminal in the embodiment shown in FIG. 5. The processor 1710 is used to execute the steps of processing the intelligent agent instance corresponding to the second terminal in the embodiment shown in FIG. 5.

[0450] In one possible implementation, the communication interface 1730 is used to execute the steps of receiving and sending data to the intelligent agent instance corresponding to the first terminal in the embodiments shown in Figures 6-14. The processor 1710 is used to execute the steps of processing the intelligent agent instance corresponding to the first terminal in the embodiments shown in Figures 6-14.

[0451] Alternatively, the communication interface 1730 is used to execute the steps of receiving and sending data to the intelligent agent instance corresponding to the second terminal in the embodiments shown in Figures 6-14. The processor 1710 is used to execute the steps of processing the intelligent agent instance corresponding to the second terminal in the embodiments shown in Figures 6-14.

[0452] The communication module described above can be a communication interface of the device, used to receive signals from other devices. For example, when the device is implemented as a chip, the communication module is the communication interface used by the chip to receive or send signals from other chips or devices.

[0453] On the one hand, a computer-readable storage medium is provided, which stores instructions that, when executed, implement the functions performed by the intelligent agent instance corresponding to the first terminal as shown in Figures 5 to 14.

[0454] On the one hand, a computer program product including instructions is provided. When the instructions are executed, they realize the functions performed by the intelligent agent instance corresponding to the second terminal as shown in Figures 5 to 14.

[0455] On the one hand, a chip is provided that is used in a terminal device. The chip includes at least one processor and a communication interface. The communication interface and at least one processor are coupled together. The processor is used to run instructions to implement the functions executed by the intelligent agent instance corresponding to the first terminal as shown in Figures 5 to 14.

[0456] On the one hand, a chip is provided that is used in a terminal device. The chip includes at least one processor and a communication interface. The communication interface and at least one processor are coupled together. The processor is used to run instructions to implement the functions executed by the intelligent agent instance corresponding to the first terminal as shown in Figures 5 to 14.

[0457] This application provides a communication system comprising: a first terminal, a second terminal, a first artificial intelligence agent function network element, and an intelligent agent registration function network element. The intelligent agent instance corresponding to the first terminal is used to implement the functions executed by the intelligent agent instance corresponding to the first terminal as shown in Figures 5-14. The intelligent agent instance corresponding to the second terminal is used to implement the functions executed by the intelligent agent instance corresponding to the second terminal as shown in Figures 5-14.

[0458] The first AI agent function network element is used to create a local intelligent agent instance corresponding to the first terminal and a local intelligent agent instance corresponding to the second terminal.

[0459] The agent registration function network element is used to store and register agent instances. The first terminal is used to send the user's task requirements. The second and third terminals are used to execute the user's tasks.

[0460] The explanations and beneficial effects of the relevant content in any of the communication devices provided above can be found in the corresponding method embodiments provided above, and will not be repeated here.

[0461] Furthermore, various aspects or features of this application can be implemented as methods, apparatus, or articles of manufacture using standard programming and / or engineering techniques. The term "article of manufacture" as used herein encompasses a computer program accessible from any computer-readable device, carrier, or medium. For example, computer-readable media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes), optical discs (e.g., compact discs (CDs), digital versatile discs (DVDs), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROMs), cards, sticks, or key drives, etc.). Additionally, the various storage media described herein may represent one or more devices and / or other machine-readable media for storing information. The term "machine-readable medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0462] It should be understood that the processor mentioned in the embodiments of this application can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0463] It should also be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0464] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) is integrated into the processor.

[0465] It should be noted that the memories described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0466] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0467] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0468] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0469] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0470] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0471] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0472] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

A communication method characterized by comprising: The method comprises: determining to establish a first subnet; determining a first user plane network element, the first user plane network element being used for the first terminal and the second terminal to establish the first subnet; sending a first request message to an intelligent agent instance corresponding to the second terminal, the first request message being used for the intelligent agent instance corresponding to the second terminal to decide to create a local intelligent agent instance corresponding to the second terminal on a first artificial intelligence agent function network element; sending a first rule to the first user plane network element, the first rule being used to instruct the first user plane network element to send data requiring multi-modal conversion in the first subnet to the first artificial intelligence agent function network element. The method of claim 1, wherein The method comprises: obtaining address information of the local intelligent agent instance corresponding to the second terminal from the intelligent agent instance corresponding to the second terminal; determining the first rule according to the address information of the local intelligent agent instance corresponding to the second terminal; sending the address information of the local intelligent agent instance corresponding to the second terminal to the first terminal. The method of claim 1, wherein The method comprises: determining the first artificial intelligence agent function network element; instructing the first artificial intelligence agent function network element to create a local intelligent agent instance corresponding to the first terminal; determining the first rule according to the address information of the local intelligent agent instance corresponding to the first terminal; sending the address information of the local intelligent agent instance corresponding to the first terminal to the first terminal. The method according to claim 3, characterized in that The first request message comprises: an identifier of the first artificial intelligence agent function network element and address information of the local intelligent agent instance corresponding to the first terminal. The method according to claim 1 or 2, characterized in that The determination of the first user plane network element comprises: sending a second request message to a first control plane network element, the second request message being used to request the first control plane network element to determine the first user plane network element; receiving an identifier of the first user plane network element from the first control plane network element. The method according to claim 1 or 3, characterized in that The method comprises: sending a second request message to a first control plane network element, the second request message being used to request the first control plane network element to determine the first artificial intelligence agent function network element, and being used to request the first artificial intelligence agent function network element to create a local intelligent agent instance corresponding to the first terminal. The method according to claim 5 or 6, characterized in that The method comprises: sending a third request message to the first control plane network element, the third request message being used to request the first control plane network element to send the first rule to the first user plane network element. The method according to claim 1, characterized in that The method further comprises: determining a second user plane network element, the second user plane network element being used for the first terminal and the second terminal to establish the first subnet. The method of claim 8, wherein The method further comprises: determining the second artificial intelligence agent function network element; creating a local intelligent agent instance corresponding to the first terminal on the second artificial intelligence agent function network element; sending the second rule to the second user plane network element, the second rule comprising address information of the local intelligent agent instance corresponding to the first terminal, the second rule being used to instruct the second user plane network element to send data requiring multi-modal conversion in the first subnet to the second artificial intelligence agent function network element; sending the address information of the local intelligent agent instance corresponding to the first terminal to the first terminal. The method according to any one of claims 1 to 9, characterized in that The determining establishing the first sub-network comprises: receiving a first message from the first terminal, the first message comprising information indicating an intent; determining, according to the information indicating the intent, to establish the first sub-network. The method of claim 10, wherein The method comprises: determining, according to the information indicating the intent, first sub-intent information; determining, according to the first sub-intent information, capabilities of an agent instance required to achieve the intent; sending a fourth request message to an agent registration function network element, the fourth request message being used to request an agent instance satisfying the capabilities of the agent instance; receiving address information of at least one agent instance returned from the agent registration function network element, the at least one agent instance comprising an agent instance corresponding to the second terminal. The method of claim 10, wherein The first message comprises an identifier of the second terminal, and the method comprises: determining, according to the information indicating the intent, first sub-intent information; sending a fifth request message to an agent registration function network element, the fifth request message being used to request address information of an agent instance corresponding to the second terminal; receiving the address information of the agent instance corresponding to the second terminal from the agent registration function network element. The method according to any one of claims 10 to 12, characterized in that The first request message comprises first sub-intent information. The method according to any one of claims 9 to 13, characterized in that The method further comprises: determining, according to the information indicating the intent, second sub-intent information; determining, according to the second sub-intent information, first template information of a local agent instance corresponding to the first terminal; sending the first template information, or an identifier of the first template information, to the first artificial intelligence agent function network element; or creating the local agent instance corresponding to the first terminal according to the first template information, and sending the local agent instance corresponding to the first terminal to the first artificial intelligence agent function network element. The method of claim 14, wherein The method further comprises: sending the first template information, or an identifier of the first template information, to the second artificial intelligence agent function network element; or creating the local agent instance corresponding to the first terminal according to the first template information, and sending the local agent instance corresponding to the first terminal to the second artificial intelligence agent function network element. A communication method characterized by comprising: The method comprises: receiving a first request message from an agent instance corresponding to the first terminal, the first request message comprising first sub-intent information; determining, according to the first sub-intent information, to create a local agent instance corresponding to the second terminal on a first artificial intelligence agent function network element; sending a sixth request message to the first artificial intelligence agent function network element, the sixth request message being used to instruct the first artificial intelligence agent function network element to deploy the local agent instance corresponding to the second terminal. The method of claim 16, wherein The sixth request message comprises instantiation information of the local agent instance corresponding to the second terminal, the instantiation information of the local agent instance corresponding to the second terminal being used to create the local agent instance corresponding to the second terminal. The method of claim 17, wherein The first request message comprises an identifier of a first user plane network element, and the method comprises: determining the first artificial intelligence agent function network element according to the first user plane network element. The method of claim 17, wherein The first request message includes an identifier of the first artificial intelligence agent function network element and address information of a local agent instance corresponding to the first terminal, and the method comprises: indicating to create a local agent instance corresponding to the second terminal on the first artificial intelligence agent function network element. The method according to any one of claims 16 to 19, characterized in that The method further comprises: sending, to the second terminal, address information of the local agent instance corresponding to the second terminal. The method according to any one of claims 16 to 20, characterized in that The method further comprises: determining second template information of the local agent instance corresponding to the second terminal according to the first sub-intention information; sending, to the first artificial intelligence agent function network element, the second template information or an identifier of the second template information; or creating the local agent instance corresponding to the second terminal according to the second template information and sending, to the first artificial intelligence agent function network element, the local agent instance corresponding to the second terminal. A communication method characterized by comprising: The method comprises: receiving a sixth request message from an agent instance corresponding to the second terminal, the sixth request message being used to indicate to create a local agent instance corresponding to the second terminal on the first artificial intelligence agent function network element; creating the local agent instance corresponding to the second terminal; receiving data requiring multi-modal conversion from a first sub-network. The method of claim 22, wherein The method comprises: receiving second template information of a local agent instance corresponding to the second terminal or an identifier of the second template information, the second template information being used to create the local agent instance corresponding to the second terminal. The method of claim 22, wherein The method comprises: creating a local agent instance corresponding to the first terminal. The method of claim 24, wherein The method comprises: receiving first template information of an agent instance corresponding to the first terminal or an identifier of the first template information, the first template information being used to create the local agent instance corresponding to the first terminal. A communication device characterized by comprising: The apparatus comprises modules for performing the method of any one of claims 1-25. A communication system characterized by The system comprises at least one of the following: a first terminal, a second terminal, a first artificial intelligence agent function network element, an agent registration function network element; a local agent instance corresponding to the first terminal and a local agent instance corresponding to the second terminal are deployed in the first artificial intelligence agent function network element, the agent instance corresponding to the first terminal is used to implement the method of any one of claims 1-15, the agent instance corresponding to the second terminal is used to implement the method of any one of claims 16-21, and the first artificial intelligence agent function network element is used to implement the method of any one of claims 22-25; the agent registration function network element is used to save and register agent instances. A communication device characterized by comprising: The communication device comprises a memory and a processor, the memory is used to store instructions, the processor is used to execute the instructions stored in the memory, and execution of the instructions stored in the memory causes the processor to perform the method of any one of claims 1-15, or perform the method of any one of claims 16-21, or perform the method of any one of claims 22-25. A chip characterized by The chip comprises at least one processor and a communication interface, the communication interface is coupled with the at least one processor, the at least one processor is used to run computer programs or instructions to realize the method as claimed in any one of claims 1-15, or realize the method as claimed in any one of claims 16-21, or realize the method as claimed in any one of claims 22-25, and the communication interface is used to communicate with other modules outside the chip. A computer-readable storage medium, characterized by The computer readable storage medium stores instructions, when the instructions are run, realize the method as claimed in any one of claims 1-15, or realize the method as claimed in any one of claims 16-21, or realize the method as claimed in any one of claims 22-25. A computer program product comprising instructions, characterized in that When the instructions are run on the computer, the computer is caused to execute the method as claimed in any one of claims 1-15, or execute the method as claimed in any one of claims 16-21, or execute the method as claimed in any one of claims 22-25.

Images