A communication method and apparatus

Abstract

A communication method and device, the method comprising: a first intelligent agent sending a first request to a first network element, the first request being used for requesting to create a first network; the first network element creating the first network in response to the first request and sending a second request to a second intelligent agent. The first network is a mobile communication network. The second request comprises an identifier of the first network, and the second request is used for requesting the second intelligent agent to join the first network. Through the method, the first network element can create the first network based on the triggering of the first intelligent agent, and flexible networking of intelligent agents can be realized. Moreover, the first network element can actively trigger the second intelligent agent to join the first network, and the task execution efficiency can be improved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a communication method and apparatus. Background Technology

[0002] With the development of artificial intelligence (AI), more and more terminals are becoming intelligent, and correspondingly, various AI agents have emerged, also known as intelligent agents. Intelligent agents include, for example, robots with intelligent technologies, intelligent cars, smartphones, and intelligent wearable devices.

[0003] Some tasks require collaboration among multiple intelligent agents. For example, in emergency rescue scenarios, on-site rescue operations may require the participation of multiple intelligent agents. For instance, aerial agents (such as drones) conduct aerial reconnaissance, while ground-based agents (such as robots and intelligent vehicles) perform search and rescue missions and are responsible for transporting supplies. To achieve efficient rescue, these multiple intelligent agents need to collaborate. For example, ground-based agents can use terrain information gathered by aerial agents to plan suitable routes. However, how to achieve agent collaboration remains to be solved. Summary of the Invention

[0004] This application provides a communication method and apparatus for creating an intelligent agent network on demand to achieve intelligent agent collaboration.

[0005] To achieve the above objectives, the embodiments of this application adopt the following technical solutions:

[0006] Firstly, a communication method is provided, which can be applied to a core network side device (also called a core network device). The core network device can be the core network equipment itself, or a module or unit used to implement some or all of the functions of the core network equipment. For example, the core network device can be a circuit or chip / chip system in the core network equipment, or the core network device can be a logical node, logical module, or software module that implements all or part of the functions of the core network equipment. As an example, the core network device is an (AI) domain management function ((A)DMF), or the core network device can also be a circuit or chip / chip system (e.g., a system-on-chip (SoC) chip or a system-in-package (SIP) chip) or other functional module in the (A)DMF. For ease of description, the core network device is taken as a first network element. For example, the first network element includes (or is) a ((A)DMF) network element.

[0007] The method includes: a first network element receiving a first request from a first intelligent agent, and in response to the first request, sending a second request to a second intelligent agent. The first request is used to request the creation of a first network, which is a mobile communication network. The second request includes an identifier of the first network and is used to request the second intelligent agent to join the first network.

[0008] For example, when a first intelligent agent needs to perform a first task or requires another intelligent agent (e.g., a second intelligent agent) to perform the first task, it can send a first request to a first network element to request the first network element to create a first network. Upon responding to the first request, the first network element requests the second intelligent agent to join the first network so that the second intelligent agent can perform / complete the first task based on the first network. This method enables collaboration between intelligent agents. In this method, the first network element requests the second intelligent agent to join the first network based on the first intelligent agent's triggering, which is more flexible. Furthermore, the first network element can actively trigger the second intelligent agent to join the first network, which improves the execution efficiency of the first task compared to passively waiting for the second intelligent agent to join.

[0009] In one design, the first request includes the identifier of a second intelligent agent. In this design, the second intelligent agent is determined by the first intelligent agent and indicated to the first network element via the first request. Because the second intelligent agent is determined by the first intelligent agent, the needs of the first intelligent agent can be satisfied as much as possible.

[0010] In one design, the method further includes: a first network element determining a second intelligent agent. In this design, the second intelligent agent is determined by the first network element. The first network element can manage multiple intelligent agents, thereby selecting a second intelligent agent from these multiple intelligent agents to join the first network, thus avoiding unnecessary intelligent agents joining the first network and consuming the resources of the first network.

[0011] In one design, the first request includes first information, and the determination of the second intelligent agent by the first network element includes: the first network element determining the second intelligent agent based on the first information. Wherein, when the first information includes a communication protocol type, the second intelligent agent supports the communication protocol type. When the first information includes requirement information for a first task, the second intelligent agent satisfies the requirement indicated by the requirement information, wherein the first network is used for the execution of the first task. When the first information includes capability information of the intelligent agent, the capabilities of the second intelligent agent match the capabilities indicated by the capability information. When the first information includes information about an intelligent agent discovery method, the second intelligent agent supports being discovered by that intelligent agent discovery method.

[0012] In this design, the first information can be used to assist the first network element in determining the second intelligent agent, thereby ensuring that the second intelligent agent is suitable for joining the first network and avoiding unnecessary intelligent agents joining the first network and consuming its resources. For example, the first information may include the requirement information of the first task. The first network element can determine the second intelligent agent based on this requirement information, and the ultimately selected second intelligent agent meets the requirements indicated by the requirement information. Alternatively, the first information may include the capability information of the intelligent agent. The first network element can determine the second intelligent agent based on this capability information, and the ultimately selected second intelligent agent matches the capabilities indicated by the capability information, or the ultimately selected second intelligent agent possesses the capabilities indicated by the capability information. The above examples of the first information are merely illustrative; the specific content of the first information is not limited, as long as it can be used to assist the first network in determining the second intelligent agent. For example, the first information may also include the type information of the intelligent agent, so that the type of the second intelligent agent is the type indicated by the type information.

[0013] In one design, before sending the second request to the second agent, the method further includes: the first network element creating a first network.

[0014] In one design, the creation of a first network by a first network element includes: the first network element creating the first network when a first condition is met. The first condition includes at least one of the following: a first intelligent agent has the authority to request the creation of the network; a second intelligent agent has the authority to join the network; or a second intelligent agent has the authority to communicate with intelligent agents in the network. For example, the first intelligent agent having the authority to request the creation of the network includes having the authority to request the creation of the first network. Similarly, the second intelligent agent having the authority to join the network includes having the authority to join the first network. Likewise, the second intelligent agent having the authority to communicate with intelligent agents in the network includes having the authority to communicate with intelligent agents in the first network. In this design, the first network decides whether to create the first network based on the first condition, which avoids the first network element creating an unnecessary first network, thereby avoiding a waste of network resources. For example, if the first intelligent agent does not have the authority to request the creation of the network, the first network element does not create the first network. Furthermore, if the second intelligent agent does not have the authority to join the network, even if the first network creates the first network, the second intelligent agent cannot join the first network; therefore, the creation of the first network is unnecessary, and the first network element does not create the first network. For example, if the second agent does not have the authority to communicate with agents in the network, even if the first network creates the first network, the second agent cannot cooperate with other agents. In this case, the creation of the first network is unnecessary, and the first network element does not create the first network.

[0015] In one design, the creation of a first network by a first network element includes: the first network element creates the first network only when at least M agents accept joining the first network, where M is a positive integer. In this case, the first network element sending a second request to a second agent includes the first network sending a second request to the at least M agents. In this design, the acceptance of joining the first network by at least M agents can be considered a condition for the first network element to create the first network. In other words, the first network element creates the first network only when at least M agents accept joining. Conversely, if fewer than M agents accept joining, the first network element does not create the first network. This design avoids the waste of network resources caused by the first network element creating unnecessary first networks.

[0016] In one design, before the first network element creates the first network, the method further includes: the first network element receiving second information from at least M agents, the second information indicating acceptance of joining the first network. In this design, the first network element directly determines whether an agent accepts joining the first network based on the second information, resulting in lower processing complexity.

[0017] In one design, the first request includes M. In this design, M, as a condition for whether to create the first network, can be indicated by the first agent to the first network element. For example, the first agent specifies that at least M agents must accept joining the first network to complete the first task, thereby the first network element determines that at least M second agents must accept joining the first network before creating the first network, in order to avoid the first network element creating an unnecessary first network and wasting network resources.

[0018] In one design, the creation of a first network by a first network element includes: if the agents accepting membership in the first network include agents indicated by first attribute information, the first network element creates the first network. In this case, the first network element sending a second request to a second agent includes the first network sending a second request to the agents accepting membership in the first network. In this design, the agent indicated by the first attribute information can be a specific agent, a specific type of agent, etc. The acceptance of membership in the first network by the agent indicated by the first attribute information can be considered a condition for the first network element to create the first network. In other words, the first network element creates the first network only when the agent indicated by the first attribute information accepts membership. Conversely, if the agents accepting membership do not include the agent indicated by the first attribute information, the first network element does not create the first network. This design avoids the waste of network resources caused by the first network element creating unnecessary first networks.

[0019] In one design, before the first network element creates the first network, the method further includes: the first network element receiving second information from at least N agents, the second information indicating acceptance of joining the first network, wherein the N agents include agents indicated by first attribute information, and N is a positive integer. In this design, the first network element directly determines whether an agent accepts joining the first network through the second information, thereby determining that the agents accepting joining the first network include the agents indicated by the first attribute information, resulting in lower processing complexity.

[0020] In one design, the first request includes first attribute information. In this design, the first attribute information serves as a condition for whether to create a first network. It can be indicated by a first intelligent agent to a first network element, so that the first network element determines whether the condition for creating the first network is met based on the first attribute information, and only then creates the first network, thereby avoiding the waste of network resources caused by the first network element creating an unnecessary first network.

[0021] In one design, before receiving the second information, the method further includes: a first network element sending at least one of the following information: a communication protocol type, agent capability information, agent discovery method information, or first task requirement information, wherein the first network is used for executing the first task. This at least one piece of information can be used to determine whether to accept joining the first network. For example, before the first network element receives the second information from at least M agents, the method further includes: the first network element sending the at least one piece of information to the at least M agents, the at least one piece of information being used by the at least M agents to determine whether to accept joining the first network. As another example, before the first network element receives the second information from at least N agents, the method further includes: the first network element sending the at least one piece of information to the at least N agents, the at least one piece of information being used by the at least N agents to determine whether to accept joining the first network.

[0022] In this design, agents decide whether to join the first network based on at least one piece of information, which maximizes the ability of agents within the first network to collaborate and facilitates efficient cooperation. Furthermore, this design supports negotiation of application layer protocol parameters. For example, an agent can negotiate the communication protocol type with other agents in the first network, thereby establishing a data transmission channel within the first network based on the negotiated communication protocol type for communication.

[0023] In one design, the first network element sending the at least one piece of information includes: when the first network is a temporary network, the first network element sends at least one piece of information. When a temporary network is released, the context information associated with that network is deleted. Compared to temporary networks, when a permanent / persistent network is released, the context information associated with that network does not need to be deleted and can be reused subsequently, thus avoiding duplicate input. For example, if the network is a persistent network, by retaining the context information, the network can automatically apply this information later (e.g., when the first network element recreates the network, it obtains the at least one piece of information from the context information retained by the network), without requiring the first agent to provide the same data again. In this design, when the first network is a temporary network, the first network element sends at least one piece of information so that other agents in the network can be aware of that at least one piece of information.

[0024] In one design, sending a second request from a first network element to a second intelligent agent includes: the first network element sending the second request to the second intelligent agent through a second network element, wherein the second network element serves the second intelligent agent, and the first network element serves the first intelligent agent. The second network element serving the second intelligent agent can be replaced by the second intelligent agent being within the service range of the second network element. Similarly, the first network element serving the first intelligent agent can be replaced by the first intelligent agent being within the service range of the first network element. This design enables collaboration between intelligent agents within different network ranges.

[0025] In one design, the method further includes sending a fifth request to a third agent. The fifth request includes an identifier of the first network and is used to request the third agent to leave the first network. In this design, the first network element can remove the third agent from the first network to improve network resource utilization. For example, if the third agent has already collaboratively completed a first task, it can leave the first network, thereby releasing the resources occupied by the third agent.

[0026] In one design, the method further includes receiving a fourth request before sending a fifth request to the third agent, the fourth request being used to request the third agent to leave the first network. In this design, the first agent can proactively trigger a first network element to delete a third agent that has already joined the first network as needed, achieving network updates without needing to rebuild the first network, thus providing greater flexibility.

[0027] In one design, the method further includes: when a second condition is met, the first network element releases the first network, wherein the second condition includes at least one of the following: an agent indicated by second attribute information in the first network leaves the first network; all agents in the first network leave the first network; the transmission rate in the first network is less than or equal to a first threshold; or a first task is completed, wherein the first network is used for executing the first task. The second condition is the condition for releasing the first network; when the second condition is met, the first network element releases the first network, which helps to save network resources.

[0028] In one design, releasing the first network by the first network element includes: if the first network is a temporary network, the first network element deletes the context information associated with the first network. Deleting the context information associated with the first network when it is released saves network storage space.

[0029] In one design, the creation of a first network by a first network element includes: the first network element allocating at least one of the following resources to the first network: control plane resources, user plane resources, data plane resources, or computing resources. The types of resources mentioned above are merely examples.

[0030] In one design, the second request includes a non-access stratum (NAS) message or a push message. This design supports collaboration between agents via NAS messages, which can be exchanged directly through the core network with fewer physical links. Compared to configuring the network based on application function (AF) network elements through network exposure function (NEF) interfaces, which requires forwarding through more physical links, this design makes collaboration between agents more efficient. Sending the second request based on a push message (or short message) ensures that the second request is sent to the second agent even if the agent has not yet entered the connected state, thus maximizing the chances of successful transmission of the second request.

[0031] In one design, the second agent supports the NAS protocol, and the second request is a NAS message; alternatively, the second agent does not support the NAS protocol, and the second request is a PUSH message; or, the second agent supports the NAS protocol, but the NAS message is unreachable, and the second request is a PUSH message. Here, NAS message unreachability includes situations where the NAS message channel has not been established and the second agent has not entered the connected state. In this design, the second request can be either a NAS message or a PUSH message. The first network element can choose to send the second request as a NAS message or a PUSH message based on the capabilities of the second agent (e.g., whether it supports the NAS protocol) and the connection status of the second agent, in order to maximize the cooperation efficiency between agents or ensure the success rate of the second request.

[0032] Secondly, a communication method is provided that can be applied to an intelligent terminal. The intelligent terminal can be the intelligent agent itself, or a module or unit used to perform some functions of the intelligent agent, or it can be a logical node, logical module, or software module that implements all or part of the functions of the intelligent agent. In one example, the intelligent terminal is a second intelligent agent, or the intelligent agent is a circuit or chip / chip system (e.g., a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core) or other functional module within the second intelligent agent.

[0033] The method includes: a second agent receiving a second request from a first network element, and in response to the second request, sending a message indicating joining a first network to send the identifier of the first network to a third network element. The second request includes the identifier of the first network and is used to request the second agent to join the first network. The third network element is used for forwarding data packets within the first network. For example, the third network element is used for forwarding data packets between the second agent and other agents in the first network, where the data packets include the identifier of the first network.

[0034] In this method, the third network element can be used for packet forwarding / routing between agents in the first network. For example, the third network element can be used for packet forwarding / routing between the second agent and other agents in the first network. In this method, the second agent, triggered by the first network element, sends a message indicating its intention to join the first network, thereby sending the identifier of the first network to the third network element.

[0035] Sending the identifier of the first network to the third network element can also be understood as adding the identifier of the first network to the third network element, or adding the identifier of the first network to the context of the second intelligent agent stored in the third network element. For example, after receiving the identifier of the first network, the third network element adds the identifier of the first network to the context of the second intelligent agent.

[0036] A second intelligent agent joining the first network can send data packets to other intelligent agents in the first network, or send data packets to other intelligent agents in the first network via a third network element. For example, the second intelligent agent sends a data packet containing the identifier of the first network. The third network element receives this data packet and forwards it to other intelligent agents in the first network based on the identifier, thus enabling collaboration between intelligent agents. Furthermore, the second intelligent agent joins the first network based on a trigger from the first network element, thereby improving the efficiency of collaboration between intelligent agents. For instance, the third network element receives the data packet, determines the routing rules of the first network based on the identifier, and then forwards the data packet to other intelligent agents in the first network according to the routing rules.

[0037] In one design, the method further includes: a second agent sending a first data packet to an agent in the first network via a third network element, the first data packet including an identifier of the first network. This design uses the identifier of the first network in the first data packet to indicate that the first data packet is a data packet from the first network, supporting the establishment of data transmission channels in the first network through a user plane session establishment process. This avoids the need to repeatedly construct session management and data channel management functions in the first network, thereby simplifying network architecture design.

[0038] In one design, the second request includes a communication protocol type. Sending a first data packet from the second agent to an agent in the first network via a third network element includes: the second agent sending the first data packet to the agent in the first network via the third network element according to the communication protocol type. In this design, the second request includes a communication protocol type, allowing the second agent to communicate with agents in the first network based on the communication protocol type. For example, the second agent can establish end-to-end communication with agents in the first network based on communication protocol parameters (e.g., domain name, application layer information) corresponding to the communication protocol type.

[0039] Optionally, the second request may further include at least one of the following information: agent capability information, agent discovery method information, or first task requirement information. This at least one piece of information can be used by the second agent to communicate with agents in the first network. The second agent may send a first data packet to agents in the first network via a third network element according to the content included in the second request. For example, the second agent may determine an agent discovery method based on the second request, discover agents in the first network based on this method, and then send a first data packet to the discovered agents. Alternatively, the second agent may negotiate the communication protocol type to be used with agents in the first network based on the communication protocol type, and then send a first data packet to agents in the first network according to the communication protocol parameters corresponding to that communication protocol type.

[0040] In one design, before the second agent receives a second request from the first network element, the method further includes: the second agent sending information to the first network element indicating acceptance of joining the first network. In this design, the second agent can explicitly indicate acceptance of joining the first network, which helps the first network decide whether to create the first network and saves network resources.

[0041] In one design, the method further includes: a second agent receiving a third request from a first network element, the third request including at least one of the following: communication protocol type, agent capability information, agent discovery method information, or first task requirement information, wherein the first network is used for the execution of the first task. In this scenario, the second agent sending information to the first network element to indicate acceptance of joining the first network includes: when the third request includes a communication protocol type and the second agent supports the communication protocol type, the second agent sends information to the first network element to indicate acceptance of joining the first network; when the third request includes requirement information for a first task and the second agent meets the requirement indicated by the requirement information, the second agent sends information to the first network element to indicate acceptance of joining the first network, wherein the first network is used for the execution of the first task; when the third request includes capability information of the agent and the second agent's capability matches the capability indicated by the capability information, the second agent sends information to the first network element to indicate acceptance of joining the first network; when the third request includes information on an agent discovery method and the second agent supports being discovered based on the agent discovery method, the second agent sends information to the first network element to indicate acceptance of joining the first network; when the third request includes the identifier of the first agent and the second agent has the authority to communicate with the first agent, the second agent sends information to the first network element to indicate acceptance of joining the first network. In this design, the second agent can decide whether to join the first network based on the information carried by the third request, which can ensure that the agents that join the first network can cooperate as much as possible, and help the cooperation between agents to be completed efficiently.

[0042] Thirdly, embodiments of this application provide a communication device for performing the method described in the first aspect, the second aspect, or any of the designs above. The beneficial effects can be found in the relevant descriptions of the first or second aspect, and will not be repeated here.

[0043] In one possible design, the communication device includes corresponding means, modules, or units for performing the methods of the first or second aspect. These modules, units, or means can be implemented in software, hardware, or a combination of both. For example, the communication device includes a processing unit (sometimes also called a processing module or processor) and / or input / output interfaces. Input / output interfaces include input interfaces and / or output interfaces, which can be interface circuits, output circuits, input circuits, pins, or related circuits. Optionally, the communication device also includes a transceiver unit (sometimes also called a transceiver module or transceiver). The transceiver unit is capable of both transmitting and receiving functions. When the transceiver unit performs the transmitting function, it can be called a transmitting unit (sometimes also called a transmitting module), and when it performs the receiving function, it can be called a receiving unit (sometimes also called a receiving module). The transmitting unit and the receiving unit can be the same functional unit, referred to as the transceiver unit, which performs both transmitting and receiving functions; or, the transmitting unit and the receiving unit can be different functional units, with the transceiver unit being a collective term for these functional units. These input / output interfaces and units (modules) can perform the corresponding functions in the method examples of the first or second aspect above. For details, please refer to the detailed description in the method examples, which will not be repeated here.

[0044] In one possible design, when the communication device is a second intelligent agent, the processing unit includes a baseband device and the transceiver unit includes a radio frequency device.

[0045] For example, the communication device is used to implement the corresponding functions in the method example of the first aspect. Accordingly, the transceiver unit is used to receive a first request from a first agent, the first request being for requesting the creation of a first network, the first network being a mobile communication network. The processing unit is used to create the first network in response to the first request. The transceiver module is also used to send a second request to a second agent, the second request including an identifier of the first network, the second request being for requesting the second agent to join the first network. See the detailed description in the method example for further details, which will not be repeated here.

[0046] For example, the communication device is used to implement the corresponding function in the method example of the second aspect. Accordingly, the transceiver unit is used to receive a second request from the first network element, and in response to the second request, to send a message indicating joining the first network to add the identifier of the first network to the third network element. The processing unit is used to generate a message indicating joining the first network. The second request includes the identifier of the first network and is used to request the second agent to join the first network. The third network element is used for packet forwarding in the first network. See the detailed description in the method example for further details; it will not be repeated here.

[0047] Fourthly, embodiments of this application provide a communication device including a processor configured to execute the methods of the first aspect or the second aspect and any of their designs. This application does not limit the specific type of processor. For example, the processor can be a baseband device, a central processing unit (CPU), or other specific integrated circuits. As another example, the processor can be 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, or discrete hardware components.

[0048] Optionally, the communication device further includes a memory for storing computer programs (also referred to as code or instructions), data, etc. The processor is coupled to the memory. When the processor reads the computer program, data, etc., from the memory, the methods of the first or second aspect and any of their designs are executed.

[0049] In one design, the memory is located outside the communication device.

[0050] In one design, the memory is located within the communication device.

[0051] In one design, the processor and memory are integrated together.

[0052] Fifthly, embodiments of this application provide a chip system including a processor and a communication interface for implementing the methods described in the first or second aspect. Optionally, the chip system further includes a memory. The memory stores computer programs (also referred to as code or instructions). The processor retrieves and executes the computer programs from the memory, causing a device equipped with the chip system to perform the methods of the first or second aspect and any of their designs. The chip system may be composed of chips or may include chips and other discrete devices.

[0053] Sixthly, embodiments of this application provide a communication device including an input / output interface and logic circuitry. The input / output interface is used for inputting and / or outputting information. The input / output interface may be an interface circuit, an output circuit, an input circuit, pins, or related circuits, etc. The logic circuitry is used to execute the methods described in the first or second aspect.

[0054] The communication device in the sixth aspect can be a chip, the input circuit can be an input pin, the output circuit can be an output pin, and the logic circuit can be a transistor, gate circuit, flip-flop, and various other logic circuits. The input signal received by the input circuit can be received and input by, for example, but not limited to, a receiver, and the signal output by the output circuit can be, for example, but not limited to, output to a transmitter and transmitted by the transmitter. Furthermore, the input circuit and the output circuit can be the same circuit, which is used as both the input circuit and the output circuit at different times. This application does not limit the specific implementation of the input / output interface and the logic circuit.

[0055] In one implementation of the sixth aspect, when the communication device is an intelligent agent, the interface circuit can be a radio frequency processing chip in the intelligent agent, and the processing circuit can be a baseband processing chip in the intelligent agent.

[0056] The aforementioned communication device may be the first network element in the first aspect, or it may be a device capable of supporting the first network element to perform the functions required by the method provided in the first aspect, such as a chip or chip system in the first network element. Alternatively, the communication device may be an intelligent agent in the second aspect. Or, the communication device may be a device capable of supporting the intelligent agent to perform the functions required by the method provided in the second aspect, such as a chip or chip system in the intelligent agent. The chip may be a baseband chip and / or a radio frequency chip, and the chip system may be composed of chips or may include chips and other discrete devices.

[0057] In a seventh aspect, embodiments of this application provide a communication system comprising a first network element and a first intelligent agent. The first network element is used to implement the functions described in the first aspect, and the first intelligent agent is used to request the first network element to create a first network. Optionally, the communication system further includes a second intelligent agent, which is used to implement the functions described in the second aspect.

[0058] Eighthly, embodiments of this application provide a computer-readable storage medium for storing a computer program or instructions that, when executed, cause the methods described in the first or second aspect and any of their designs to be implemented.

[0059] Ninthly, embodiments of this application also provide a computer program product containing instructions that, when run on a computer, cause the methods described in the first or second aspect and any of their designs to be implemented.

[0060] The beneficial effects of the third to ninth aspects and their implementation methods mentioned above can be referenced to the beneficial effects of the first or second aspect and any one of their designs. Attached Figure Description

[0061] Figure 1 This is a schematic diagram of the architecture of a communication system;

[0062] Figure 2 A flowchart illustrating the communication method provided in Embodiment 1 of this application;

[0063] Figure 3 This is a schematic diagram illustrating NAS message extension in an embodiment of this application;

[0064] Figure 4 A schematic diagram of a process for a first intelligent agent to send a first request according to an embodiment of this application;

[0065] Figure 5 Another flowchart illustrating the process of a first intelligent agent sending a first request as provided in an embodiment of this application;

[0066] Figure 6 A schematic diagram illustrating the process of a first network element sending a third request, provided in an embodiment of this application;

[0067] Figure 7 This is a flowchart illustrating the communication method provided in Embodiment 2 of this application;

[0068] Figure 8 This is a flowchart illustrating the communication method provided in Embodiment 3 of this application;

[0069] Figure 9 A schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0070] Figure 10 This is another schematic diagram of the communication device provided in the embodiments of this application. Detailed Implementation

[0071] This application provides a method for collaboration between intelligent agents. To facilitate understanding of the technical solutions provided in this application, the relevant terms and other information involved in the embodiments of this application will be explained below.

[0072] An AI agent is a concept in the field of AI. An AI agent possesses human-like intelligent abilities and behaviors, such as learning, reasoning, decision-making, and execution. An AI agent can react to changes in its environment, automatically adjusting its behavior and state. Different AI agents can also interact with each other based on their respective intentions. An AI agent can be a type of AI module or AI model.

[0073] In this application, an intelligent agent refers to software, hardware, or a combination of software and hardware that incorporates AI technology. Any entity that incorporates intelligent technology and can independently interact with other entities in the environment can be considered an intelligent agent. For example, an intelligent agent can be centered around an AI model and include memory modules, data processing modules, planning modules, and action modules. The AI ​​model can be a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q-learning model, or other machine learning models. The neural network can be a deep neural network, such as a convolutional neural network, a recurrent neural network, a fully connected neural network, or a Transformer network. In this application, the AI ​​model can be replaced with other names, such as AI algorithm, fusion model, or fusion algorithm, without limitation.

[0074] As an example, the intelligent agent is a digital human. The digital human referred to in this application is a virtual digital human, a virtual character with a digital appearance, displayed via a display device.

[0075] As another example, an intelligent agent is a terminal device centered on an AI model, or a terminal device with AI functionality. The AI ​​model is the concrete implementation of AI functionality; from this perspective, an intelligent agent can also be a terminal device that deploys an AI model. Alternatively, an intelligent agent can also be viewed as a terminal device driven by an AI agent. AI functionality can include at least one of the following: data collection (collecting training data and / or inference data), data preprocessing, model training (or model learning), model information dissemination (configuring model information), model validation (validating the trained model), model inference (performing inference using the trained model), or inference result dissemination. Inference can also be referred to as prediction. When the AI ​​model is located on a device (e.g., a terminal device or a core network device), for a specific functional module, one or more AI models in that device may be able to implement the functionality of that module. For example, for networking functionality, one or more AI models in the terminal can provide the functions involved in the networking process. In the embodiments of this application, "networking" can also be replaced with any of the following descriptions: creating a network, establishing a network, or building a network.

[0076] In this embodiment, the terminal device can also be replaced by a terminal or terminal apparatus. There are no restrictions on the type of terminal device. For example, the terminal device can be: user equipment (UE), mobile phone, mobile station, mobile terminal computer, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, station (STA), robotic arm, camera, robot, digital terminal, digital human, robot dog, vehicle, drone, helicopter, airplane, ship, or smart home device (e.g., television, air conditioner, robot vacuum cleaner, speaker, set-top box), relay, customer premises equipment (CPE), etc. When the terminal device is applied to vehicle-to-everything (V2X) communication, it can also be called a V2X device, such as a smart car, intelligent car, unmanned car, driverless car, pilotless car, or automobile, or roadside unit (RSU). The various terminal devices described above, if located on a vehicle (e.g., placed / installed inside the vehicle), can all be considered in-vehicle terminal devices. In-vehicle terminal devices can be built into a vehicle's in-vehicle module, in-vehicle component, in-vehicle chip, or in-vehicle unit as one or more components or units. The vehicle can implement the methods of this application through the built-in in-vehicle module, in-vehicle component, in-vehicle chip, or in-vehicle unit. In-vehicle terminal devices can be vehicle equipment, in-vehicle modules, vehicles, in-vehicle units (on-board units, OBUs), remote sensing units (RSUs), in-vehicle infotainment systems (or in-vehicle transmission units) (telematics boxes, T-boxes), chips, or system-on-chips (SoCs), etc. These chips or SoCs can be installed in the vehicle, OBU, RSU, or T-box.

[0077] Intelligent agents can be applied to various fields, such as intelligent manufacturing, intelligent transportation, smart homes, smart healthcare, intelligent security, autonomous driving, and smart cities. In some scenarios, multiple intelligent agents need to collaborate to complete a task. For example, in a home appliance repair scenario, a butler robot A invites a community service robot B to perform on-site repairs. With authorization from the butler robot A, service robot B temporarily establishes a network with the butler robot A and the home appliance to be repaired. Based on this network, service robot B and the butler robot A can communicate and exchange information (such as fault information) within the authorized scope to complete the repair task. As another example, in an emergency rescue scenario, a rescue robot (or a remote robot) and the robot working on-site can temporarily establish a network. Based on this network, they can share information such as map information, route planning information, task negotiation information, and rescue decision information to complete the rescue task. How to achieve collaboration between intelligent agents remains to be solved.

[0078] Therefore, embodiments of this application provide a method for intelligent agent networking. In this method, an intelligent agent requests the creation of a network from a core network. The core network responds to the intelligent agent's request, creates the network, and triggers the intelligent agents to join the network. On the one hand, the request to create the network is actively triggered by the intelligent agent, which helps to meet the actual application needs of the intelligent agent. On the other hand, the core network can actively trigger intelligent agents to join the network, which improves the execution efficiency of the tasks that the intelligent agent needs to perform compared to passively waiting for intelligent agents to join the network. Furthermore, the core network dynamically creates the network based on the triggering of the intelligent agent, which is more flexible.

[0079] The method provided in this application can be applied to various communication systems. For example, the communication system can be a cellular system related to the 3rd Generation Partnership Project (3GPP). Examples include Long Term Evolution (LTE), 5G mobile communication systems / New Radio (NR) communication systems, future communication systems, or other similar communication systems. Other similar communication systems may include Wireless Fidelity (WIFI), V2X, Internet of Things (IoT) systems, etc. The method provided in this application can be applied to terrestrial networks (TN); alternatively, the method can also be applied to non-terrestrial networks (NTN), such as satellite communication systems, for example, transparent satellite architectures, backhaul satellite architectures, or regenerative satellite architectures, etc., without limitation.

[0080] Please see Figure 1 This is a schematic diagram of the architecture of a communication system applicable to embodiments of this application. The network architecture comprises three parts: terminal equipment, access network (AN), and core network (CN). Logically, the core network can be divided into user plane and control plane. The control plane is responsible for the management of the mobile network, while the user plane is responsible for the transmission of service data. It should be noted that... Figure 1 The architecture shown is merely illustrative. The communication system described in the embodiments of this application is intended to more clearly illustrate the technical solutions of the embodiments of this application and does not constitute a limitation on the communication system to which the embodiments of this application apply. For example, the communication system may also include other devices, such as wireless relay devices and wireless backhaul devices, etc. Figure 1 Not shown in the diagram. Those skilled in the art will recognize that, with the evolution of network architecture, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems. When applying the technical solutions of the embodiments of this application to other communication systems, the devices, components, modules, etc., in the embodiments can be replaced with corresponding devices, components, modules in other communication systems, without limitation.

[0081] The following are Figure 1 The various components of the architecture shown are described in detail. The terminal devices include intelligent agents / intelligent terminals, which are described above and will not be repeated here.

[0082] (1) Access Network

[0083] Access networks include radio access networks (RANs), which are interchangeable with RANs. For ease of description, RANs will be used as an example below. RANs can be access networks in 3GPP-related cellular systems, or they can be open RANs (O-RAN or ORAN), cloud radio access networks (CRANs), virtualized RANs (vRANs), NTNs, etc. RANs can also be access networks in communication systems that integrate two or more of the above systems.

[0084] RAN includes at least one RAN device, which can also be called a RAN node, RAN entity, or access node, etc. In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), or a base station in a future mobile communication system. RAN nodes can be macro base stations, micro base stations, indoor stations, relay nodes, donor / host nodes, or radio controllers, etc. RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, in V2X technology, the RAN node can be an RSU (Radio Service Unit).

[0085] In another possible scenario, the RAN node can be a module or unit that performs some of the functions of the base station; or multiple RAN nodes can cooperate to assist terminal equipment in achieving wireless access, with different RAN nodes performing some of the functions of the base station. For example, the RAN node can be a central unit (CU), a distributed unit (DU), or a radio unit (RU). The function of the CU can be implemented by a single entity or by different entities. For example, the function of the CU can be further divided, that is, the control plane and the user plane can be separated and implemented by different entities, namely the control plane CU entity (i.e., CU-control plane (CP) entity) and the user plane CU entity (i.e., CU-user plane (UP) entity). The CU-CP entity and the CU-UP entity can be coupled with the DU to jointly complete the function of the RAN node. The CU and DU can be set up separately or included in the same network element, such as in the baseband unit (BBU). Any of the units among the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented by software modules, hardware modules, or a combination of software modules and hardware modules.

[0086] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an open RAN (ORAN) system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples.

[0087] The CU and DU can be configured according to the protocol layer functions of the wireless network they implement: for example, the CU can be configured to implement the functions of the Packet Data Convergence Protocol (PDCP) layer and above (such as the Radio Resource Control (RRC) layer and / or the Service Data Adaptation Protocol (SDAP) layer); the DU can be configured to implement the functions of the protocol layers below the PDCP layer (such as the Radio Link Control (RLC) layer, the Medium Access Control (MAC) layer, and / or the Physical (PHY) layer). For specific descriptions of the above protocol layers, please refer to the relevant 3GPP technical specifications or the technical specifications of other applicable communication protocols.

[0088] The above division of the processing functions of CU and DU according to protocol layers is merely an example; other division methods are also possible, and this application does not limit this. For example, in one design, CU or DU can be further divided into processing functions with protocol layers. In one design, some functions of the RLC layer and the functions of the protocol layer above the RLC layer are located in the CU, while the remaining functions of the RLC layer and the functions of the protocol layer below the RLC layer are located in the DU.

[0089] In another possible design, the DU and RU collaborate to implement the PHY layer functionality, or, more specifically, a portion of the PHY layer functionality of the DU can be moved to the RU. A DU can be connected to one or more RUs. The functions of the DU and RU can be configured in various ways depending on the design. For example, the DU may be configured to implement baseband functions, and the RU may be configured to implement mid-RF functions. Alternatively, the DU may be configured to implement higher-level functions in the PHY layer, and the RU may be configured to implement lower-level functions in the PHY layer, or both lower-level and RF functions. Higher-level functions in the physical layer may include a portion of the physical layer's functionality closer to the MAC layer, and lower-level functions may include another portion of the physical layer's functionality closer to the mid-RF side. This application does not limit the specific functions of the DU and RU. The interface between the DU and RU can be called a fronthaul interface. In one design, the CU may not have a PDCP layer; for example, the CU may only include an RRC layer. The CU-CP may not have PDCP-C. The CU-UP may not have PDCP-U, or may not have a CU-UP. In one design, the DU may not have an RLC layer; for example, the DU may only have a MAC and a higher PHY layer.

[0090] When the RAN is O-RAN, it can also have AI capabilities. For example, O-RAN includes an intelligent controller. The intelligent controller can be a non-real-time RAN intelligent controller (RIC / non-RT RIC / NRT RIC) or a near-real-time RAN intelligent controller (RIC / near-RT RIC / nRT RIC). A non-real-time RIC can be used to implement non-real-time intelligent management of RAN functions, enabling workflows including model training and model updates, and guiding applications / functions in the nRT RIC based on policies. A near-real-time RIC can be used to implement near-real-time intelligent management of the RAN. Through data collection and related operations on the E2 interface, near-real-time control and optimization of O-RAN modules and resources are achieved.

[0091] (2) Core Network

[0092] The core network can be divided into control plane network elements and user plane network elements. Control plane network elements include, for example, access management function network elements, unified data management network elements, session management function network elements, or policy control function network elements. User plane network elements include domain forwarding function network elements, etc. The following is an introduction to some network elements in the core network.

[0093] Access management function (AMF) network elements are used for access control and mobility management of terminal equipment accessing the operator's network. Functions include mobility state management, allocation of temporary user identities, and authentication (e.g., authentication). This AMF network element can be an access and mobility management function (AMF) network element in a 5G communication system. In future communication systems, AMF network elements may have other names, without limitation.

[0094] The session management function (SMF) network element is responsible for session management in mobile networks, such as session establishment, modification, and release. It can also assign Internet Protocol (IP) addresses to users, select user plane function (MPF) network elements providing packet forwarding, establish control plane session contexts for terminal devices, and forward control plane messages. This SMF network element can be a session management function (SMF) network element in a 5G communication system. In future communication systems, the SMF network element may have other names, without limitation.

[0095] Network Open Function (NEF) elements connect internal core network elements with external application servers to provide network capability information to external application servers or vice versa. For example, they can provide interfaces for opening dynamic networking capabilities to the external network, allowing terminal devices to initiate dynamic networking requests through application functions, which are then forwarded to the appropriate network functions. This NEF element can be a NEF element in a 5G communication system. In future communication systems, NEF elements may have other names, without limitation.

[0096] A network storage function (NRF) element is responsible for providing storage and selection functions for network function entity information to other network elements. For example, it can provide the ability to query the addresses of various related network functions. This NRF element can be a network repository function (NRF) element in a 5G communication system. In future communication systems, the NRF element may have other names, without limitation.

[0097] Domain management function network elements are responsible for the network's lifecycle management, including network creation, modification, and deletion. They allocate network resources by calling other functions or cooperating with other network elements, and can invite or trigger agents to join or leave the network. This domain management function network element can be a DMF network element in a 5G communication system. In future communication systems, the domain management function network element may have other names, without limitation.

[0098] Optionally, DMF network elements and SMF network elements can be deployed together.

[0099] The domain forwarding function network element is responsible for data forwarding between various agents within the network, including routing and forwarding unicast and broadcast data packets, and data exchange isolation between different networks. This domain forwarding function network element can be the domain forwarding function (DFF) network element in a 5G communication system. In future communication systems, the domain forwarding function network element may have other names, without limitation.

[0100] The identity management network element is responsible for managing the data identity of terminal devices, including terminal capability information associated with digital identities (such as the application layer communication protocols supported by the terminal, whether it supports dynamic networking, etc.). This identity management network element can be the identity management (IDM) network element in a 5G communication system. In future communication systems, the identity management network element may have other names, without limitation.

[0101] The data management network element is used to record user-related subscription information, including network information to which the user belongs (e.g., network identifier / status), member information within the network (e.g., member identifier / status), and whether the user can initiate / participate in dynamic networking (e.g., permitted network types). This data management network element can be a unified data management (UDM) network element in a 5G communication system. In future communication systems, the data management network element may have other names, without limitation.

[0102] Optionally, IDM and UDM network elements can be deployed together, and the subscription data of terminal devices can be stored in a separate database, such as a unified data repository (UDR) network element. The functionality of the UDM network element can be achieved through interaction with the UDR network element, which stores the data required by the UDM network element to perform its operations. In practice, the UDM network element and the UDR network element can be two independent physical entities, or the UDR network element can be integrated into the UDM network element; there are no limitations.

[0103] A network data analytics function (NWDAF) network element is used to collect and analyze network operation data from various network elements within the communication system. This NWDAF function can be a network data analytics function (NWDAF) network element in a 5G communication system. In future communication systems, the NWDAF network element may have other names, without limitation.

[0104] The Short Message Service Center (SMSC) is used to process and forward Short Message Service (SMS) messages. For example, when a user sends an SMS message, the SMSC receives and stores the message until the target device is ready to receive it. Once the target user's device is online, the SMSC forwards the message to the user.

[0105] The push server (PUSH) is responsible for sending invitation / trigger requests to join the network in the form of PUSH messages to the destination device based on the requests from DMF network elements.

[0106] In this application, a network element may also be referred to as an entity or a functional entity. For example, an AMF network element may also be referred to as an AMF entity or an AMF functional entity. Similarly, an SMF network element may also be referred to as an SMF entity or an SMF functional entity. Optionally, the device name mentioned in the embodiments of this application may omit "network element." For example, AMF network element and AMF have the same meaning.

[0107] The aforementioned network elements can serve intelligent agents; correspondingly, "XX network element" can also be called "intelligent XX network element". For example, an AMF network element is also called AAMF, an SMF network element is also called ASMF, a DMF network element can also be called ADMF, and so on.

[0108] The network elements / functional entities in the various possible network architectures described above can be network components in hardware devices, software functions running on dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform). Optionally, the aforementioned network elements or functional entities can be implemented by a single device, multiple devices working together, or different functional modules within a single device; this application embodiment does not specifically limit this. In actual deployment, the aforementioned network elements can be co-located. For example, a domain management function network element can be co-located with a session management function network element. When two network elements are co-located, the interaction between these two network elements provided in this application embodiment becomes an internal operation of the co-located network element or can be omitted.

[0109] (3) In the embodiments of this application, "transmission" includes "sending" and / or "receiving". "Sending" and "receiving" indicate the direction of signal transmission. For example, "sending information to XX" can be understood as the destination of the information being XX, including direct sending and indirect sending through other units, modules, devices, or network elements. "Receiving information from YY" can be understood as the source of the information being YY, including receiving directly from YY via the air interface and receiving indirectly from YY via other units or modules via the air interface. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface. In other words, sending and receiving can occur between devices, such as between access network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0110] In this application embodiment, the number of nouns, unless otherwise specified, refers to "singular nouns or plural nouns," that is, "one or more." "At least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A / B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. For example, A / B means: A or B. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and / or c means the following combinations: a exists alone, b exists alone, c exists alone, a and b exist simultaneously, a and c exist simultaneously, b and c exist simultaneously, or a, b, and c exist simultaneously, where a, b, and c can be single or multiple.

[0111] In the embodiments of this application, "when," "if," and "if" all refer to the device taking corresponding actions under certain objective circumstances, and are not time-limited, nor do they require the device to perform a judgment action, nor do they imply any other limitations. Unless otherwise specified, "if" and "if" can be substituted, and "when" and "in the case of" can be substituted. "When" and "if" / "if" can be substituted.

[0112] In the embodiments of this application, the words "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 this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner. In the embodiments of this application, "of," "corresponding, relevant," and "corresponding" may sometimes be used interchangeably, and it should be noted that their intended meanings are consistent unless their distinction is emphasized.

[0113] In this application's embodiments, ordinal numbers such as "first" and "second" are used to distinguish multiple objects, and are not used to limit the size, content, order, timing, priority, or importance of the multiple objects. For example, "first agent" and "second agent" refer to two different agents, and do not indicate a difference in the priority or importance of these two agents.

[0114] In the embodiments of this application, the solutions in each embodiment can be used in a reasonable combination, and the explanations or descriptions of various terms, similar operations, or steps appearing in the embodiments can be referenced or explained to each other in the embodiments, without limitation.

[0115] The solutions provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0116] In the following description, the communication method provided in the embodiments of this application is applied to Figure 1 The architecture shown is an example. The network architecture and application 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 by the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems. In the embodiments of this application, the solutions in each embodiment can be reasonably combined and used, and the explanations or descriptions of various terms, similar operations, or steps appearing in the embodiments can be referenced or explained to each other in the various embodiments, without limitation.

[0117] In the following description, the first network element plays a role in managing intelligent agents. It can build networks for intelligent agents, invite / request / trigger intelligent agents to join the network, and also trigger intelligent agents to leave the network. For example, the first network element includes DMF / ADMF. The first network element (e.g., DMF) can be an independent functional module, a part of an existing network element, or co-located with other functional network elements. For example, DMF is a functional module within AMF, and an AMF with DMF can be considered an enhanced AMF. Alternatively, the first network element can also be an intelligent agent that manages other intelligent agents and builds networks for them. In this case, the first network element can also be called the master intelligent agent, central intelligent agent, centralized intelligent agent, or advanced intelligent agent. Conversely, the first or second intelligent agent can also be called a lower-level intelligent agent or an edge intelligent agent.

[0118] The first intelligent agent can be one or more intelligent agents. In this paper, the intelligent agent used to request the first network element to create the first network is collectively referred to as the first intelligent agent. The second intelligent agent can be one or more intelligent agents. The second intelligent agent can execute / complete the first task, or the second intelligent agent can cooperate with the first intelligent agent to execute / complete the first task.

[0119] In this embodiment, the steps performed by the intelligent agent can be implemented by the intelligent agent itself, by components within the intelligent agent (such as chips, processing units, or processor modules), or by a device including the intelligent agent. For example, if the intelligent agent is an AI model, the steps performed by the intelligent agent can be implemented by a device deploying the AI ​​model. As another example, if the intelligent agent is a robot, the steps performed by the intelligent agent can be implemented by an AI processing chip within the robot. The steps performed by the first network element can be implemented by the first network element itself, or by components within the first network element (such as chips, processing units, or processor modules). Furthermore, the processing performed by a single executing entity can be divided into multiple executing entities, which can be logically and / or physically separated.

[0120] The embodiments of this application will be described in detail below with reference to Embodiments 1 to 3.

[0121] Example 1

[0122] Please see Figure 2 , Figure 2 This is a flowchart illustrating the communication method provided in Embodiment 1 of this application. Figure 2 This method is introduced from the perspective of the interaction between the first intelligent agent, the second intelligent agent, and the first network element. For example... Figure 2 As shown, the communication method provided in this application includes the following steps.

[0123] S201, The first intelligent agent sends the first request.

[0124] A first intelligent agent can send a first request to a first network element, and correspondingly, the first network element receives the first request from the first intelligent agent. This first request can be used to request the creation of a network. For ease of description, this network is referred to as the first network. The first network belongs to a mobile communication network; for example, the first network is a sub-network within a mobile communication network. The first network can also be understood as a logical communication domain partitioned within the physical underlying mobile communication network. This logical communication domain can include communication members (e.g., intelligent agents), the connection relationships between communication members, and network resources. These network resources include, for example, computing resources, storage resources, and resources used for communication connections. The specific name of the first request is not limited. For example, the first request can be called a network creation request.

[0125] A first intelligent agent can send a first request based on actual needs to trigger a first network element to create a first network. For example, when a first intelligent agent needs to perform a first task, the execution of which requires the cooperation of other intelligent agents, it sends a first request to a first network element to request the first network element to create a first network. Accordingly, the first network can be used for the execution of the first task. Using the first network for the execution of the first task can also be understood as using the first network for an intelligent agent to execute / complete the first task. For example, if the first task requires the cooperation of a second intelligent agent, then using the first network for the execution of the first task can also be replaced by using the first network for a second intelligent agent to execute / complete the first task.

[0126] In this embodiment, the first intelligent agent triggers the first network element to create the first network on demand, which helps to meet the actual needs of the first intelligent agent and improve the user experience. The first network element creates the first network based on the triggering of the first intelligent agent, which is more flexible.

[0127] In possible implementations, the first request may be explicitly or implicitly indicated as a request to create a first network, as illustrated in the following examples.

[0128] In implementation method 1, the first request is a signaling / message for requesting network creation, or the signaling / message for requesting network creation includes the first request. The first network element determines the function of the first request based on the signaling / message carrying the first request. This implementation method 1 can be understood as the first request explicitly indicating that it is used to request the creation of the first network.

[0129] In implementation method 2, the content included in the first request can implicitly indicate that the first request is used to request the creation of the first network.

[0130] As an example, the first request includes the identifier (ID) of the second agent, implicitly indicating that the first request is for requesting the creation of the first network, or indicating that the first request is for requesting the creation of the first network for the second agent. Alternatively, when the first request includes the identifier of the second agent, the first request is for requesting to establish communication with the second agent, implicitly indicating that the first request is for requesting the creation of the first network. Optionally, the identifier of the second agent is carried in a cell for requesting the creation of the network, indicating that the first request is for requesting the creation of the first network.

[0131] The specific implementation of the second agent's ID is not limited, as long as it can identify the second agent. For example, the second agent's ID can be the device number of the second agent, or the second agent's ID can be a virtual ID assigned to the second agent, such as the second agent's numeric ID.

[0132] The second agent can be one or more agents. The first network element receives a first request. When the first request includes the identifier of the second agent, the first network element determines that the first request is for requesting the creation of a first network, or that the first network element determines that the first request is for requesting the creation of a first network for the second agent. For the first agent, there are multiple candidate agents; however, due to limitations such as capabilities, some of these candidate agents can cooperate, while others cannot. Therefore, before sending the first request, the first agent can determine the second agent to ensure that the determined second agent can cooperate.

[0133] In one implementation, a first agent can determine a second agent from among multiple agents based on relevant information from these agents. These multiple agents can be all or some agents already connected to an agent communication network (ACN). This ACN is based on... Figure 1The architecture shown provides a network environment that enables communication and information sharing between agents. The first agent can obtain relevant information about these agents, such as their identifiers, application layer protocol information, and capability information. Application layer protocol information includes, for example, the communication protocol type and related configuration parameters. Communication protocol types include, for example, Data Distribution Service (DDS) and / or Hypertext Transfer Protocol (HTTP). Related configuration parameters include, for example, the domain ID required for DDS protocol communication, the participant ID (i.e., the agent's ID), the topic name and type, and the agent discovery method. It should be understood that a topic is a logical message channel used to publish messages to a specific message category. Clients subscribed to a topic can receive messages published by that topic. Publishers publish messages to specified topics, and subscribers receive messages by subscribing to the corresponding topics. The topic type refers to the data structure or data format of the message associated with that topic. Agent discovery methods are used for agents to discover each other, such as discovery methods based on the Simple Public Datagram Protocol (SPDP) and the Simple Endpoint Discovery Protocol (SEDP).

[0134] The above information regarding intelligent agents is merely illustrative, and no specific restrictions are placed on the details related to intelligent agents. The specific implementation method for the first intelligent agent to obtain information from multiple intelligent agents is also not restricted. The information of multiple intelligent agents can be stored in one or more network elements, and the first intelligent agent can obtain this information through interaction with these network elements. For example, the information of multiple intelligent agents may be stored on a server, and the first intelligent agent can obtain this information by querying the server. Alternatively, the information of multiple intelligent agents can be configured for the first intelligent agent, which can then store this information locally. Another example is that the first intelligent agent can obtain the information of multiple intelligent agents by scanning a code. The application layer protocol information of the intelligent agents may be stored in the IDM (Internet Data Manager), and the first intelligent agent can obtain this information by querying the IDM.

[0135] For example, a first intelligent agent can determine a second intelligent agent from multiple intelligent agents based on first information. The first information may include at least one of the following: communication protocol type, intelligent agent capability information, intelligent agent discovery method information, or requirements information for the first task. The content of the first information described above is merely illustrative; the embodiments of this application do not limit the specific content of the first information, as long as it can assist in determining the second intelligent agent. For example, the first information may also include intelligent agent type information. Based on the first information, the first intelligent agent can independently decide which second intelligent agent to perform the first task from among multiple intelligent agents already connected to the ACN, ensuring that the determined second intelligent agent is suitable for performing the first task and meets the actual needs of the first intelligent agent.

[0136] The communication protocol types may include, for example, DDS and / or HTTP. The first information may include one or more communication protocol types. When the first information includes multiple communication protocol types, the second agent supports one or more of these communication protocol types. For example, if the first information includes a first communication protocol type and a second communication protocol type, the second agent supports both the first and / or the second communication protocol type. When the first information includes at least one communication protocol type, the first agent may select an agent from among multiple agents that supports one or more of the at least one communication protocol type as the second agent. For example, if the first information includes DDS and HTTP communication protocol types, the first agent may select an agent that supports DDS as the second agent, or an agent that supports HTTP as the second agent, or an agent that supports both DDS and HTTP as the second agent. Ultimately, the second agent determined by the first agent may be one or more agents. It should be understood that when the first intelligent agent participates in the first task, the communication protocol type included in the first information includes (or is) the communication protocol type supported by the first intelligent agent, indicating that the first intelligent agent expects the second intelligent agent to support the communication protocol type supported by the first intelligent agent.

[0137] The capabilities indicated by the agent's capability information may include one or more of the following: collaboration and interaction capabilities, perception capabilities, reasoning and decision-making capabilities, or learning capabilities. Optionally, the capabilities indicated by the agent's capability information are related to the first task. For example, if the first task is a perception task, then it is expected that the second agent has perception capabilities. The first agent may select an agent from multiple agents whose capabilities match those indicated by its capability information as the second agent. Here, "matching" includes whether the second agent's capabilities fully or partially match those indicated by its capability information. For example, there are multiple candidate agents, including agent 1, agent 2, and agent 3, where agent 1 has collaboration and interaction capabilities and perception capabilities, agent 2 has perception capabilities, and agent 3 has collaboration and interaction capabilities and learning capabilities. When the capabilities indicated by the agent's capability information include perception capabilities, the second agent determined by the first agent may be agent 1 and / or agent 2. In this case, the second agent's capabilities fully match those indicated by its capability information. When the capabilities indicated by the capability information of an agent include perception capabilities and collaboration and interaction capabilities, the second agent determined by the first agent can be agent 1 and / or agent 3. In this case, the capabilities of agent 3 as the second agent partially match the capabilities indicated by the capability information of the agent.

[0138] The above-described capability information for an intelligent agent is merely an example, and the specific content of the capability information for an intelligent agent is not limited in the embodiments of this application. For example, the capability information for an intelligent agent may also include other content; for instance, the capability information for an intelligent agent may also indicate planning and execution capabilities. If the execution of the first task requires the intelligent agent to formulate a plan and execute it effectively, then a second intelligent agent that is more suitable to perform the first task can be determined based on whether the intelligent agent has planning and execution capabilities, which helps to complete the first task efficiently.

[0139] Agent discovery methods refer to the methods by which agents in a multi-agent system discover each other. Examples include methods that support discovery via SPDP (Specialized Private Diplomacy Detection Method) and methods that support discovery via SEDP (Secondary Private Diplomacy Detection Method). The first piece of information includes information about the agent discovery method itself, indicating that the second agent can be discovered using that method, or that the second agent can be discovered using that method. Considering agent discovery methods, efforts can be made to ensure that identified second agents can discover each other.

[0140] The first information may include information about one or more agent discovery methods. When the first information includes information about multiple agent discovery methods, the second agent supports being discovered through one or more of these methods. For example, the first information includes a first agent discovery method and a second agent discovery method, and the second agent supports being discovered through the first and / or the second agent discovery method. When the first information includes at least one agent discovery method, the first agent may select an agent that supports one or more of these methods as the second agent. For example, if the first information includes SPDP and SEDP, the first agent may select an agent that supports SPDP, an agent that supports SEDP, or an agent that supports both SPDP and SEDP as the second agent. Ultimately, the second agent determined by the first agent may be one or more agents. It should be understood that when the first intelligent agent participates in the first task, the intelligent agent discovery method included in the first information includes (or is) an intelligent agent discovery method supported by the first intelligent agent, and the first intelligent agent indicates that it expects the second intelligent agent to support the method through the intelligent agent discovery method supported by the first intelligent agent.

[0141] The requirements information for the first task includes at least one of the following: latency requirements, service type (e.g., data analysis), etc. When the first information includes the requirements information for the first task, the second intelligent agent satisfies the requirements indicated by that requirements information. The first intelligent agent can select from multiple intelligent agents that satisfy the requirements indicated by that requirements information as the second intelligent agent. For example, if the requirements information for the first task includes a service type indicating data analysis, the second intelligent agent can perform data analysis.

[0142] The agent's type information indicates the agent's type. There are no restrictions on how the agent type is classified. For example, based on behavior, agents can be categorized as reactive and proactive. Or, based on capabilities, agents can be categorized as learning agents and non-learning agents. When the first information includes agent type information, the type of the second agent is the type indicated by that information. The first agent can select the agent of the type indicated by that information as the second agent from among multiple agents.

[0143] In another implementation, the second intelligent agent can be determined by the first network element. For example, the first request may include first information. The first network element receives the first request and determines the second intelligent agent based on the first information. Typically, the first network element can manage multiple intelligent agents and has access to more information about them, or more information about different intelligent agents. This helps the first network element select a suitable second intelligent agent to meet the actual needs of the first intelligent agent. Furthermore, it helps reduce the processing complexity of the first intelligent agent, thus achieving a lightweight design. The method by which the first network element determines the second intelligent agent based on the first information is the same as the method by which the first intelligent agent determines the second intelligent agent based on the first information, and will not be elaborated here.

[0144] Optionally, after determining the second intelligent agent, the first network element may instruct the first intelligent agent. For example, in response to a first request, the first network element determines the second intelligent agent and sends a first response to the first intelligent agent. This first response may instruct the second intelligent agent; for example, the first response may include the identifier of the second intelligent agent.

[0145] Optionally, when the first request includes the identifier of at least one agent, the first request also includes first information. In this case, the at least one agent can be understood as an agent recommended by the first agent, and the second agent can ultimately be determined by the first network element. The first network element can determine the second agent based on the first information. The second agent can be some or all of the at least one agent, or the second agent can include some of the at least one agent and agents other than the at least one agent, or the second agent can be an agent other than the at least one agent.

[0146] For example, the first request includes the identifiers of agent 1, agent 2, and agent 3. The first information includes the requirement information for the first task and the capability information of the agents. Based on the requirement information and the capability information, the first network element determines that agent 2 is sufficient to complete the first task well. Agents 1 and 3 do not need to participate in the first task, and the first network element can determine that the second agent is agent 2. In this way, the participation of unnecessary agents can be reduced, saving network resources.

[0147] For example, the first request includes the identifiers of agent 1, agent 2, and agent 3. The first information includes the requirement information for the first task and the capability information of the agents. Based on the requirement information and the capability information, the first network element determines that the collaboration of agents 1, 2, and 3 is insufficient to complete the first task. The first network element can then determine other agents (e.g., agent 4) from among the agents other than agents 1, 2, and 3 to collaborate in completing the first task, based on the first information. Accordingly, the second agent is agents 1, 2, 3, and 4. Alternatively, if the first network element determines that the collaboration of agents 1, 2, and 3 cannot adequately complete the first task based on the requirement information and the capability information, the first network element can re-determine agents capable of adequately completing the first task, such as agents 1 and 4. Accordingly, the second agent is agents 1 and 4.

[0148] Optionally, the first request may also include an identifier of the first intelligent agent, so that the first network element determines the intelligent agent requesting the creation of the first network based on the identifier of the first intelligent agent. If the first request does not include an identifier of the first intelligent agent, the first network element can determine the first intelligent agent based on the source address of the first request.

[0149] Optionally, the first request may also include application layer information, which can be used by the agent performing the first task in the first network to negotiate the communication protocol and establish a communication session. The content of the application layer information can be found in the foregoing description and will not be repeated here. The application layer information included in the first request can be determined based on the application layer information of the first agent. For example, if the communication protocol supported by the first agent is DDS, the application layer information included in the first request may include DDS, the domain ID used by DDS, and the Topic name / type expected to interact with the second agent.

[0150] Optionally, the first request may also include relevant information about the first network, which can be used by the first network element to create the first network. For example, the relevant information about the first network may include at least one of the following: the identifier of the first network, the conditions that need to be met to create the first network, the type of the first network, and network resource description information. When the first request includes the identifier of the first network, the first agent also assigns an identifier to the first network. Optionally, the identifier of the first network may be assigned by the first network element; for example, when the first request does not include the identifier of the first network, the first network element assigns an identifier to the first network. The conditions that need to be met to create the first network, the type of the first network, and the network resource description information are described below in sequence.

[0151] (1) Conditions that need to be met to create the first network

[0152] The conditions for creating a first network may include at least one condition. If this at least one condition is met, the first network element creates the first network; conversely, if one or more of these conditions are not met, the first network element does not create the first network, thus avoiding the creation of an unnecessary first network and preventing waste of network resources. The following example illustrates the conditions required for creating a first network.

[0153] Condition a: The first agent has the authority to request the creation of a network.

[0154] The phrase "the first intelligent agent has the authority to request network creation" can be replaced with "the first intelligent agent is allowed to request network creation." The first network element will create the first network only when the first intelligent agent has the authority to request network creation. If the first intelligent agent does not have the authority to request network creation, then the first network element will not create the first network.

[0155] Optionally, when the first network element receives the first request from the first intelligent agent, if the first intelligent agent does not have the authority to request the creation of the network, the first network element may reject or ignore the first request.

[0156] Optionally, the first intelligent agent having the authority to request the creation of a network includes the first intelligent agent having the authority to request the creation of a first network. Before creating the first network, the first network element determines whether the first intelligent agent has the authority to request the creation of the first network.

[0157] Optionally, the first intelligent agent's authority to request network creation includes the first intelligent agent's authority to request the creation of a first type of network (e.g., a temporary network / persistent network). For example, if the first type of network is a temporary network and the first network is a temporary network, then the first network element creates the first network; if the first type of network is a temporary network and the first network is a persistent network, then the first network element does not create the first network.

[0158] Condition b: The second agent has the authority to join the network.

[0159] The phrase "the second agent has permission to join the network" can be replaced with "the second agent is allowed to join the network" or "the second agent has permission to be invited to join the network." If the second agent does not have permission to join the network or is not allowed in the first network, even if the first network element creates the first network, the second agent cannot join it, making the creation of the first network unnecessary. Therefore, the first network element only creates the first network when the second agent has permission to join, to avoid wasting network resources.

[0160] Optionally, the second intelligent agent's permission to join the network includes the second intelligent agent's permission to join the first network. Before creating the first network, the first network element determines whether the second intelligent agent has the permission to join the first network.

[0161] Optionally, the second intelligent agent's permission to join the network includes the second intelligent agent's permission to join a first type of network (e.g., a temporary network / persistent network). For example, if the first type of network is a temporary network and the first network is a temporary network, then the first network element creates the first network; if the first type of network is a temporary network and the first network is a persistent network, then the first network element does not create the first network.

[0162] Condition c: The second agent has the authority to communicate with agents in the first network.

[0163] Although the second agent supports communication with agents in the first network, it may be unable to do so due to permission restrictions. For example, a user can set permissions for an agent, including permissions to collaborate with other agents and to perform tasks. For instance, if the second agent is set not to collaborate with the first agent, and the first agent is located in the first network, the second agent can be considered to lack permission to communicate with agents in the first network.

[0164] If the second agent does not have the permission to communicate with agents in the first network, even if the first network element creates the first network and the second agent joins it, it will not be able to cooperate with the agents in the first network, making the creation of the first network unnecessary. Therefore, the first network element only creates the first network when the second agent has the permission to communicate with agents in the first network, in order to avoid wasting network resources.

[0165] Condition d: At least M agents accept joining the first network, where M is a positive integer.

[0166] The requirement that at least M agents accept joining the first network can also be replaced with: at least M agents agree to join the first network. These at least M agents can be understood as the M agents required to complete the first task. If fewer than M agents accept joining the first network, the first network element does not create the first network to conserve network resources.

[0167] Optionally, the at least M agents are M agents out of P agents, where P is an integer greater than or equal to M and P is an integer less than or equal to X, where X is the number of agent identifiers included in the first request. The P agents may be P specific agents (also called key agents) requested by the first agent. For example, the first request includes the identifiers of X agents, which include P key agents, and the M agents are M agents out of the P key agents. Alternatively, the P agents may be the P agents determined by the first network element in response to the first request.

[0168] Condition e: The agents that accept joining the first network include agents indicated by the first attribute information.

[0169] For example, completing the first task requires an agent indicated by the first attribute information to accept joining the first network. If the agents accepting joining the first network do not include the agent indicated by the first attribute information, the first network element does not create the first network to save network resource overhead.

[0170] The agent indicated by the first attribute information can be a specific agent. This specific agent can include at least one of the following: a specific agent or one or more agents, an agent of a specific type, an agent playing a certain role, or an agent possessing a certain ability. For example, the first attribute information includes the identifier of at least one agent, and the agent indicated by the first attribute information includes the agent indicated by the identifier of that at least one agent. Another example is that the first attribute information includes the type information of the agent, and the agent indicated by the first attribute information includes the type of agent indicated by that type information. Yet another example is that the first attribute information includes the ability information of the agent, which indicates a first ability, and the agent indicated by the first attribute information includes an agent possessing that first ability. For example, if the first ability is learning ability, the agent indicated by the first attribute information includes an agent possessing learning ability. Yet another example is that the first attribute information includes the role information of the agent, and the agent indicated by the first attribute information includes an agent capable of playing that role. For example, if the role is a decision-maker, the agent indicated by the first attribute information includes an agent capable of playing the role of a decision-maker.

[0171] The first request may include one or more of the conditions described above. For example, the first request may include M and / or first attribute information, that is, the first request may include condition d and / or condition e.

[0172] (2) Types of the first network

[0173] In the embodiments of this application, the type of the first network includes a first type and a second type, which are relative terms.

[0174] The first type of first network refers to a network where, after successful creation, relevant information / contextual information (such as the network's identifier, the identifiers of agents joining the network, and the agents' application layer information) is stored in the network (e.g., IDM / UDM / UDR). Even when an agent leaves the first network or the network is released, this information remains stored for future reuse. For example, if the network is of the first type, by retaining context information, the network can automatically apply this information later (e.g., when creating a new network, it can obtain the agent's application layer information from the retained context information) without requiring the first agent to provide the same data again.

[0175] The second type of first network refers to a network in which, after the first network is successfully created, the relevant information / context information of the first network (such as the identifier of the first network, the identifier of the intelligent agent that accepts the joining of the first network, application layer information, etc.) is stored in the network (such as IDM / UDM / UDR). When the intelligent agent leaves the first network or the first network is released, the relevant information / context information of the first network is deleted from the network and cannot be reused later.

[0176] The embodiments of this application do not limit the specific names of the first type of network and the second type of network. For example, the first type of network can be called a permanent / persistent network, and the second type of network can be called a temporary network.

[0177] (3) Network resource description information

[0178] Network resource description information can be used to indicate one or more network resources, or to indicate resources required by a first network. For example, network resource description information includes at least one of the following: whether the first network supports multicast / broadcast, network awareness, quality of service (QoS), duration of the first network, traffic requirements of the first network, traffic quota of the first network, etc.

[0179] As described above, the contents of the first request are as follows: how the first intelligent agent sends the first request to the first network element.

[0180] The first intelligent agent can send a first request to the first network element through a service-oriented interface with the first network element, or the first intelligent agent can send a first request to the first network element through other network elements, as described below.

[0181] (1) The first request is a NAS message

[0182] For example, the information elements included in the NAS message can be expanded to carry the content included in the first request. The NAS message supports the first agent to actively initiate the first request to the network in real time, and the exchange is carried out directly through the core network without going through the access layer. The physical links are reduced, which can improve the sending efficiency of the first request, and thus improve the efficiency of cooperation between agents.

[0183] As an example, a NAS message includes at least one of the following information elements: "Network Type", "Source Identifier", "Member Identifier", "Network Information", or "Application Layer Information", such as... Figure 3 As shown. Figure 3 Taking all the information cells mentioned above as an example.

[0184] The "Network Type" information element carries the type information of the first network. The NAS message may also omit the "Network Type" information element. In this case, the protocol predefines or the first agent and the first network element agree on the type of the first network. Alternatively, the NAS message may omit "Network Type" to indicate that the first network is of one type; or the NAS message may include "Network Type" to indicate that the first network is of another type. For example, the NAS message omitting "Network Type" indicates that the first network is a temporary network; the NAS message including "Network Type" indicates that the first network is a persistent network.

[0185] The "source identifier" cell can be used to carry the identifier of the first agent. Alternatively, the identifier of the first agent can be determined based on the source of the NAS message; therefore, the NAS message may not include the "source identifier" cell.

[0186] The "member identifier" cell can be used to carry the identifier of the second intelligent agent. If the first intelligent agent also wants to join the first network, the "member identifier" cell can also be used to carry the identifier of the first intelligent agent.

[0187] The "Network Information" cell is used to carry relevant information about the first network. As an example, the structure of "Network Information" is as follows:

[0188]

[0189] The "Application Layer Information" cell is used to carry application layer information. As an example, the structure of "Application Layer Information" is as follows:

[0190]

[0191] The above example provides only one possible form of expression. The data type can also be binary type-length-value (TLV) encoding, abstract syntax notation one (ASN.1) encoding, or other encoding methods.

[0192] The first agent can forward the first request to the first network element through AAMF or ASMF, or the first agent can send the first request directly to the first network element.

[0193] For example, see Figure 4 This illustrates three implementation methods for the first intelligent agent to send the first request to the first network element. These three implementation methods are as follows: Implementation Method 1 to Implementation Method 3.

[0194] In implementation mode 1, the first intelligent agent sends the first request to the first network element, including steps S401a to S403a.

[0195] S401a, The first agent sends a first request to AAMF.

[0196] Accordingly, AAMF receives a first request from the first agent, which is a NAS message.

[0197] S402a and AAMF determine the first network element based on the first request.

[0198] The AAMF receives a first request, determines that the first request is for creating a first network, and can select a suitable first network element to handle the first request. Taking the first network element as an example, the network may include multiple ADMFs, and the AAMF can select a matching first network element for the first agent based on the first request.

[0199] For example, the AAMF is locally configured with a policy for selecting the ADMF. This policy may include a correspondence between at least one piece of information and the ADMF, such as agent information, network type, etc. The AAMF can select one ADMF from multiple ADMFs as the first network element according to this policy.

[0200] For example, AAMF can query network elements such as IDM / UDM / UDR / NRF to obtain information about at least one ADMF, thereby determining the first network element ( Figure 4(Taking this as an example). For instance, the AAMF can send a query message to the UDM, which includes query conditions (such as agent and / or network type). The UDM receives the query message, determines the ADMF that matches the query conditions, and feeds back the information of that ADMF to the AAMF. For example, the UDM sends the identifiers or address information of one or more ADMFs to the AAMF. If the UDM sends the identifiers or address information of multiple ADMFs to the AAMF, the AAMF can select one ADMF from the multiple ADMFs as the first network element. It should be understood that if the first agent is in a roaming visited location, the query message can be routed to network elements such as the IDM / UDM / UDR / NRF of the home network, and the determined ADMF will also be an ADMF in the home network.

[0201] S403a and AAMF send the first request to the first network element.

[0202] The AAMF identifies the first network element and sends a first request to it. Optionally, during the process of sending the first request to the first network element, the AAMF can forward the first request to the first network element through other network elements with NAS routing forwarding capabilities. For example, if the AAMF is in a visited network, the AAMF needs to forward the first request to the ADMF in the home network through the gateway of the home network.

[0203] In implementation method 2, the first intelligent agent sends the first request to the first network element, including steps S401b to S404b.

[0204] S401b, The first agent sends the first request to AAMF.

[0205] Accordingly, AAMF receives a first request from the first agent, which is a NAS message.

[0206] S402b, AAMF sends the first request to ASMF.

[0207] AAMF receives a first request from the first agent and can send the first request to ASMF.

[0208] S403b and ASMF determine the first network element based on the first request.

[0209] The specific implementation of ASMF determining the first network element based on the first request can be found in the description of S402a above, and will not be repeated here.

[0210] S404b and ASMF send the first request to the first network element.

[0211] The specific implementation of ASMF sending the first request to the first network element can be found in the description of S403a above, and will not be repeated here.

[0212] Optionally, the first agent can send the first request directly to the ASMF, without having to send the first request to the ASMF through the AAMF.

[0213] In implementation method 3, the first intelligent agent directly sends a first request to the first network element, including steps S401c to S402c.

[0214] S401c, the first intelligent agent determines the first network element.

[0215] The first agent is locally configured with a policy for selecting an ADMF (Advanced Network Element). This policy may include a correspondence between at least one piece of information and an ADMF, such as agent information and network type. The first agent can select one ADMF from multiple ADMFs as the first network element according to this policy.

[0216] S402c, the first intelligent agent sends the first request to the first network element.

[0217] The first agent identifies a first network element and sends a first request to that first network element. Optionally, during the process of sending the first request to the first network element, the first request can be forwarded to the first network element by other network elements with NAS routing forwarding capabilities. For example, if the first agent is in a visited network, the first agent needs to forward the first request to the ADMF in the home network through the gateway of the home network.

[0218] (2) The first request is an HTTP message

[0219] For example, the message header and body of an HTTP message can be extended to implement a first request. The content of the first request can be carried within the message header and / or body of the HTTP message, and this content can be encapsulated in XML or JSON format. For details regarding the content of the first request, please refer to the aforementioned related content; it will not be repeated here. The first request is an HTTP message, and the first agent can initiate a network formation request to the ANEF via AF. This is equivalent to an enhancement of the networking process in 5G LAN, further supporting the first agent to proactively initiate network formation requests on the basis of 5G LAN networking, making it more flexible, timely, and efficient.

[0220] As an example 1, the message body of an HTTP message can be extended. The structure of the extended message body is as follows:

[0221]

[0222] As an example 2, the HTTP message header and message body can be extended, and the structure of the extended HTTP message is as follows:

[0223]

[0224] As an example 3, the HTTP message header can be extended. The structure of the extended message header is as follows:

[0225]

[0226]

[0227] The first agent can send a first request to the ANEF via the AF, and the ANEF will forward the first request to the first network element. Specifically, after receiving the first request, the AF sends the first request to the ANEF; this first request is an HTTP message. The ANEF, upon receiving the first request, can then send it to the first network element. Optionally, the ANEF sends the first request to the first network element when one or more conditions for creating the first network (e.g., one or more of the aforementioned conditions a to e) are met. The ANEF can then forward the first request to the first network element via one or more network elements within the network.

[0228] For example, see Figure 5 This illustrates three implementation methods for ANEF to send the first request to the first network element. These three implementation methods are as follows: Implementation Method 1 to Implementation Method 3.

[0229] In implementation mode 1, ANEF sends the first request to the first network element through APCF, and the process includes steps S501a to S504a.

[0230] S501a and ANEF send the relevant network configuration information to IDM / UDM / UDR.

[0231] The network configuration includes, for example, the content carried by the aforementioned information elements such as "network type", "source identifier", "member identifier", "network information", or "application layer information".

[0232] S502a and IDM / UDM / UDR send network configuration information to APCF.

[0233] When the network configuration changes, the IDM / UDM / UDR will send the updated network configuration to the APCF.

[0234] S503a and APCF determine the first network element based on the relevant network configuration.

[0235] The APCF determines the first network element based on the relevant network configuration. For example, the APCF can query the IDM / UDM / UDR / NRF and other network elements to find the matching first network element, as detailed in the aforementioned S402a, which will not be repeated here.

[0236] S504a and APCF send the first request to the first network element.

[0237] After APCF identifies the first network element, it sends the first request to the first network element.

[0238] In implementation method 2, ANEF directly sends a first request to the first network element, including steps S501b to S502b.

[0239] S501b and ANEF determine the first network element.

[0240] The ANEF receives the first request and determines the first network element based on the first request. The determination of the first network element by the ANEF is similar to that by the AAMF, and the details are described in S402a above, so they will not be repeated here.

[0241] S502b and ANEF send the first request to the first network element.

[0242] After identifying the first network element, ANEF sends a first request to it. ANEF can either transparently transmit the received first request to the first network element as an HTTP message, or ANEF can convert the first request into an interface type message that the first network element can process, such as a NAS message.

[0243] In implementation method 3, ANEF sends a first request to the first network element through ASMF, including steps S501c to S503c.

[0244] S501c and ANEF send the first request to ASMF.

[0245] ANEF can pass through the first request it receives to ASMF, which is an HTTP message; or ANEF can convert the first request into an interface type message that ASMF can handle, such as a NAS message.

[0246] S502c and ASMF determine the first network element.

[0247] The ASMF receives the first request and determines the first network element based on the first request. The determination of the first network element by the ASMF is similar to that by the AAMF, and the details are as described in S402a above, which will not be repeated here.

[0248] S503c and ASMF send the first request to the first network element.

[0249] After ASMF identifies the first network element, it sends the first request to the first network element.

[0250] The above implementation methods 1 to 3 can all enable the first intelligent agent to send a first request to the first network element. The specific implementation method used by the first intelligent agent is not restricted.

[0251] S202, The first network element responds to the first request and creates the first network.

[0252] A first network element receives a first request and, in response, can create a first network. Creating the first network includes allocating network resources to the first network. Allocating network resources includes requesting at least one other network element to create / configure resources, such as instantiating a new network element or network function, or requesting / reserving relevant resources from existing network elements. The new network element can be at least one network element, which can be deployed in different home networks (or different operator networks, or different network ranges). The new network function can be at least one network function, which can be deployed in different home networks (or different operator networks, or different network ranges). For example, the first network element can allocate at least one of the following resources to the first network: control plane resources (e.g., ASMF serving the first network), user plane resources (e.g., ADFF serving the first network), data plane resources (e.g., sensing functions serving the first network), or computing resources (e.g., computing functions serving the first network). Optionally, the first request includes network resource description information, and the first network element can allocate resources to the first network based on the network resource description information.

[0253] After the first network element creates the first network, it can also assign an identifier to the first network. Optionally, the identifier of the first network is assigned by the first intelligent agent. For example, if the first request includes the identifier of the first network, then the first network element does not need to assign an identifier to the first network. The first network element can also notify each network element serving the first network of the identifier of the first network, so that each network element can identify whether the information being interacted is related to the first network.

[0254] Specifically, if the conditions for creating the first network are met, the first network element will create the first network; if the conditions for creating the first network are not met, the first network element will not create the first network.

[0255] For example, if the first condition is met, the first network element creates the first network. This first condition may include one or more of the aforementioned conditions a to c. In one implementation, the IDM / UDM stores the subscription information of each agent, which includes the agent's permission information. The first network element can obtain the agent's permission information from the IDM / UDM to determine whether the first condition is met. In another implementation, the first network element locally stores the agent's permission information, or caches the agent's permission information from other network elements (e.g., APCF). The first network element can determine whether the first condition is met based on the locally stored agent permission information.

[0256] For example, the first network element creates the first network when the third condition is met. This third condition may include the aforementioned condition d and / or condition e. For example, the first network element creates the first network when M agents accept joining the first network. The first network element also creates the first network when an agent indicated by the first attribute information accepts joining the first network.

[0257] Before creating the first network, the first network element can determine whether there are M agents willing to join. As one implementation, the first network element can invite K agents to join the first network. If each of these K agents accepts the invitation, they can send a notification to the first network element confirming their acceptance, where K is an integer greater than or equal to M. For example, the first network element can send a third request to each of the K agents, requesting to join the first network. For any one of the K agents, if it receives the third request and accepts the invitation, it sends a second message to the first network element, indicating its acceptance. If the first network element receives the second message from the M agents, it determines that at least M agents have accepted the invitation to join the first network.

[0258] Optionally, the third request includes at least one of the following information, which can be used by the second agent to determine whether to join the first network. Alternatively, the at least one piece of information can be used by the second agent to communicate with agents in the first network. This at least one piece of information may include, for example, a communication protocol type, agent capability information, agent discovery method information, the identifier of the first agent, or the requirement information of the first task. For example, when the third information includes the identifier of the first agent, the second agent allows communication with the first agent and sends the second information to the first network element. Or, when the third request includes the identifier of the first agent, the second agent is authorized by the user to communicate with the first agent and sends the second information to the first network element. When the third request includes a communication protocol type, and the second agent supports that communication protocol type, it sends the second information to the first network element. When the third request includes the requirement information of the first task, and the second agent meets the requirement indicated by the requirement information, it sends the second information to the first network element. When the third request includes the agent's capability information, and the second agent's capabilities match the capabilities indicated by the capability information, it sends the second information to the first network element. When the third request includes information about the agent discovery method, the second agent supports sending the second information to the first network element when it is discovered based on the agent discovery method.

[0259] Similarly, before creating the first network, the first network element can determine whether the agent indicated by the first attribute information accepts joining the first network. For example, the first network element sends a third request to L agents. For any one of the L agents, if the agent accepts the third request and accepts joining the first network, then the agent sends a second message to the first network element, which indicates acceptance of joining the first network, where L is a positive integer. If the first network element receives second messages from N agents, then the first network element determines that N agents accept joining the first network, where N is an integer less than or equal to L. If these N agents include the agent indicated by the first attribute information, then the first network element determines that the agent indicated by the first attribute information accepts joining the first network.

[0260] Optionally, if the first network is a temporary network, the first network element sends a third request. Alternatively, based on the networking strategy configured locally by the first network element, the first network element sends third information. Optionally, if the first request includes the identifier of the first network, the third request may also include the identifier of the first network, for use by the first network element to trigger the second agent to join the first network.

[0261] The first network element can send a third request to the second agent through one or more network elements in the network. The third request can be a NAS message or a PUSH message. For example, when the second agent supports the NAS protocol, the third request is a NAS message. When the second agent does not support the NAS protocol, the third request is a PUSH message. When the second agent supports the NAS protocol but the NAS message is unreachable, the third request is a PUSH message. "NAS message unreachable" means that the NAS message to the second agent is unreachable. For example, if the NAS message channel to the second agent has not yet been established, or the second agent has not yet entered the connected state, then the NAS message to the second agent is unreachable. The first network element can choose to send the second request as a NAS message or a PUSH message based on the capabilities of the second agent (e.g., whether it supports the NAS protocol) and the connection status of the second agent, in order to maximize the cooperation efficiency between agents or ensure the success rate of sending the second request.

[0262] Please see Figure 6 This illustrates three implementation methods for a first network element to send a third request to a second intelligent agent. These three implementation methods are as follows: Implementation Method 1 to Implementation Method 3.

[0263] In implementation method 1, the first network element forwards the third request to the second intelligent agent through ASMF, including steps S601a to S603a.

[0264] S601a, the first network element determines ASMF.

[0265] After determining that the first condition is met, the first network element can identify the ASMF associated with the second agent, or the ASMF that serves the second agent. The network may contain multiple ASMFs, and the first network element needs to identify the ASMF associated with the second agent from among these multiple ASMFs.

[0266] For example, the first network element is locally configured with a strategy for selecting ASMFs. This strategy may include the association between agents and ASMFs. The first network element may select the ASMF associated with the second agent from multiple ASMFs according to this strategy.

[0267] For example, a first network element can query network elements such as IDM / UDM / UDR / NRF to obtain information on at least one ASMF, and then select the ASMF associated with the second agent from among these at least one ASMF. For instance, the first network element can send a query message to the UDM, which includes query conditions (such as the identifier of the second agent and / or network type). The UDM receives the query message, determines the ASMF matching the query conditions, and feeds it back to the first network element. For example, the UDM sends the identifiers or address information of one or more ASMFs to the first network element. If the UDM sends the identifiers or address information of multiple ASMFs, the first network element can select one ASMF from the multiple ASMFs. It should be understood that if the second agent is in a roaming visited location, the query message can be routed to network elements such as IDM / UDM / UDR / NRF in the home network, and the determined ASMF is also an ASMF in the home network.

[0268] S602a, the first network element sends a third request to the ASMF.

[0269] The first network element identifies the ASMF and sends a third request to it. Optionally, during the process of the first network element sending the third request to the ASMF, the third request can be forwarded to the ASMF by other network elements with NAS routing forwarding capabilities. For example, if the second agent is in a visited network, the first network element needs to forward the third request to the ASMF in the home network through the gateway of the home network.

[0270] S603a, ASMF sends a third request to the second agent.

[0271] Accordingly, the ASMF receives the third request and forwards it to the second agent. This third request can be a NAS message. Optionally, during the process of the ASMF sending the third request to the second agent, the third request can be forwarded through other network elements associated with the second agent (such as the AAMF) to minimize the possibility that the second agent may not receive the third request due to its movement.

[0272] In implementation method 2, the first network element directly sends the third request to the second intelligent agent, including step S601b.

[0273] S601b, the first network element sends a third request to the second intelligent agent, which can be a NAS message.

[0274] Correspondingly, the second intelligent agent receives a third request from the first network element.

[0275] Optionally, during the process of the first network element sending a third request to the second intelligent agent, the third request can be forwarded through other network elements (such as AAMF or network elements with NAS message routing function). Figure 6 The first network element sends the third request to the second intelligent agent via AAMF.

[0276] In implementation method 3, the first network element sends the third request to the second intelligent agent via a PUSH message, including steps S601c to S603c.

[0277] S601c, the first network element determines that the NAS message to the second intelligent agent is unreachable.

[0278] S601 is an optional step, meaning it is not a mandatory step. Figure 6 The middle part is indicated by a dashed line.

[0279] When the third request is an NSA message and the NAS message to the second agent is unreachable, the second agent will not receive the third request even if the first network element sends it. Therefore, when the first network element determines that the NAS message to the second agent is unreachable, it can send a third request to the second agent via a PUSH message to improve the success rate of the third request.

[0280] There are no restrictions on how the first network element determines that the NAS message to the second intelligent agent is unreachable. For example, the first network element sends a third request to the second intelligent agent according to the aforementioned implementation method 1 or implementation method 2, and the second intelligent agent responds to the third request by reporting a reception failure. Alternatively, the first network element can query the network connection status of the second intelligent agent. If the network is connected, then the NAS message to the second intelligent agent is reachable; if the network is not connected, then the NAS message to the second intelligent agent is unreachable.

[0281] S602c, the first network element determines the identifier of the PUSH message of the second intelligent agent.

[0282] The first network element can query the IDM / UDM / UDR for the identifier of the PUSH message from the second intelligent agent. This identifier is used by the first network element to send a PUSH message to the second intelligent agent, indicating that the PUSH message is intended for the second intelligent agent. This ensures that the PUSH message sent to the second intelligent agent is correctly identified and processed.

[0283] There are no restrictions on the specific implementation of the PUSH message identifier. For example, the PUSH message identifier can be the Mobile Station International Subscriber Directory Number (MSISDN), the International Mobile Subscriber Identity (IMSI), or the Subscription Permanent Identifier (SUPI), etc.

[0284] S603c, the first network element sends a third request to the second intelligent agent.

[0285] The first network element encapsulates the content of the third request into a PUSH message, or encapsulates the third request (or NAS message) within a PUSH message, and sends the PUSH message to the second intelligent agent. This PUSH message includes an identifier to indicate that it is sent to the second intelligent agent. The PUSH message can be an SMS message sent via SMS-SC, IMS, or other message channels.

[0286] Through any of the above implementation methods 1 to 3, the first network element can send the third request to the second intelligent agent. The specific implementation method used by the first network element is not restricted.

[0287] The first network element can proactively send a third request to the second agent to invite the second agent to join the first network. This allows for a more timely determination of whether the second agent accepts the invitation, helping to reduce the latency and improve the efficiency of creating the first network. Furthermore, the third request can be either a NAS message or a PUSH message, applicable to both connected and disconnected agents, thus broadening its applicability.

[0288] S203, the first network element sends a second request to the second intelligent agent.

[0289] Accordingly, the second agent receives a second request from the first network element. The first network element determines that the second agent accepts to join the first network and can send a second request to the second agent to request the second agent to join the first network. Sending a second request from the first network element to the second agent means that the first network element sends a second request to the agent that has accepted to join the first network. For example, the first network element sends a second request to the second agent when the second agent accepts to join the first network. Another example is that if at least M agents accept to join the first network, the first network element sending a second request to the second agent includes the first network element sending a second request to all at least M agents. Yet another example is that if the agent indicated by the first attribute information accepts to join the first network, the first network element sending a second request to the second agent includes the first network element sending a second request to the agent indicated by the first attribute information.

[0290] The second request may include at least one piece of information used by the second agent to join the first network, or used by the second agent to communicate with agents in the first network. This at least one piece of information may include, for example, the identifier of the first network, the identifier of the first agent, the identifier of the second agent, and application layer information. If any of the above information has already been sent to the second agent via the third request, the second request may not include that information. For example, if the third request includes the identifier of the first agent, the second request may not include the identifier of the first agent. Similarly, if the third request includes the identifier of the first network, the second request may not include the identifier of the first network.

[0291] Furthermore, the second request can be a NAS message or a PUSH message. For example, when the second agent supports the NAS protocol, the second request is a NAS message. When the second agent does not support the NAS protocol, the second request is a PUSH message. When the second agent supports the NAS protocol and the NAS message is unreachable, the second request is a PUSH message. The specific implementation of the first network element sending the second request to the second agent can be referred to the aforementioned implementation of the first network element sending the third request to the second agent, and will not be repeated here.

[0292] The first network element can proactively send a second request to the second intelligent agent to trigger the second intelligent agent to join the first network. Compared to the passive waiting process for the network to join the UE during UE networking in 5G LAN, this reduces the latency for the intelligent agent to join the first network, helping to improve the execution efficiency of the first task. Furthermore, the second request can be either a NAS message or a PUSH message, applicable to both connected and disconnected intelligent agents, thus having a wider range of applications.

[0293] S204, The second agent sends a message indicating that it will join the first network.

[0294] In response to the second request, the second agent can perform the operation of joining the first network. As an example, in response to the second request, the second agent can send a message indicating its intention to join the first network, thereby sending the identifier of the first network to a third network element, and then sending data packets to agents in the first network through the third network element. Sending the identifier of the first network to the third network element can also be understood as adding the identifier of the first network to the third network element, or adding the identifier of the first network to the context of the second agent stored in the third network element. For example, after receiving the addition of the identifier of the first network, the third network element adds the identifier of the first network to the context of the second agent.

[0295] The third network element is used for data packet forwarding between agents in the first network. For example, the third network element can be an ADFF (Advanced Directional Forwarding Filter), which can establish routing and forwarding rules for each agent in the first network, allowing each agent to forward data packets based on these rules. The forwarding methods include IP multicast, MAC broadcast, etc. "Route forwarding rules" can also be called data forwarding rules, data forwarding paths, or routing forwarding paths. The third network element can also perform network isolation for agents in different networks to prevent the flooding of data packets sent via IP multicast, MAC broadcast, etc. The third network element can be one or more network elements, determined by the networks to which the first and second agents belong, which will be described in detail below and will not be discussed here.

[0296] The process by which the second agent sends a message indicating its intention to join the first network involves interactions with the AAMF, ASMF, and third network element, including the process of establishing a user plane session between the second agent and the third network element. The information indicating its intention to join the first network includes some or all of the information exchanged between the various network elements during this process.

[0297] For example, a second agent initiates a session establishment request, which can be considered part of the information for joining the first network. This request may include the identifier of the first network. The access network device receives this session establishment request and forwards it to the AAMF. Upon receiving the session establishment request, the AAMF sends a session establishment request to the ASMF to request session creation. The session establishment request received by the AAMF and the one sent to the ASMF by the AAMF can be the same or different. The ASMF receives the session establishment request, configures the forwarding rules for the data flow, and assigns appropriate parameters to each bearer channel. The ASMF sends information including the identifier of the first network to a third network element to request routing and forwarding rules. For example, the ASMF sends a session establishment request to the third network element, which includes the identifier of the first network. The third network element receives this session establishment request and can establish routing and forwarding rules for agents in the first network. The third network element can also determine the configuration information of the bearer channels. After establishing the routing and forwarding rules, the third network element can report the routing and forwarding rules and the established bearer channel information back to the ASMF. The ASMF receives this information and notifies the ASMF that the session establishment is complete. The configuration information for the bearer channel includes the data encapsulation method, and the routing and forwarding rules configured by the third network element include tunnel establishment. ASMF also sends relevant information to the second agent for establishing a user plane session in the first network, enabling the second agent to establish such a session with the third network element. This relevant information may include the second agent's IP address in the first network and the user plane tunnel identifier used by the second agent in the first network.

[0298] After the second agent establishes a user plane session with the third network element (or joins the first network), it can send a first data packet to an agent in the first network (e.g., the first agent). This first data packet includes the identifier of the first network. For example, a second or third request may include information about the agent discovery method and application layer information. The second agent discovers an agent in the first network (e.g., the first agent) based on the agent discovery method and negotiates relevant parameters of the application layer protocol with the first agent based on the application layer information, thereby achieving end-to-end communication between the agents. Alternatively, the second and first agents can also discover each other based on application layer information and establish end-to-end communication based on the application layer information. For example, the second agent obtains the communication protocol type and relevant parameters of the communication protocol type based on the application layer information, and forwards data packets in the first network based on the relevant parameters. For example, when the application layer information includes relevant parameters of the DDS protocol (such as Domain ID, SPDP / SEDP, etc.), the first and second agents can discover each other using SPDP / SEDP based on the Domain ID, and then establish relevant Topic subscription notification interactions. For example, when application layer information includes AgentProtocol parameters (such as the Agent's URL), the first agent and the second agent 2 can establish HTTP requests to each other based on the URL, and interact with data packets based on these HTTP requests. The second agent establishes end-to-end communication, encapsulates the data to be sent into a first data packet, and forwards it to other agents in the first network via a third network element. Taking the second agent sending first data to the fifth agent in the first network as an example, the first data packet includes the identifier of the first network. The third network element receives the first data packet and, based on the identifier of the first network in the first data packet, forwards the first data packet to the fifth agent. The identifier of the fifth agent can be its IP address. For example, the third network element receives the first data packet, determines the routing rules of the first network based on the identifier of the first network, and then forwards the first data packet to the fifth agent in the first network according to the routing rules.

[0299] If the first intelligent agent also participates in executing the first task, then the first network element will also send a second request to the first intelligent agent. Similar to the second intelligent agent, the first intelligent agent receives the second request and, in response, sends information instructing the first network's identifier to be sent to the third network element; details will not be elaborated here. Optionally, when the first intelligent agent also participates in executing the first task, the second request sent by the first network element to the first intelligent agent can be a response message to the first request. In other words, when the first intelligent agent sends a first request to the first network element and also participates in executing the first task, the first network element can send a response to the first intelligent agent to the first request, which is used to request the first intelligent agent to join the first network.

[0300] pass Figure 2 The illustrated process enables collaboration between intelligent agents. The first intelligent agent can request network creation on demand, offering considerable flexibility. Furthermore, the first network element can proactively trigger the second intelligent agent to join the first network, improving the efficiency of collaboration between agents. Figure 2 The process shown supports negotiation of application layer protocol parameters between agents to achieve end-to-end application layer communication sessions.

[0301] Example 2

[0302] In Embodiment 2, based on the process of Embodiment 1, the first network element can also delete the intelligent agent in the first network.

[0303] Please see Figure 7 This is a flowchart illustrating a communication method provided in Embodiment 2 of this application. Figure 7 The flowchart shown only illustrates the process after the first network element creates the first network. For the process before and after the first network element creates the first network, please refer to [the provided text]. Figure 2 The process shown is repeated here; the parts that are repeated will not be described again.

[0304] S701, the first intelligent agent sends a fourth request to the first network element.

[0305] Accordingly, the first network element receives a fourth request from the first intelligent agent, which requests the third intelligent agent to leave the first network. The third intelligent agent is an intelligent agent that has joined the first network. The third intelligent agent can be one intelligent agent or multiple intelligent agents.

[0306] Optionally, the fourth request may also include the identifier of the third agent. If the fourth request does not include the identifier of the third agent, the first network element receives the fourth request and assumes that the first agent requests the deletion of all agents in the first network.

[0307] Optionally, if the first network element has the authority to request the deletion of an intelligent agent, it sends a fifth request to the third intelligent agent. Regarding the first network element's determination of whether the first intelligent agent has the authority to request the deletion of an intelligent agent, this authority includes one or more of the following: the first intelligent agent has the authority to request the deletion of at least one specific intelligent agent; the first intelligent agent has the authority to request the deletion of an intelligent agent of a specific type; or the first intelligent agent has the authority to request the deletion of an intelligent agent with a specific capability. For example, when the first intelligent agent has the authority to request the deletion of at least one specific intelligent agent, and the third intelligent agent belongs to that at least one intelligent agent, the first network element sends a fifth request to the third intelligent agent. When the first intelligent agent has the authority to request the deletion of an intelligent agent of a first type, and the third intelligent agent belongs to the first type of intelligent agent, the first network element sends a fifth request to the third intelligent agent. When the first intelligent agent has the authority to request the deletion of an intelligent agent with learning capabilities, and the third intelligent agent has learning capabilities, the first network element sends a fifth request to the third intelligent agent.

[0308] In this method, the first intelligent agent can request the first network element to delete the intelligent agents that have already joined the first network as needed, and the first network can be updated without rebuilding it, which is more flexible.

[0309] S702, the first network element sends the fifth request to the third intelligent agent.

[0310] The first network element receives the fourth request and, in response to the fourth request, sends a fifth request to the third intelligent agent. The fifth request includes the identifier of the first network and is used to request the third intelligent agent to leave the first network.

[0311] S703, the third agent sends a message indicating that it is leaving the first network.

[0312] The third agent receives the fifth request and sends a message to the ASMF indicating that it is leaving the first network, so that the ASMF releases the user plane session of the first network.

[0313] Figure 7The illustrated process uses the example of a first agent requesting a first network element to delete a third agent from the first network. In possible application scenarios, the first agent can also request the first network element to add agents to the first network. For example, if the first agent requests a fifth agent to join the first network, the first agent can send a sixth request to the first network element. This sixth request requests the fifth agent to join the first network. The first network element receives the sixth request and, in response, sends a second request to the fifth agent. This second request includes the identifier of the first network and requests the fifth agent to join the first network. The fifth agent receives the second request and performs the operation of joining the first network. The operation of the fifth agent joining the first network is similar to that of the second agent, and will not be described in detail here.

[0314] The first intelligent agent can request the first network element to add new intelligent agents to the first network as needed, and the first network can be updated without rebuilding it, which is more flexible.

[0315] When the first network is no longer needed, the first network element can release the first network to save network resources. It should be understood that releasing the first network includes releasing the resources associated with the first network. When the first network is a temporary network, when the first network element releases the first network, it also deletes the context information associated with the first network to save storage space as much as possible.

[0316] In a possible implementation, the first network element releases the first network when a second condition is met. This second condition includes at least one of the following conditions f to j:

[0317] Condition f: The agent indicated by the second attribute information in the first network leaves the first network.

[0318] For example, agents joining the first network need to collaborate to complete a first task. If the agent indicated by the second attribute information leaves the first network and the first task cannot be completed, then the first network element can release the first network to save network resource overhead. For example, completing the first task requires agents with learning capabilities, and the agents indicated by the second attribute information include agents with learning capabilities. As another example, completing the first task requires agents that act as decision-makers, and the agents indicated by the second attribute information include agents capable of acting as decision-makers.

[0319] The agent indicated by the second attribute information can be a specific agent. This specific agent can include at least one of the following: a specific agent or one or more agents, an agent of a specific type, an agent playing a certain role, or an agent possessing a certain ability. For details, please refer to the aforementioned description of the agent indicated by the first attribute information; it will not be repeated here.

[0320] Condition g: All agents in the first network leave the first network.

[0321] If all agents in the first network leave the first network, then the first network element can release the first network to save network resource overhead.

[0322] Condition h: The transmission rate in the first network is less than or equal to the first threshold.

[0323] The first threshold can be (pre)configured or predefined. The transmission rate in the first network can be the average transmission rate of all agents in the first network. If the transmission rate in the first network is less than or equal to the first threshold, then the quality of the first network is poor, affecting the completion of the first task. The first network element can release the first network to save network resource overhead. The condition j for the average transmission rate of all agents in the first network is: the first task is completed.

[0324] Once the first task is completed, the first network element can release the first network to save network resource overhead.

[0325] The foregoing Figure 2 or Figure 7 The illustrated process uses the example of the first and second agents belonging to the same network scope. Here, "network scope" can be replaced with "domain," "network service scope," or "ACN." In possible scenarios, the first and second agents belong to different network scopes. In this case, the interaction between the first and second agents can be forwarded through an intermediate network element. Similarly, the first network element and the second agent may also belong to different network scopes, and the interaction between them can be forwarded through an intermediate network element. For example, the first network element serves the first agent, or the first network element and the first agent belong to the first network scope, and the second network element serves the second agent, or the second network element and the second agent belong to the second network scope. Here, "the second network element serves the second agent" can be replaced with "the second agent is within the service scope of the second network element." Similarly, "the first network element serves the first agent" can be replaced with "the first agent is within the service scope of the first network element." In this case, the first network element can send a second request to the second agent through the second network element to achieve networking between agents located in different network scopes.

[0326] Example 3

[0327] In Example 3, the first agent and the second agent are not in the same network range.

[0328] Please see Figure 8 This is a flowchart illustrating a communication method provided in Embodiment 3 of this application. Figure 8The illustrated process describes the collaboration between agents belonging to different network scopes. In the following description, the first ADMF (ADMF1), first ASMF (ASMF1), first AAMF (AAMF1), first IDM (IDM1), and first ADFF (ADFF1) serve the first agent, while the second ADMF (ADMF2), second ASMF (ASMF2), second AAMF (AAMF2), second IDM (IDM2), and second ADFF (ADFF2) serve the second agent. Figure 2 or Figure 7 The repetitive parts of the process shown will not be repeated.

[0329] S801, The first intelligent agent obtains information from the second intelligent agent.

[0330] A first agent can query an IDM / UDM / UDR / NRF to learn about a second agent and then retrieve information about that second agent. For example, a first agent can request a query from a first IDM for at least one agent, where the first IDM and the first agent belong to the same network scope (e.g., ACN1), or the first IDM serves the first agent. In response to this request, the first IDM determines that the second agent and the first IDM are not in the same network scope, and queries the second IDM for at least one agent, where the second IDM belongs to a different network scope (e.g., ACN2) than the first IDM. The second IDM determines the information of at least one agent and feeds it back to the first IDM, which then feeds the information of at least one agent back to the first agent. This at least one agent includes the second agent, thus allowing the first agent to obtain information about the second agent.

[0331] S802, the first agent sends a first request to the second ADMF.

[0332] The first agent can send a first request to the second ADMF through the first ADMF. For example, the first agent sends a first request to the first ADMF, and the first ADMF forwards the first request to the second ADMF.

[0333] S803, the first ADMF and the second ADMF perform business authentication checks.

[0334] The first ADMF receives the first request and determines whether the first condition is met. If the first condition is met, the first request is sent to the second ADMF, as described in the relevant section of S202 above.

[0335] S804, the first ADMF sends a third request to the second agent.

[0336] The first ADMF can send a third request to the second agent through the second ADMF. When there are multiple agents as the second agent, the first ADMF can send a message (the third request) to the second ADMF, which includes the identifiers of the multiple agents. The second ADMF receives the message and can obtain the identifiers of the multiple agents. The second ADMF can then send the third request to each of these agents individually. In other words, the second ADMF sends multiple third requests, with each third request corresponding to one agent.

[0337] S805, the first ADMF determines whether the third condition is met.

[0338] The third condition may include the aforementioned condition d and / or condition e. If the first network element receives second information from at least M agents, then condition d is satisfied. If the first ADMF receives second information from N agents, and the N agents include the agent indicated by the first attribute information, then condition e is satisfied.

[0339] S806. If the third condition is met, create the first network.

[0340] The first ADMF responds to the first request and creates the first network. It should be understood that the creation of the first ADMF by the first network element requires interaction with other network elements in the network (such as ASMF, IDM, UDM, ADFF, etc.).

[0341] S807, the first ADMF sends a second request to the second agent.

[0342] For example, the first ADMF can send a second request to a second agent through the second ADMF. When there are multiple agents as the second agent, the first ADMF can send a message (the second request) to the second ADMF, which includes the identifiers of the multiple agents. The second ADMF receives the message and can obtain the identifiers of the multiple agents. The second ADMF can then send the second request to each of these agents individually. In other words, the second ADMF sends multiple second requests, with each second request corresponding to one agent.

[0343] Alternatively, the first ADMF can send a second request to the second agent via the second ASMF. When there are multiple agents as the second agent, the first ADMF can send a message (the second request) to the second ASMF, which includes the identifiers of the multiple agents. The second ASMF receives this message and can obtain the identifiers of the multiple agents. The second ASMF can then send the second request to each of these agents individually. In other words, the second ASMF sends multiple second requests, with each second request corresponding to one agent. The second ASMF can forward the second request to the second agent via the second AAMF. Figure 8 Take this as an example.

[0344] Alternatively, the first ADMF can send a second request to the second agent through the second AAMF. When there are multiple agents as the second agent, the first ADMF can send a message (the second request) to the second AAMF, which includes the identifiers of the multiple agents. The second AAMF receives the message and can obtain the identifiers of the multiple agents. The second AAMF can then send the second request to each of these agents individually. In other words, the second AAMF sends multiple second requests, with each second request corresponding to one agent.

[0345] S808, the first ADMF sends a second request to the first agent.

[0346] If the first agent participates in the execution of the first task, the first ADMF will also send a second request to the first agent. The execution order of S808 and S807 is not restricted; for example, S808 can be executed before S807 or simultaneously with S807.

[0347] S809, the second agent sends a message to the second ASMF indicating that it is joining the first network.

[0348] In response to the second request, the second agent sends a message to the second ASMF requesting to join the first network. The second ASMF receives this message and sends a message to the second ADFF instructing the second agent to request to join the first network; this message includes the identifier of the first network. Furthermore, the second ASMF also provides the second agent with information for establishing a user plane session on the first network, such as the second agent's IP address in the first network and the user plane tunnel identifier used by the second agent in the first network.

[0349] S810, the first intelligent agent sends a message to the first ASMF indicating that it is joining the first network.

[0350] In response to the second request, the first agent sends a message to the first ASMF requesting to join the first network. Upon receiving this message, the first ASMF sends a message to the first ADFF instructing the second agent to request to join the first network; this message includes the identifier of the first network. Furthermore, the first ASMF also provides the first agent with information for establishing a user plane session on the first network, such as the first agent's IP address in the first network and the user plane tunnel identifier used by the first agent in the first network.

[0351] S811, Establish a user plane session for the first network.

[0352] The first ADFF receives a message instructing the first agent to request to join the first network. It can establish routing rules for each agent in the first network, allowing each agent to forward data packets based on these rules. Similarly, the second ADFF receives a message instructing the second agent to request to join the first network, and can establish routing rules for each agent in the first network. Each agent then forwards data packets based on these rules. Furthermore, a routing rule for the first network is established between the first and second ADFFs, allowing data packets between the first and second agents to be forwarded via the first and / or second ADFFs.

[0353] S812, the second intelligent agent and the first intelligent agent establish end-to-end communication.

[0354] The second agent joins the first network and establishes end-to-end communication with the first agent in the first network. For example, a second or third request may include application layer information, enabling negotiation of application layer protocol parameters between the second agent and agents in the first network, thereby achieving end-to-end communication between agents. For instance, the second agent obtains the communication protocol type and related parameters based on the application layer information, and forwards data packets in the first network based on these parameters. For example, when the application layer information includes parameters related to the DDS protocol (such as DomainID, SPDP / SEDP, etc.), the first and second agents can discover each other using SPDP / SEDP based on the Domain ID, and then establish related Topic subscription notification interactions. As another example, when the application layer information includes parameters related to the Agent Protocol (such as the Agent's URL), the first and second agents can establish HTTP requests to each other based on the URL, and interact with data packets based on these HTTP requests.

[0355] Specifically, the second agent can send a first data packet to the first agent via the second ADFF, the first data packet including the identifier of the first network. Based on the identifier of the first network included in the first data packet, the first agent can determine that the first data packet was sent within the first network.

[0356] based on Figure 8 The process shown can enable networking between intelligent agents in different network ranges.

[0357] In the embodiments provided above, the methods provided by the embodiments of this application are described using the execution of a first intelligent agent, a second intelligent agent, and a first network element as examples. In this application, each embodiment can be implemented independently or in combination based on certain inherent connections; in each embodiment, different implementation methods can be implemented in combination or independently. To achieve the functions in the methods provided by the embodiments of this application above, the steps executed by the intelligent agent can be implemented by the intelligent agent itself, or by a device entity including the intelligent agent, or by different functional entities constituting the intelligent agent. The steps executed by the first network element can be implemented by the first network element itself, or by different functional entities constituting the first network element. To achieve the functions in the methods provided by the embodiments of this application above, the intelligent agent and the first network element can include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or hardware structures plus software modules. Whether a particular function is executed in the form of hardware structures, software modules, or hardware structures plus software modules depends on the specific application and design constraints of the technical solution.

[0358] Based on the same inventive concept as the method embodiments, this application provides a communication device. The communication device used to implement the above method in the embodiments of this application is described below with reference to the accompanying drawings. The content above can be used in subsequent embodiments, and repeated content will not be repeated.

[0359] Figure 9 This is a schematic block diagram of a communication device 900 provided in an embodiment of this application. The communication device 900 can correspondingly implement the functions or steps implemented by the first network element in the various method embodiments described above. For example, the communication device 900 may be... Figure 1 The communication device 900 can be a DMF (Digital Microsystem Component); or, the communication device 900 can be a chip (system) within the DMF; or, the communication device 900 can be a software module of the DMF. Alternatively, the communication device 900 can correspondingly implement the functions or steps implemented by the second intelligent agent in the above-described method embodiments. For example, the communication device 900 can be... Figure 1The communication device 900 can be a chip (system) within an intelligent agent; or, the communication device 900 can be a software module of the intelligent agent. The communication device 900 may include a processing module 910 and a transceiver module 920. Optionally, it may also include a storage module for storing instructions (code or programs) and / or data. This storage module may be, for example, a memory. The processing module 910 and the transceiver module 920 may be coupled to the storage module. For example, the processing module 910 may read instructions (code or programs) and / or data from the storage module to implement a corresponding method. When the communication device 900 is a chip within an intelligent agent, the storage module may be an internal storage module within the chip, such as a register or cache. For example, the storage module may also be an external storage module within a terminal device, such as a read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, such as random access memory (RAM). The aforementioned units may be independently configured or partially or completely integrated.

[0360] Processing module 910 may be a processor or controller, such as a CPU, general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. Transceiver module 920 is a transceiver, interface circuit, bus, pin, or other possible communication interface for receiving signals from other devices. For example, when the device is implemented as a chip, transceiver module 920 is an interface circuit for the chip to receive signals from other chips or devices, or an interface circuit for the chip to send signals to other chips or devices.

[0361] In one implementation, the communication device 900 can correspondingly implement the behavior and function of the first network element in the above method embodiments. The communication device 900 can be the first network element, a component (e.g., a chip or circuit) within the first network element, a part of a chip or chipset within the first network element used to execute the relevant method function, or a software module within the first network element capable of implementing the above communication method; there are no limitations. For details, please refer to the relevant content of the foregoing method embodiments, which will not be repeated here.

[0362] For example, the transceiver module 920 is used to receive a first request from a first intelligent agent, and in response to the first request, to send a second request to a second intelligent agent. The first request is used to request the creation of a first network, which is a mobile communication network. The second request is used to request the second intelligent agent to join the first network.

[0363] As an optional implementation, the first request includes the identifier of the second agent.

[0364] As an optional implementation, the processing module 910 is also used to determine the second agent.

[0365] As an optional implementation, the first request includes first information. The processing module 910 is used to determine a second intelligent agent based on the first information. Wherein, when the first information includes a communication protocol type, the second intelligent agent supports that communication protocol type. When the first information includes requirement information for a first task, the second intelligent agent satisfies the requirement indicated by that requirement information, wherein the first network is used for the execution of the first task. When the first information includes capability information of the intelligent agent, the capabilities of the second intelligent agent match the capabilities indicated by that capability information. When the first information includes information about an intelligent agent discovery method, the second intelligent agent supports being discovered using that intelligent agent discovery method.

[0366] As an optional implementation, the processing module 910 is also used to create the first network.

[0367] As an optional implementation, the processing module 910 is specifically used to: create a first network when a first condition is met. The first condition includes at least one of the following: a first intelligent agent has the authority to request network creation; a second intelligent agent has the authority to join the network; or a second intelligent agent has the authority to communicate with intelligent agents in the network.

[0368] As an optional implementation, processing module 910 is specifically used to: create a first network element when at least M agents accept joining the first network, where M is a positive integer. In this case, the first network element sending a second request to the second agents includes the first network sending a second request to the at least M agents.

[0369] As an optional implementation, before the first network element creates the first network, the transceiver module 920 is also used to receive second information from at least M agents, which is used to indicate acceptance to join the first network.

[0370] As an optional implementation, the first request includes M.

[0371] As an optional implementation, the processing module 910 is specifically used to: create a first network when the agents joining the first network include agents indicating first attribute information. The transceiver module 920 is specifically used to send a second request to the agents that have received the first attribute information indication among the agents joining the first network.

[0372] As an optional implementation, before the first network element creates the first network, the transceiver module 920 is further configured to receive second information from at least N agents, the second information being used to indicate acceptance of joining the first network, the N agents including the agents indicated by the first attribute information, where N is a positive integer.

[0373] As an optional implementation, the first request includes first attribute information.

[0374] As an optional implementation, before receiving the second information, the transceiver module 920 is further configured to send at least one of the following information: communication protocol type, agent capability information, agent discovery method information, or first task requirement information, wherein the first network is used for the execution of the first task. This at least one piece of information can be used to determine whether to accept joining the first network.

[0375] As an optional implementation, the transceiver module 920 is specifically used to: send at least one piece of information when the first network is a temporary network.

[0376] As an optional implementation, the transceiver module 920 is specifically used to: send a second request to the second intelligent agent through the second network element, wherein the second network element serves the second intelligent agent and the first network element serves the first intelligent agent.

[0377] As an optional implementation, the transceiver module 920 is also used to send a fifth request to a third agent, the fifth request including the identifier of the first network, the fifth request being used to request the third agent to leave the first network.

[0378] As an optional implementation, the transceiver module 920 is also configured to receive a fourth request before sending a fifth request to the third agent, the fourth request being used to request the third agent to leave the first network.

[0379] As an optional implementation, the processing module 910 is further configured to: release the first network when a second condition is met, wherein the second condition includes at least one of the following: the agent indicated by the second attribute information in the first network leaves the first network, all agents in the first network leave the first network, the transmission rate in the first network is less than or equal to a first threshold, or the first task is completed, wherein the first network is used for the execution of the first task.

[0380] As an optional implementation, the processing module 910 is specifically used to: delete the context information associated with the first network when the first network is a temporary network.

[0381] As an optional implementation, the processing module 910 is specifically used to allocate at least one of the following resources to the first network: control plane resources, user plane resources, data plane resources, or computing resources. The types of resources mentioned above are merely examples.

[0382] As an optional implementation, the second request may include a NAS message or a PUSH message.

[0383] As an optional implementation, the second agent supports the NAS protocol and the second request is a NAS message; or, the second agent does not support the NAS protocol and the second request is a PUSH message; or, the second agent supports the NAS protocol but the NAS message is unreachable and the second request is a PUSH message.

[0384] In one implementation, the communication device 900 can correspondingly implement the behavior and functions of the second intelligent agent in the above method embodiments. The communication device 900 can be an intelligent agent, a component (e.g., a chip or circuit) within the intelligent agent, a part of a chip or chipset within the intelligent agent used to execute related method functions, or a software module in the second intelligent agent capable of implementing the above communication method; there are no limitations. For details, please refer to the relevant content of the foregoing method embodiments, which will not be repeated here.

[0385] For example, the transceiver module 920 is used to receive a second request from a first network element, and in response to the second request, sends a message indicating joining the first network to send the identifier of the first network to a third network element. The second request includes the identifier of the first network and is used to request the second agent to join the first network. The third network element is used for forwarding data packets between the second agent and other agents in the first network, and these data packets include the identifier of the first network.

[0386] As an optional implementation, the transceiver module 920 is also used to: send a first data packet to an agent in the first network via a third network element, the first data packet including the identifier of the first network.

[0387] As an optional implementation, the second request includes a communication protocol type, and the transceiver module 920 is specifically used for: the second agent sending a first data packet to the agent in the first network through a third network element according to the communication protocol type.

[0388] As an optional implementation, before the second agent receives the second request from the first network element, the transceiver module 920 is also used to send information to the first network element indicating acceptance of joining the first network.

[0389] As an optional implementation, the transceiver module 920 is also used to receive a third request from the first network element. In this scenario, the transceiver module 920 sends information to the first network element indicating acceptance of joining the first network, including: when the third request includes a communication protocol type and the second intelligent agent supports the communication protocol type, the transceiver module 920 sends information to the first network element indicating acceptance of joining the first network; when the third request includes requirement information for a first task and the second intelligent agent meets the requirement indicated by the requirement information, the transceiver module 920 sends information to the first network element indicating acceptance of joining the first network, wherein the first network is used for the execution of the first task; when the third request includes capability information for an intelligent agent and the capability of the second intelligent agent matches the capability indicated by the capability information, the transceiver module 920 sends information to the first network element indicating acceptance of joining the first network; when the third request includes information on an intelligent agent discovery method and the second intelligent agent supports being discovered based on the intelligent agent discovery method, the transceiver module 920 sends information to the first network element indicating acceptance of joining the first network; when the third request includes the identifier of the first intelligent agent and the second intelligent agent has the permission to communicate with the first intelligent agent, the transceiver module 920 sends information to the first network element indicating acceptance of joining the first network.

[0390] When the communication device 900 is a chip-based device or circuit, the transceiver module can be an input / output circuit and / or a communication interface; the processing module is an integrated processor, microprocessor, or integrated circuit.

[0391] Figure 10 This is a schematic block diagram of a communication device 1000 provided in an embodiment of this application. The communication device 1000 can be a first network element or a second intelligent agent as described in the above embodiments. For example, the communication device 1000 can be... Figure 1 The DMF or the chip (system) within the DMF. For example, the communication device 1000 could be... Figure 1 The intelligent agent or the chip (system) within the intelligent agent. In the embodiments of this application, the chip system may be composed of chips or may include chips and other discrete devices. Specific functions can be found in the descriptions of the above method embodiments.

[0392] The communication device 1000 includes one or more processors 1001, used to implement or support the communication device 1000 in implementing the functions of the first network element or the second intelligent agent in the methods provided in the embodiments of this application. For details, please refer to the detailed description in the method examples, which will not be repeated here. The processor 1001 can also be called a processing unit or processing module, and can implement certain control functions to control the communication device 1000. The processor 1001 can be a general-purpose processor or a dedicated processor, etc. For example, it includes: a baseband processor, a central processing unit, an application processor, a modem processor, a graphics processor, an image signal processor, a digital signal processor, a video codec processor, a controller, a memory, and / or a neural network processor, etc. The baseband processor can be used to process communication protocols and communication data. The central processing unit can be used to control the communication device 1000 (e.g., a terminal device or a network device), execute software programs, and / or process data. Different processors can be independent devices or integrated into one or more processors, for example, integrated on one or more application-specific integrated circuits.

[0393] In one design, processor 1001 may include program 1003 (sometimes also referred to as code or instructions), which can be executed on processor 1001 to cause communication device 1000 to perform the methods described in the embodiments below. In yet another possible design, communication device 1000 includes circuitry (…). Figure 10 (Not shown), the circuit is used to implement the functions of the first network element or the second intelligent agent in the above embodiments.

[0394] In one design, the communication device 1000 may include one or more memories 1002 storing a program 1004 (sometimes referred to as code or instructions), which can be run on the processor 1001 to cause the communication device 1000 to perform the methods described in the above method embodiments.

[0395] In one design, the processor 1001 and / or memory 1002 may include an AI module for implementing AI-related functions. The AI ​​module may be implemented through software, hardware, or a combination of both. For example, the AI ​​module may include a RIC module. For instance, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0396] In one possible design, the processor 1001 and / or memory 1002 may also store data. The processor and memory may be configured separately or integrated together.

[0397] In one possible design, the communication device 1000 may further include a communication interface 1005. This communication interface 1005 may be a transceiver and / or antenna, or a circuit or pin, etc. The transceiver, sometimes also referred to as a transceiver unit, transceiver, transceiver circuit, or simply a transceiver, is used to implement the transmission and reception functions of the communication device 1000 via an antenna.

[0398] In one possible design, the communication device 1000 may further include one or more of the following components: a wireless communication module, an audio module, an external memory interface, internal memory, a universal serial bus (USB) interface, a power management module, an antenna, a speaker, a microphone, an input / output module, a sensor module, a motor, a camera, or a display screen, etc. It is understood that in some embodiments, the communication device 1000 may include more or fewer components, or some components may be integrated, or some components may be separated. These components may be implemented in hardware, software, or a combination of software and hardware.

[0399] The communication device in the above embodiments can be a network element or an intelligent agent, a circuit, or a chip or other combination device or component having the aforementioned terminal device or network device applied in the first network element or the second intelligent agent. When the communication device is an intelligent agent, the transceiver module can be a transceiver, which may include an antenna and radio frequency circuits, etc., and the processing module can be a processor, such as a CPU. When the communication device is a chip system, the communication device can be an FPGA, a dedicated ASIC, a SoC, a CPU, a network processor (NP), a DSP, a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips. The processing module can be the processor of the chip system. The transceiver module or communication interface can be the input / output interface or interface circuit of the chip system. For example, the interface circuit can be a code / data read / write interface circuit. The interface circuit can be used to receive code instructions (the code instructions are stored in memory and can be read directly from memory or through other devices) and transmit them to the processor; the processor can be used to run the code instructions to execute the method in the above method embodiments. For example, the interface circuit can also be a signal transmission interface circuit between the communication processor and the transceiver.

[0400] This application also provides a communication system, which includes a first intelligent agent and a first network element. The first intelligent agent is an intelligent agent used to implement the functions related to the first intelligent agent in the above embodiments, and the first network element is a network element used to implement the DMF-related functions in the above embodiments. Optionally, the communication system further includes a second intelligent agent, which is an intelligent agent used to implement the functions related to the second intelligent agent in the above embodiments.

[0401] This application also provides a computer-readable storage medium, including instructions that, when run on a computer, cause the method executed by the first network element or the second intelligent agent in the above-described communication method to be executed.

[0402] This application also provides a computer program product, including computer program code, which, when executed, causes the method executed by the first network element or the second intelligent agent in the above-described communication method to be executed.

[0403] This application provides a chip system including a processor and potentially a memory, for implementing the functions of the first network element or the second intelligent agent in the aforementioned communication method. The chip system can be composed of a chip or may include chips and other discrete components.

[0404] To achieve the above Figures 9-10 In addition to the functions of the communication device, this application also provides a chip, including a processor, for supporting the communication device in implementing the functions involved in the first network element or the second intelligent agent in the above method embodiments. In one possible design, the chip is connected to a memory or the chip includes a memory for storing the computer programs or instructions and data necessary for the communication device.

[0405] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0406] Those skilled in the art will recognize that the various illustrative logical blocks and steps 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 implementations should not be considered beyond the scope of this application.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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 essential contributing part of the technical solution of this application, 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, ROM, RAM, magnetic disks, or optical disks.

[0411] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A communication method, characterized in that, The method includes: Receive a first request from a first intelligent agent, the first request being used to request the creation of a first network, the first network being a mobile communication network; In response to the first request, a second request is sent to the second agent, the second request including the identifier of the first network, the second request being used to request the second agent to join the first network.

2. The method as described in claim 1, characterized in that, The first request includes the identifier of the second intelligent agent.

3. The method as described in claim 1 or 2, characterized in that, The method further includes: Identify the second intelligent agent.

4. The method as described in claim 3, characterized in that, The first request includes first information, and determining the second intelligent agent includes: The second intelligent agent is determined based on the first information; The first information includes a communication protocol type, and the second intelligent agent supports the communication protocol type. The first information includes the requirement information of the first task, and the second intelligent agent satisfies the requirement indicated by the requirement information, wherein the first network is used for the execution of the first task; The first information includes the capability information of the intelligent agent, and the capabilities of the second intelligent agent match the capabilities indicated by the capability information; The first information includes information about the agent discovery method, and the second agent supports being discovered through the agent discovery method.

5. The method according to any one of claims 1-4, characterized in that, Before sending the second request to the second agent, the method further includes: Create the first network.

6. The method as described in claim 5, characterized in that, Creating the first network includes: The first network is created if a first condition is met, wherein the first condition includes at least one of the following: The first intelligent agent has the authority to request the creation of a network; The second intelligent agent has the authority to join the network; or, The second intelligent agent has the authority to communicate with intelligent agents in the network.

7. The method as described in claim 5 or 6, characterized in that, The creation of the first network includes: creating the first network when at least M agents accept joining the first network, where M is a positive integer; Sending the second request to the second agent includes sending the second request to the at least M agents.

8. The method as described in claim 7, characterized in that, Prior to creating the first network, the method further includes: Receive second information from the at least M agents, the second information being used to indicate acceptance of joining the first network.

9. The method as described in claim 7 or 8, characterized in that, The first request includes the M.

10. The method according to any one of claims 5-9, characterized in that, The creation of the first network includes: creating the first network upon receiving an indication that the agents joining the first network include agents with first attribute information; Sending the second request to the second agent includes sending the second request to the agent that has accepted the indication of the first attribute information to join the first network.

11. The method as described in claim 10, characterized in that, Prior to creating the first network, the method further includes: Receive second information from at least N agents, the second information being used to indicate acceptance of joining the first network, the N agents including the agents indicated by the first attribute information, and N being a positive integer.

12. The method as described in claim 10 or 11, characterized in that, The first request includes the first attribute information.

13. The method as described in claim 8 or 11, characterized in that, Before receiving the second information, the method further includes: Send at least one of the following information: communication protocol type, agent capability information, agent discovery method information, or first task requirement information, wherein the first network is used for the execution of the first task, and the at least one piece of information is used to determine whether to accept joining the first network.

14. The method as described in claim 13, characterized in that, The sending of at least one of the following information includes: If the first network is a temporary network, the at least one piece of information is sent.

15. The method according to any one of claims 5-14, characterized in that, Creating the first network includes: The first network is allocated at least one of the following resources: control plane resources, user plane resources, data plane resources, or computing resources.

16. The method according to any one of claims 1-15, characterized in that, The method further includes: If a second condition is met, the first network is released, wherein the second condition includes at least one of the following: The agent indicated by the second attribute information leaves the first network; All agents in the first network leave the first network; The transmission rate in the first network is less than or equal to a first threshold; or, The first task is completed, wherein the first network is used for the execution of the first task.

17. The method as described in claim 16, characterized in that, The release of the first network includes: If the first network is a temporary network, delete the context information associated with the first network.

18. The method according to any one of claims 1-17, characterized in that, The second request may include non-access stratum messages or push messages.

19. The method as described in claim 18, characterized in that, The second intelligent agent supports non-access stratum protocols, and the second request is the non-access stratum message; The second intelligent agent does not support non-access layer protocols, and the second request is the push message; or, The second intelligent agent supports non-access stratum protocols, and the non-access stratum messages are unreachable; the second request is the push message.

20. A communication method, characterized in that, The method is applied to a second intelligent agent, and the method includes: Receive a second request, the second request including the identifier of the first network, the second request being used to request the second agent to join the first network; In response to the second request, a message indicating joining the first network is sent to send the identifier of the first network to a third network element, the third network element being used for data packet forwarding between the second agent and agents in the first network, the data packet including the identifier of the first network.

21. The method as described in claim 20, characterized in that, The method further includes: The third network element sends a first data packet to the intelligent agent in the first network, the first data packet including the identifier of the first network.

22. The method as described in claim 21, characterized in that, The second request includes a communication protocol type, and the sending of the first data packet to the agent in the first network through the third network element includes: According to the communication protocol type, the first data packet is sent to the intelligent agent in the first network through the third network element.

23. The method according to any one of claims 20-22, characterized in that, Before receiving the second request from the first network element, the method further includes: Send information to the first network element to indicate acceptance of joining the first network.

24. The method as described in claim 23, characterized in that, The method further includes: receiving a third request from the first network element, the third request including at least one of the following: communication protocol type, agent capability information, agent discovery method information, identifier of the first agent, or requirement information of the first task, wherein the first network is used for the execution of the first task; Sending information to the first network element to indicate acceptance of joining the first network includes: When the third request includes a communication protocol type and the second agent supports the communication protocol type, it sends information to the first network element to indicate acceptance of joining the first network. When the third request includes the requirement information of the first task, and the second intelligent agent meets the requirement indicated by the requirement information, it sends information to the first network element to indicate acceptance of joining the first network. When the third request includes the capability information of the agent, and the capability of the second agent matches the capability indicated by the capability information, information indicating acceptance to join the first network element is sent to the first network element. When the third request includes information about the agent discovery method, the second agent supports sending information to the first network element to indicate acceptance of joining the first network when it is discovered based on the agent discovery method. When the third request includes the identifier of the first agent and the second agent has permission to communicate with the first agent, information indicating acceptance of joining the first network is sent to the first network element.

25. A communication system, characterized in that, The system includes a first network element and a first intelligent agent, wherein the first network element is used to execute the method as described in any one of claims 1-19, and the first intelligent agent is used to request the first network element to create a first network.

26. The system as described in claim 25, characterized in that, The system further includes a second agent for performing the method as described in any one of claims 20-24.

27. A communication device, characterized in that, The communication device includes a module for performing the method as described in any one of claims 1-19, or includes a module for performing the method as described in any one of claims 20-24.

28. A communication device, characterized in that, The communication device includes at least one processor, the at least one processor being configured to cause the method of any one of claims 1-19 to be performed by the communication device, or the at least one processor being configured to cause the communication device to perform the method of any one of claims 20-24 to be performed by the communication device.

29. A chip or chip system, characterized in that, The chip or chip system includes: At least one processor and an interface, the at least one processor being configured to call and execute instructions from the interface, such that, when the at least one processor executes the instructions, the method as claimed in any one of claims 1-19 is executed, or the method as claimed in any one of claims 20-24 is executed.

30. A computer program product, characterized in that, The computer program product includes a computer program that, when run on a computer, causes the method as described in any one of claims 1-19 to be performed, or causes the method as described in any one of claims 20-24 to be performed.

Images