A communication method, apparatus and system

Abstract

This application provides a communication method, apparatus, and system. The method includes: a first intelligent agent acquiring information about at least one service, the information of which includes the service type to which each service belongs and information about at least one tool corresponding to each service; then receiving a discovery request from the first intelligent agent, the discovery request including a first service type; and finally sending a discovery response to the first intelligent agent, the discovery response including information about at least one tool corresponding to the first service. The at least one service includes the first service, and the first service type includes the service type to which the first service belongs. Using this method, signaling overhead can be reduced and service discovery efficiency improved while realizing the intent of the terminal device.

Description

Technical Field

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

[0002] In communication systems, a network repository function (NRF) is defined to handle the automated management of network functions (NFs) or network function services (NFS), including registration and discovery. For example, a discovery requester (e.g., an access and mobility management function (AMF)) can send a discovery request to the NRF with discovery request parameters (e.g., the target network function type is session management function (SMF), and the target service name is session service). The NRF then filters SMF instances that meet the discovery requirements from the registered NFs based on the discovery request parameters and returns the SMF instance information (e.g., SMF01 profile) to the discovery requester. In other words, the current NRF supports a service discovery mechanism at the single-network function granularity.

[0003] With the continuous development of artificial intelligence (AI) technology, AI models are being applied to mobile communication networks. For example, agents in mobile communication networks can use AI models to process tasks and realize the intentions of terminal devices. However, when an agent realizes the intentions of a terminal device, the network function services it supports may be multiple. For example, when an agent executes a connection service, it needs to discover AMF and SMF, which requires multiple rounds of discovery signaling interaction, resulting in long processing times and low discovery efficiency. Summary of the Invention

[0004] This application provides a communication method, apparatus, and system that can reduce signaling overhead and improve service discovery efficiency while realizing the intent of a terminal device.

[0005] Firstly, a communication method is provided. This method can be executed by a first network element in the network. Unless otherwise specified, the first network element in this application can refer to the first network element itself, or a component in the first network element (e.g., a processor, chip, or chip system, such as a circuit or chip in the first network element responsible for communication functions (e.g., a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core or a system-in-package (SIP) chip), or it can be a logic module or software that can implement all or part of the functions of the first network element.

[0006] In this method, a first network element acquires information about at least one service, the information of which includes the service type to which each service belongs and information about at least one tool corresponding to each service; receives a discovery request from a first intelligent agent, the discovery request including a first service type; and sends a discovery response to the first intelligent agent, the discovery response including information about at least one tool corresponding to the first service, the at least one service including the first service, and the first service type including the service type to which the first service belongs.

[0007] For example, the services in this application can be understood as: network function (NF) in the current network, or a service within a network function (also known as NFS), or a sub-function within a network function, etc. The services in this application can be alternatively described as: network service, or atomic service, or network atomic service, or network function service, or atomic function service, etc., without limitation on their specific names. For example, a service may include at least one of the following: connection service, session service, computing power service, sensing service, or other services, etc.

[0008] For example, the first network element can be a service repository or a service storage node. In this application, the first network element supports functions such as service registration, service discovery, and storage of service information.

[0009] For example, the first intelligent agent can be a service agent from a different service domain, supporting the invocation of local or remote models for task orchestration and the output of task orchestration results. For instance, the first intelligent agent may include a computational intelligent agent, a connectivity intelligent agent, or a perception intelligent agent.

[0010] Using the above method, the first network element can obtain information about at least one service for subsequent service discovery by the first intelligent agent. Furthermore, by receiving a discovery request from the first intelligent agent, the first network element can discover information about services that meet the discovery request from at least one service. For example, the first network element can discover information about a first service belonging to a first service type, such as information about at least one tool corresponding to the first service, and send this information to the first intelligent agent. This facilitates the first intelligent agent's subsequent task orchestration based on this tool, improving the accuracy and effectiveness of task orchestration, thereby realizing the intent of the terminal device and meeting its business needs. Considering that the first intelligent agent may support multiple network functions corresponding to the services it supports during the realization of the terminal device's intent—for example, the first intelligent agent needs to discover AMF and SMF when performing connection services—this means that the first intelligent agent needs to perform multiple network function discovery signaling interactions. In contrast, in this application, the first network element obtains information about at least one service, or in other words, the first network element can store information about at least one service at the service granularity, so that the first intelligent agent can request the first network element to discover the information of the first service based on the first service type. That is, the first intelligent agent can realize the intention of the terminal device by calling at least one tool corresponding to the first service. In this method, the first intelligent agent does not need to perform multi-round discovery signaling interaction for network functions, which can reduce signaling overhead and improve service discovery efficiency.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, at least one service further includes a second service, and obtaining information about at least one service includes: obtaining first information and second information, wherein the first information includes information about the service type to which the first service belongs and information about at least one tool corresponding to the first service, and the second information includes information about the service type to which the second service belongs and information about at least one tool corresponding to the second service.

[0012] The above method provides an implementation for a first network element to obtain information about at least one service. That is, the first network element can obtain information about the first service and information about the second service by obtaining first information and second information, which helps the intelligent agent to discover the first service and / or the second service in the future.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, obtaining information about at least one service includes: receiving a first registration request from a second network element, the first registration request including information about at least one service supported by the second network element.

[0014] For example, the second network element can be an atomic service. An atomic service can be understood as a network function in the current network, or a service or sub-function within a network function, or a microservice in the field of information technology (IT), etc., and its form of expression is not limited.

[0015] The above method provides an implementation for the first network element to obtain information about at least one service. That is, the first network element can obtain information about at least one service supported by the second network element by receiving a first registration request from the second network element, which helps the intelligent agent to discover the at least one service in the future.

[0016] Optionally, the first network element may send a first registration response to the second network element, which indicates that at least one service has been successfully registered. In other words, the first network element acquires and stores information about the at least one service for subsequent service discovery.

[0017] In conjunction with the first aspect, in some implementations of the first aspect, at least one service further includes a second service, and the first registration request includes a first information element and a second information element. The first information element includes information about the service type to which the first service belongs and information about at least one tool corresponding to the first service, and the second information element includes information about the service type to which the second service belongs and information about at least one tool corresponding to the second service.

[0018] It should be noted that at least one service may include one or more services, and the service types of these one or more services may be the same or different, without limitation. For example, at least one service includes service #1, and the service type of service #1 is service type #1 (e.g., connection service type); optionally, at least one service also includes service #2 and service #3, where service #2 belongs to service type #2 (e.g., computing power service type), and service #3 belongs to service type #1. This indicates that service #1 and service #2 belong to different service types, while service #1 and service #3 belong to the same service type.

[0019] The above method provides an implementation for a first network element to obtain information about at least one service. That is, the first network element can obtain a first information element and a second information element by obtaining a first registration request, and then obtain information about the first service and the second service. In other words, information about different services can be carried in different information elements of the first registration request, which helps the intelligent agent to discover the first service and / or the second service in the future.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: in response to the first registration request, storing information of at least one service.

[0021] Using the above method, after receiving the first registration request, the first network element can store at least one service information, indicating that at least one service supported by the second network element has been successfully registered or completed, facilitating service discovery by the intelligent agent in the future. It is understood that the technical solution of this application stores information at the service level, compared to the existing solution which stores information at the network function level. This implementation eliminates the need for multiple rounds of discovery signaling interaction when realizing the intent of the terminal device, reducing signaling overhead and improving service discovery efficiency.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining the information of the first service and the information of at least one tool corresponding to the first service based on the information of at least one service and the first service type.

[0023] In conjunction with the first aspect, in some implementations of the first aspect, determining the information of the first service and the information of at least one tool corresponding to the first service based on the information of at least one service and the first service type includes: when the service type to which the first service belongs belongs to the service type to which at least one service belongs, determining the information of the first service and the information of at least one tool corresponding to the first service from the information of at least one service.

[0024] It is understandable that the service type to which the first service belongs in at least one service is the first service type, or in other words, the service type to which at least one service belongs contains the first service type.

[0025] Using the above method, the first network element can select a first service that meets the discovery request and its corresponding at least one tool from at least one registered service stored locally, based on the first service type to which the service discovered by the second network element belongs. This facilitates the first intelligent agent to perform task orchestration based on at least one tool to realize the intent of the terminal device and meet the business needs of the terminal device.

[0026] Optionally, if at least one service belongs to a service type that does not include the first service type, the first network element cannot provide discovery services to the second network element, that is, it cannot provide feedback to the second network element on the information of the first service belonging to the first service type. Optionally, the first network element may send a reason value to the second network element to indicate that the service belonging to the first service type is not registered, and / or that the first network element has not stored information on the service belonging to the first service type.

[0027] In conjunction with the first aspect, in some implementations of the first aspect, the information of at least one service also includes the service identifier of each service in at least one service.

[0028] Using the above method, when the first network element obtains at least one service information, it can also obtain the service type to which each service belongs, the information of at least one tool corresponding to each service, and the service identifier of each service. Furthermore, when the first intelligent agent initiates a discovery request, it can carry the first service type and / or the first service identifier. It is understood that the first service identifier indicates that the first service belongs to the first service type, which facilitates the subsequent intelligent agent to perform effective and rapid service discovery.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: receiving a subscription request from a first intelligent agent, the subscription request including a first service type; and, based on the subscription request, sending updated information of one or more services belonging to the first service type to the first intelligent agent in the event of an update to the information of one or more services.

[0030] Using the above method, the first network element, based on the received subscription request, can promptly update the service information to the first intelligent agent when the information of a service belonging to the first service type changes. For example, the information of the first service belonging to the first service type may change, such as an increase or decrease in the number of callable tools corresponding to the first service; or, for example, other services belonging to the first service type (e.g., service #a) may go online and complete registration, meaning the first network element locally stores the information of #a. Therefore, the first network element can send the information of the first service and / or the information of service #a to the first intelligent agent, enabling the first intelligent agent to promptly obtain valid information of one or more services belonging to the first service type. This facilitates the first intelligent agent's subsequent task orchestration based on at least one updated tool, improving the accuracy and effectiveness of task orchestration, thereby realizing the intent of the terminal device and meeting the business needs of the terminal device.

[0031] Secondly, a communication method is provided. This method can be executed by a second network element. Unless otherwise specified, the second network element in this application can refer to the second network element itself, or a component within the second network element (e.g., a processor, chip, or chip system, such as a circuit or chip in the second network element responsible for communication functions (e.g., a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), or a logic module or software capable of implementing all or part of the functions of the second network element.

[0032] In this method, a first registration request is sent to a first network element. The first registration request includes information about at least one service supported by the second network element. The information about the at least one service includes the service type to which each service belongs and information about at least one tool corresponding to each service.

[0033] Using the above method, the second network element can register information about at least one service it supports with the first network element, so that other intelligent agents can obtain information about one or more services from at least one service through the first network element, which helps to realize service discovery.

[0034] Optionally, the second network element may receive a first registration response from the first network element, which is used to indicate that at least one service has been successfully registered.

[0035] In conjunction with the second aspect, in some implementations of the second aspect, at least one service includes a first service and a second service, the first registration request includes a first information element and a second information element, the first information element includes information about the service type to which the first service belongs and information about at least one tool corresponding to the first service, and the second information element includes information about the service type to which the second service belongs and information about at least one tool corresponding to the second service.

[0036] The beneficial effects of the second aspect and some implementations thereof can be referred to the relevant descriptions in the first aspect, and will not be repeated here.

[0037] Thirdly, a communication method is provided. This method can be executed by a first intelligent agent. Unless otherwise specified, the first intelligent agent in this application can refer to the first intelligent agent itself, or a component of the first intelligent agent (e.g., a processor, chip, or chip system, such as a circuit or chip in the first intelligent agent responsible for communication functions (e.g., a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), or a logic module or software that can implement all or part of the functions of the first intelligent agent.

[0038] In this method, a discovery request is sent to a first network element, the discovery request including a first service type; a discovery response is received from the first network element, the discovery response including information about at least one tool corresponding to the first service, the at least one service including the first service, and the first service type including the service type to which the first service belongs.

[0039] Using the above method, the first intelligent agent can discover information about a first service belonging to a first service type from the first network element by sending a discovery request. This information might include at least one tool corresponding to the first service. This facilitates subsequent task orchestration by the first intelligent agent based on at least one tool, improving the accuracy and effectiveness of task orchestration and ultimately realizing the intent of the terminal device and meeting its business needs. However, considering that the first intelligent agent may support multiple network functions corresponding to its services in realizing the terminal device's intent—for example, the first intelligent agent needs to discover AMF and SMF when performing connection services—this means the first intelligent agent needs to perform multiple rounds of network function discovery signaling interactions. In contrast, in this application, the first intelligent agent can request information about the first service from the first network element based on the first service type. That is, the first intelligent agent can then realize the terminal device's intent by calling at least one tool corresponding to the first service. This method eliminates the need for multiple rounds of network function discovery signaling interactions, reducing signaling overhead and improving service discovery efficiency.

[0040] In conjunction with the third aspect, in some implementations of the third aspect, the method further includes: receiving an orchestration request from a second agent, the orchestration request being used to request orchestration of a first task; orchestrating the first task according to at least one tool corresponding to the first service, obtaining an orchestration result of the first task, the orchestration result being used to invoke the first service to execute the first task; and sending the orchestration result of the first task to the second agent.

[0041] Using the above method, after receiving a task orchestration request from the second intelligent agent, the first intelligent agent uses at least one tool obtained from the first network element to perform task orchestration, obtains the task orchestration result, and sends the task orchestration result to the second intelligent agent. In this implementation, the first and second intelligent agents complete the orchestration of the first task through efficient cooperation, which helps the second intelligent agent to schedule network services to execute the first task, thereby realizing the intent of the terminal device.

[0042] In conjunction with the third aspect, in some implementations of the third aspect, the method further includes: sending a second registration request to a third network element, the second registration request including information of the first intelligent agent, the information of the first intelligent agent including information of at least one tool corresponding to the first service.

[0043] Using the above method, the first intelligent agent registers its own information with the third network element, so that other intelligent agents (e.g., the second intelligent agent) can obtain the first intelligent agent's information through the third network element, which helps to realize the discovery between intelligent agents. For example, the intelligent agent registration management module of the third network element can store the first intelligent agent's information in the third network element's intelligent agent information database for the discovery of other intelligent agents.

[0044] In conjunction with the third aspect, in some implementations of the third aspect, the method further includes: sending a subscription request to the first network element, the subscription request including a first service type; and receiving updated information from the first network element about one or more services belonging to the first service type.

[0045] In conjunction with the third aspect, in some implementations of the third aspect, the method further includes: sending an update request to a third network element, the update request being used to update the information of the first intelligent agent, the update request including information of at least one service after the update.

[0046] Using the above method, when the first intelligent agent obtains updated information about one or more services belonging to the first service type, it can reconstruct the information of the first intelligent agent, that is, update the information of the services supported by the first intelligent agent, and then send an update request to the third network element, so that the third network element stores the updated information of the first intelligent agent, which facilitates the effective discovery by other intelligent agents (e.g., the second intelligent agent).

[0047] The beneficial effects of the third aspect and some implementations thereof can be referred to the relevant descriptions in the first aspect, and will not be repeated here.

[0048] Fourthly, a communication method is provided. In this method, a first network element obtains information about at least one service, the information of which includes the service type to which each service belongs and information about at least one tool corresponding to each service; a first intelligent agent sends a discovery request to the first network element, the discovery request including a first service type; the first network element receives the discovery request from the first intelligent agent and then sends a discovery response to the first intelligent agent, the discovery response including information about at least one tool corresponding to the first service, the at least one service including the first service, and the first service type including the service type to which the first service belongs.

[0049] In conjunction with the fourth aspect, in some implementations of the fourth aspect, obtaining information about at least one service includes: the second network element sending a first registration request message to the first network element, the first registration request including information about at least one service supported by the second network element; and the first network element receiving the first registration request from the second network element.

[0050] In conjunction with the fourth aspect, in some implementations of the fourth aspect, at least one service further includes a second service, and the first registration request includes a first information element and a second information element. The first information element includes information about the service type to which the first service belongs and information about at least one tool corresponding to the first service, and the second information element includes information about the service type to which the second service belongs and information about at least one tool corresponding to the second service.

[0051] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the method further includes: in response to the first registration request, the first network element stores information about at least one service.

[0052] In conjunction with the fourth aspect, in some implementations of the fourth aspect, at least one service further includes a second service, and the first network element obtains information about at least one service, including: the first network element obtains first information and second information, the information of the first service includes the service type to which the first service belongs and information about at least one tool corresponding to the first service, and the information of the second service includes the service type to which the second service belongs and information about at least one tool corresponding to the second service.

[0053] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the method further includes: the first network element determining the information of the first service and the information of at least one tool corresponding to the first service based on the information of at least one service and the first service type.

[0054] In conjunction with the fourth aspect, in certain implementations of the fourth aspect, the first network element determines the information of the first service and at least one tool corresponding to the first service based on information of at least one service and the first service type, including:

[0055] If the service type to which the first service belongs belongs to the service type to which at least one service belongs, the first network element determines the information of the first service and the information of at least one tool corresponding to the first service from the information of at least one service.

[0056] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the information of at least one service also includes the service identifier of each service in at least one service.

[0057] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the method further includes: a first intelligent agent sending a subscription request to a first network element, the subscription request including a first service type; the first network element receiving the subscription request from the first intelligent agent, and according to the subscription request, sending updated information of one or more services belonging to the first service type to the first intelligent agent if the information is updated; the first intelligent agent receiving the updated information of one or more services from the first network element.

[0058] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the method further includes: a second intelligent agent sending an orchestration request to a first intelligent agent, the orchestration request being used to request orchestration of a first task; the first intelligent agent receiving the orchestration request from the second intelligent agent; the first intelligent agent orchestrating the first task according to at least one tool corresponding to the first service, obtaining an orchestration result for the first task, the orchestration result being used to invoke the first service to execute the first task; the first intelligent agent sending the orchestration result of the first task to the second intelligent agent; and the second intelligent agent receiving the orchestration result of the first task from the first intelligent agent.

[0059] In conjunction with the fourth aspect, in some implementations of the fourth aspect, the method further includes: the first intelligent agent sending a second registration request to the third network element, the second registration request including information of the first intelligent agent, the information of the first intelligent agent including information of at least one tool corresponding to the first service; the third network element receiving the second registration request from the first intelligent agent and storing the information of the first intelligent agent.

[0060] The beneficial effects of the fourth aspect and some implementations thereof can be referred to the relevant descriptions of the first to third aspects, and will not be repeated here.

[0061] Fifthly, a communication device is provided. This communication device is used to execute the methods described in the first aspect and any implementation thereof. For example, the communication device includes modules, units, or means corresponding to the operations involved in the first aspect. These modules, units, or means can be implemented in software, hardware, or a combination of software and hardware.

[0062] In one possible design, the communication device includes: a processing unit for acquiring information about at least one service, the information of which includes the service type to which each service belongs and information about at least one tool corresponding to each service; a communication unit for receiving a discovery request from a first agent, the discovery request including a first service type; and the communication unit further for sending a discovery response to the first agent, the discovery response including information about at least one tool corresponding to the first service, the at least one service including the first service, and the first service type including the service type to which the first service belongs.

[0063] The communication unit can perform the receiving and transmitting processes described in the first aspect above, and the processing unit can perform other processes described in the first aspect above besides receiving and transmitting.

[0064] The aforementioned communication device may be a first network element, or a communication module in the first network element, or a chip in the first network element responsible for communication functions, such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a logical node, logical module, or software that can realize all or part of the functions of the first network element.

[0065] Sixthly, a communication device is provided. This communication device is used to execute the methods described in the second aspect and any implementation thereof. For example, the communication device includes modules, units, or means corresponding to the operations involved in the second aspect. These modules, units, or means can be implemented in software, hardware, or a combination of software and hardware.

[0066] In one possible design, the communication device includes: a communication unit for sending a first registration request to a first network element, the first registration request including information on at least one service supported by the second network element, the information on the at least one service including the service type to which each service belongs and information on at least one tool corresponding to each service.

[0067] The communication unit can perform the receiving and transmitting processes described in the second aspect above, and the processing unit can perform other processes described in the second aspect above besides receiving and transmitting.

[0068] The aforementioned communication device may be a second network element, or a communication module in a second network element, or a chip in a second network element that is responsible for communication functions, such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a logical node, logical module or software that can realize all or part of the functions of the second network element.

[0069] In a seventh aspect, a communication device is provided. This communication device is used to execute the methods of the third aspect and any implementation thereof. For example, the communication device includes modules, units, or means corresponding to the operations involved in the third aspect. These modules, units, or means can be implemented in software, hardware, or a combination of software and hardware.

[0070] In one possible design, the communication device includes: a communication unit for sending a discovery request to a first network element, the discovery request including a first service type; and receiving a discovery response from the first network element, the discovery response including information about at least one tool corresponding to the first service, the at least one service including the first service, and the first service type including the service type to which the first service belongs.

[0071] The communication unit can perform the receiving and transmitting processes described in the third aspect above, and the processing unit can perform other processes described in the third aspect above besides receiving and transmitting.

[0072] The aforementioned communication device may be a first intelligent agent, or a communication module in the first intelligent agent, or a chip in the first intelligent agent responsible for communication functions, such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a logical node, logical module or software that can realize all or part of the functions of the first intelligent agent.

[0073] Eighthly, a communication device is provided. The communication device includes at least one processor. The at least one processor is capable of executing a computer program or instructions, which, when executed, cause the communication device to implement the methods of any one of the first to third aspects and any implementation thereof.

[0074] In one possible design, the communication device may further include at least one interface circuit. This interface circuit is used to implement communication functions within the communication device and / or communication functions between the communication device and other devices or components.

[0075] In one possible design, the communication device may further include at least one interface circuit and / or at least one memory. The at least one processor is coupled to the at least one memory. The at least one memory is used to store part or all of the necessary computer programs or instructions for implementing the functions involved in any of the first to third aspects and any implementation thereof. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0076] In one possible design, the at least one processor is used to communicate with other devices or components via at least one interface circuit.

[0077] The aforementioned communication device may be a first network element, or a communication module in the first network element, or a chip in the first network element responsible for communication functions, or a logic node, logic module, or software that can realize all or part of the functions of the first network element.

[0078] The aforementioned communication device may be a second network element, or a communication module in a second network element, or a chip in a second network element responsible for communication functions, or a logic node, logic module, or software that can realize all or part of the functions of the second network element.

[0079] The aforementioned communication device may be a first intelligent agent, or a communication module in the first intelligent agent, or a chip in the first intelligent agent responsible for communication functions, or a logic node, logic module, or software that can realize all or part of the functions of the first intelligent agent.

[0080] Ninthly, a communication system is provided. This communication system includes at least one of the communication devices described in the fifth to seventh aspects.

[0081] A tenth aspect provides a chip or chip system. The chip or chip system includes at least one processing circuitry for executing a computer program or instructions, causing the chip or chip system to perform the methods described in the first to third aspects and any possible implementation thereof.

[0082] The chip or chip system may include output circuits or interfaces for transmitting information or data, and input circuits or interfaces for receiving information or data.

[0083] Eleventhly, a computer-readable storage medium is provided. This computer-readable storage medium stores computer program code or instructions, and when a processor executes the computer program code or instructions, the methods of the first to third aspects and any possible implementation thereof are implemented.

[0084] In a twelfth aspect, a computer program product is provided. The computer program product includes computer program code or instructions, wherein when a processor executes the computer program code or instructions, the method in any of the possible implementations of the first to third aspects is implemented.

[0085] In a thirteenth aspect, a computer program is provided. When the computer program is run, it causes the methods of the first to third aspects and any possible implementation thereof to be implemented.

[0086] It should be understood that the beneficial effects of aspects five through thirteen above can be referenced from aspects one through three above and any possible implementation thereof, and will not be elaborated here. Attached Figure Description

[0087] Figure 1 and Figure 2 This is a schematic diagram of a communication system applicable to embodiments of this application;

[0088] Figure 3 This diagram illustrates the structure of an intelligent agent.

[0089] Figure 4 This diagram illustrates a process where an AMF requests the NRF to discover an SMF.

[0090] Figure 5 This is a schematic diagram of a communication system applicable to embodiments of this application;

[0091] Figure 6 This is a schematic diagram illustrating the process by which the second network element requests registration from the first network element based on the service type.

[0092] Figure 7 This is a schematic diagram illustrating the service discovery process completed by the first network element based on service type;

[0093] Figure 8 This is a schematic diagram of the process by which the first intelligent agent requests registration from the third network element;

[0094] Figure 9 It is a flowchart illustrating the process by which the first intelligent agent orchestrates tasks based on available tools;

[0095] Figures 10 to 14 This is a flowchart illustrating the communication method provided in an embodiment of this application;

[0096] Figure 15 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0097] Figure 16 This is a schematic diagram of another communication device provided in an embodiment of this application;

[0098] Figure 17 This is a schematic diagram of the chip system provided in the embodiments of this application. Detailed Implementation

[0099] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0100] Before introducing the scheme of this application, the following points should be noted.

[0101] First, in this application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0102] Second, in this application, "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 and B can be singular or plural. In the textual description of this application, the character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "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 c can mean: a, or, b, or, c, or, a and b, or, a and c, or, b and c, or, a, b, and c. Here, a, b, and c can each be single or multiple.

[0103] Third, in this application, the terms "first," "second," "#1," and "#2," as well as various numerical designations, are used for ease of description and are not intended to limit the scope of the embodiments of this application. For example, they are used to distinguish different messages, rather than to describe a specific order or sequence. It should be understood that such descriptions can be interchanged where appropriate to describe solutions other than those in the embodiments of this application.

[0104] Fourth, in this application, "instruction" or "for instruction" can include both direct and indirect instruction. When describing instruction information as being used to instruct A, it can include whether the instruction information directly or indirectly instructs A, but does not necessarily mean that the instruction information carries A.

[0105] The indication methods involved in the embodiments of this application should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated. The information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately. Moreover, the sending period and / or sending time of these sub-information can be the same or different. This application does not limit the sending method, for example.

[0106] The "instruction information" in the embodiments of this application can be an explicit instruction, that is, a direct instruction through signaling, or an instruction obtained by combining other rules or parameters with the parameters indicated by the signaling, or by deduction. It can also be an implicit instruction, that is, an instruction obtained based on rules or relationships, or based on other parameters, or by deduction. This application does not specifically limit it in this regard.

[0107] Fifth, in this application, "protocol" can refer to a standard protocol in the field of communications, such as fifth-generation (5G) protocols. th This application does not limit the scope of network protocols such as generation (5G), New Radio (NR) protocols, and related protocols applied in future communication systems. "Predefined" may include predefined terms, such as protocol definitions. "Preconfiguration" can be achieved by pre-storing corresponding codes, tables, or other means of indicating relevant information in the device; this application does not limit the implementation method.

[0108] Sixth, in this application, terms such as "message," "information," "signal," or "information element (IE, which may be abbreviated as information element)" can be used interchangeably. There is no limitation on the name of the message or information, as long as it can achieve the corresponding function.

[0109] "Sending information to XX (device)" can be understood as the destination of the information being that device. This can include sending information to that device directly or indirectly. "Receiving information from XX (device), or receiving information from XX (device)" can be understood as the source of the information being that device. This can include receiving information from that device directly or indirectly. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly, and will not be elaborated further here.

[0110] "Communication" can also be described as data transmission, information transmission, data processing, etc. "Transmission" includes sending and / or receiving. "Transmission" can be described as output. "Sending" can also be understood as the output of a chip interface, and "receiving" can be understood as the input of a chip interface. In other words, "sending" or "receiving" can occur between devices, for example, device 1 and device 2 sending or receiving data via an air interface. "Sending" or "receiving" can also occur within a device, for example, sending or receiving data between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0111] For example, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logic module within a device sending information to another logic module. For instance, "device 1 sending information" can be understood as device 1 sending information to device 2, or it can be understood as logic module 1 within device 1 sending information to logic module 2 within device 1. Similarly, "receiving information" can be understood as device 1 receiving information from device 2, or it can also be understood as logic module 1 within device 1 receiving information from logic module 2. For instance, "device 1 receiving information" can be understood as device 1 receiving information from device 2, or it can be understood as logic module 1 within device 1 receiving information from logic module 2 within device 1.

[0112] Seventh, in this application, the words "exemplarily," "for example," etc., are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as an "example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the word "example" is intended to present concepts in a concrete manner. In the embodiments of this application, "of," "corresponding, relevant," "corresponding," and "associate" may sometimes be used interchangeably, and it should be noted that their intended meanings are consistent unless their distinctions are emphasized.

[0113] The following describes the communication system to which this application applies.

[0114] The technical solutions of this application can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, 5G systems, New Radio (NR) systems, and future communication systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems.

[0115] In a communication system, a device can send signals to or receive signals from another device. These signals may include reference signals, information, signaling, or data. In this application, "device" can be replaced by an entity, network entity, communication equipment, communication module, node, or communication node.

[0116] Figure 1 This is a schematic diagram of a communication system applicable to an embodiment of this application. For example... Figure 1 As shown, the communication system 100 includes at least one terminal (such as...) Figure 1 The 120a-120j, collectively referred to as 120, comprise the radio access network (RAN) and core network (CN) 200. The RAN includes at least one RAN node (e.g., ...). Figure 1 110a and 110b in the RAN are collectively referred to as 110. The RAN may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices. Figure 1 (Not shown in the image). Terminal 120 is connected to RAN node 110 wirelessly. RAN node 110 is connected to core network 200 wirelessly or via wired connection. The core network equipment in core network 200 and RAN node 110 in RAN can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0117] RAN can be used for the third-generation partner program (3 rdCellular systems related to the Generation Partnership Project (3GPP), such as fourth-generation (4G) cellular systems. th RAN can be a generation (4G) mobile communication system, a 5G mobile communication system, or a future-oriented evolution system. RAN can also be an open radio access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN can also be a communication system that integrates two or more of the above systems.

[0118] RAN node 110, sometimes also referred to as network equipment, access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in communication system 100 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative, for example... Figure 1 Network element 120i can be a helicopter or a drone, and it can be configured as a mobile base station. For terminals 120j that access the RAN through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes referred to as communication devices, for example... Figure 1 Network elements 110a and 110b can be understood as communication devices with base station functions, while network elements 120a-120j can be understood as communication devices with terminal functions.

[0119] In one possible scenario, a RAN node can be a base station (BS), an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a base station in a future mobile communication system, or an access node in a WiFi system, etc. Figure 1 110a), micro base stations or indoor stations (such as Figure 1 In V2X technology, the access network equipment can be a roadside unit (RSU), such as a relay node or donor node (110b), or a radio controller in a CRAN scenario. Alternatively, the RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in V2X technology can be a roadside unit (RSU).

[0120] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be central units (CU), distributed units (DU), CU-control plane (CU-CP), CU-user plane (CU-UP), radio units (RU), or CU-radio units (CU-RU), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radioheads (RRHs).

[0121] In different systems, CU (including open CU-CP (O-CU-CP) and open CU-UP (O-CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called an open central unit (O-CU), DU can also be called an open distributed unit (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. Any of the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0122] Terminal 120 can be a device or module that accesses the aforementioned communication system and has corresponding communication functions. A terminal can also be referred to as user equipment (UE), terminal device, user apparatus, access terminal, user unit, user station, mobile station, mobile station (MS), remote station, remote terminal, mobile device, user terminal, terminal unit, terminal station, terminal apparatus, wireless communication equipment, user agent, or user apparatus. A terminal typically contains a communication module, circuit, or chip that performs the corresponding communication functions. The terminal may also be configured with program instructions for performing these communication functions.

[0123] For example, the terminal in this application embodiment can be a mobile phone, a personal digital assistant (PDA) computer, a laptop computer, a tablet computer, a drone, a computer with wireless transceiver capabilities, an MTC terminal, a virtual reality (VR) terminal, an augmented reality (AR) terminal, an IoT terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home (such as game consoles, smart TVs, smart speakers, smart refrigerators, and fitness equipment), a transportation vehicle with wireless communication capabilities, a communication module, or an RSU with terminal functionality.

[0124] The RAN and terminal 120 can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenario in which the RAN and terminal 120 are located.

[0125] Communication between access network devices and terminal devices follows a specific protocol layer structure. This protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: radio resource control (RRC) layer, packet data convergence protocol (PDCP) layer, radio link control (RLC) layer, media / medium access control (MAC) layer, or physical (PHY) layer, etc. The user plane protocol layer may include at least one of the following: service data adaptation protocol (SDAP) layer, PDCP layer, RLC layer, MAC layer, or physical layer, etc.

[0126] The correspondence between network elements and their achievable protocol layer functions in the ORAN system can be found in Table 1 below.

[0127] Table 1

[0128] ORAN network elements 3GPP protocol layer functions O-CU-CP RRC+PDCP-Control Plane (PDCP-C) O-CU-UP SDAP+PDCP - User Plane (PDCP-U) O-DU RLC+MAC+PHY-high O-RU PHY-low

[0129] CN 200 can be a 5G core network or an evolved 5G core network. Taking a 5G core network as an example, CN 200 includes Access and Mobility Management (AMF) network elements responsible for mobility management and access management services; Session Management Function (SMF) network elements responsible for session management; User Plane Function (UPF) network elements responsible for user plane packet routing and forwarding and quality of service (QoS) control; and Policy Control Function (PCF) network elements. These core network elements can operate independently or be combined to implement certain control functions; for example, AMF, SMF, and PCF can be combined into a single core network device.

[0130] The communication system 100 provided in this application may further include AI network elements for implementing some or all AI-related operations. AI network elements may also be referred to as AI nodes, AI devices, AI entities, AI modules, AI models, or AI units, etc. The AI ​​network elements may be built into the network elements of the communication system. For example, an AI network element may be an AI module built into: access network equipment, core network equipment, cloud server, or operation administration and maintenance (OAM) to implement AI-related functions. The OAM may act as the network management system for core network equipment and / or access network equipment. Alternatively, the AI ​​network element may also be an independently configured network element in the communication system. Optionally, the terminal or its built-in chip may also include an AI entity for implementing AI-related functions.

[0131] Figure 2 This is a schematic diagram of a communication system applicable to an embodiment of this application. For example... Figure 2 As shown, network elements in a communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in the OAM, are equipped with one or more AI modules (for clarity, ...). Figure 2 (Only one is shown in the image). The access network node can be a single RAN node or can include multiple RAN nodes, such as CU and DU. The CU and / or DU can also be configured with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are configured in CU-CP and / or CU-UP.

[0132] The AI ​​module is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0133] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0134] It should be understood that the above naming is defined solely for the purpose of distinguishing different functions and should not be construed as limiting this application. This application does not preclude the possibility of using other naming conventions in 5G networks and other future networks. For example, in future networks, some or all of the above-mentioned network elements may use the terminology from 5G, or they may use other names, etc.

[0135] Understandable. Figure 1 or Figure 2 This is merely an example and does not constitute a limitation on the scope of protection of this application. The communication method provided in the embodiments of this application may also involve... Figure 1 or Figure 2 The network elements not shown in the diagram may also include, of course, the communication method provided in this application embodiment. Figure 1 or Figure 2 Some of the network elements are shown.

[0136] To facilitate understanding of the embodiments of this application, the basic concepts involved in this application will be explained first.

[0137] 1. AI: AI enables machines to possess human-like intelligence, for example, allowing machines to use computer hardware and software to simulate certain intelligent human behaviors. To achieve artificial intelligence, machine learning methods can be employed. In machine learning, machines learn (or train) models using training data. This model represents the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result).

[0138] 2. Intelligent Agent: This is a concept in the field of artificial intelligence. Any entity capable of independent thought and interaction with its environment can be abstracted as an intelligent agent. In essence, an intelligent agent is a type of AI module. The basic characteristics of an intelligent agent are: it can react to changes in its environment and automatically adjust its behavior and state; different intelligent agents can also interact with other intelligent agents according to their own intentions.

[0139] For example, an intelligent agent can use a large language model (LLM) as its core, which includes a memory module, a tool module, a planning module, and an action module. The memory module implements long-term and / or short-term memory functions; the tool module contains multiple callable external tools; the planning module contains various planning algorithms; for example, the agent can plan external input tasks based on its memory; and the action module supports the agent in performing actions based on the planning results, such as calling up tools.

[0140] Figure 3 A schematic diagram of the structure of an intelligent agent is shown. For example... Figure 3 As shown, in an LLM-supported autonomous agent system, the LLM acts as the brain of the agent (or agent) and includes the following components.

[0141] (1) Planning.

[0142] The planning includes self-reflection, self-criticism, chain of thoughts, and subgoal decomposition.

[0143] Sub-goal decomposition: Agents break down large tasks into smaller, manageable sub-goals (or sub-tasks), enabling them to efficiently handle complex tasks. For example, by instructing the model to "think step by step" through a chain of thoughts (CoT), more testing time is used to compute the breakdown of difficult tasks into smaller, simpler steps. CoT transforms large tasks into multiple manageable tasks and elucidates the explanation of the model's thought process.

[0144] Reflection and Improvement: Intelligent agents can engage in self-criticism and self-reflection on past behaviors, learn from mistakes, and improve future steps, thereby enhancing the quality of the final result.

[0145] (2) Memory.

[0146] Short-term memory: Learning by utilizing the short-term memory of models.

[0147] Long-term memory: Provides agents with the ability to retain and recall (unlimited) information for a long time, usually by utilizing external vector storage and fast retrieval.

[0148] (3) Tools usage.

[0149] Agent learning calls external application programming interfaces (APIs) to obtain additional information missing from the model weights (which is usually difficult to change after pre-training), including current information, code execution capabilities, and access to proprietary information sources.

[0150] For example, tools include, but are not limited to: calendars, calculators, code interpreters, or search tools.

[0151] (4) Task execution (action): The model executes a specific task and records the results.

[0152] In this application, an intelligent agent can generally be considered as a proxy that can autonomously complete a set goal through action. "Intelligent agent" and "intelligence" are inseparable; it possesses some human-like intelligent abilities and behaviors, such as learning, reasoning, decision-making, and execution capabilities. Optionally, the intelligent agent can be replaced with other terms, such as artificial general intelligence (AGI), artificial intelligence, AI controller, intelligent unit, intelligent entity, or intelligent agent, etc. This application does not limit the name of the intelligent agent, as long as it can achieve the corresponding function.

[0153] In this application, the intelligent agent can be integrated into the existing hardware / software of the communication device, or the intelligent agent can be independent of the existing hardware / software of the communication device. The existing hardware / software may include at least one of the following: a chip, a baseband chip, a modem chip, a SoC chip containing a modem core, a SIP chip, a communication module, a chip system, a processor, a logic module, or software, etc.

[0154] The above description of the terminology is for ease of understanding only and does not limit the scope of protection of the embodiments of this application.

[0155] Currently, communication systems define Network Memory Function (NRF) to handle the automated management of Network Memory (NF) or Network Storage Service (NFS), including registration and discovery. Below, we will discuss this in conjunction with... Figure 4 This document provides an example illustrating the techniques used by the AMF to request the NRF to discover the SMF.

[0156] Figure 4 This diagram illustrates a process where an AMF requests the NRF to discover an SMF. Figure 4 As shown, it includes the following steps.

[0157] Step 1: The discovery requester (e.g., AMF) sends a discovery request to the NRF with discovery request parameters.

[0158] The discovery request parameters include at least one of the following: target network function type (e.g., SMF), target service name (e.g., Nsmf PDUSession), or requester plmn list (e.g., public land mobile network (PLMN), such as PLMN1).

[0159] In other words, the AMF requests the NRF to discover the SMF. The discovery requirements include: the SMF supports session services and the network where the SMF is located is PLMN1. In other words, the SMF supports PLMN1. That is, the AMF requests the NRF to discover an SMF located in PLMN1 that supports sessions.

[0160] Step 2: The NRF selects a service provider (e.g., an SMF instance) that meets the discovery requirements from one or more registered SMFs based on the discovery request parameters.

[0161] For example, assume that the NRF stores three SMF instances, such as SMF01, SMF02, and SMF03. SMF01 supports both session services and event open services, and is located in PLMN3; therefore, it does not match the requester PLMN list. SMF02 supports event open services and is located in PLMN1; therefore, it does not match the target service name. SMF03 supports session services and is located in PLMN1; therefore, SMF03 meets the AMF discovery requirements.

[0162] Step 3: NRF returns SMF03 information (e.g., SMF03 profile) to AMF.

[0163] Based on this, the current NRF supports service discovery mechanisms at the single-network-function granularity. Due to the continuous advancement of AI technology, AI models are being applied to mobile communication networks. This means that agents in mobile communication networks can use AI models to process tasks and realize the intentions of terminal devices. For example, when an agent realizes the intentions of a terminal device, the network functions corresponding to the services it supports may be multiple. For instance, when an agent executes a connection service, it needs to discover AMF and SMF, thus requiring multiple rounds of discovery signaling interaction, which is time-consuming and inefficient.

[0164] In view of this, this application provides a communication method and a communication device that can reduce signaling overhead and improve service discovery efficiency while realizing the intention of the terminal device.

[0165] To facilitate understanding of the technical solution of this application, the following is combined with... Figures 5 to 9The following examples illustrate the network architecture applicable to the embodiments of this application: a second network element (e.g., an atomic service) initiates a service registration process with a first network element (e.g., a service repository) based on a service type; the first network element supports a service discovery process initiated by a first agent based on a service type; after the first agent (e.g., a service agent) requests information about a first service belonging to the first service type from the second network element, it constructs its own information (e.g., a service agent profile) and initiates an agent registration process with a third network element (e.g., an agent repository); the second agent (e.g., a system agent, sys-agent) initiates a task orchestration request to the first agent; and the first agent requests the first network element to discover available tools and uses them to complete task orchestration.

[0166] Figure 5 This is a schematic diagram of a communication system applicable to embodiments of this application. For example... Figure 5 As shown in (a), an AI mobile network architecture for multi-agent collaboration is proposed. This architecture may include agents, third network elements (e.g., agent repository), and fourth network elements (e.g., task-centric function (TCF)). The agents in this application include second agents (e.g., sys-agent) and first agents (e.g., service agent).

[0167] Optionally, the architecture may also include at least one of the following: a message bus (e.g., an agent message bus) or a terminal device.

[0168] For example, the first intelligent agent may include agents from different service domains, such as a connection agent, a computation agent, or a perception agent. The first intelligent agent receives task orchestration requests from the second intelligent agent, supports calling large local or remote models for task orchestration, and outputs the task orchestration results. As an example, the first intelligent agent includes functional modules such as... Figure 5As shown in (b). The task orchestration module receives task orchestration requests from the second agent and utilizes the AI ​​model and knowledge base of this service domain for reasoning and task orchestration to obtain the orchestration results. The agent topology management module manages the topology of local agents, providing functions such as agent selection, agent discovery, agent registration, and deregistration. The agent connection management module implements the underlying transmission connection management and state maintenance for information interaction and communication among multiple agents.

[0169] For example, the second intelligent agent supports understanding the intent of the terminal device using a large model, decomposing the intent into tasks (e.g., a first task) in one or more service domains (e.g., a perception service domain, a computing power service domain, or a session service domain), and then invoking the intelligent agent in each of the one or more service domains to orchestrate the tasks in that service domain. Optionally, the second intelligent agent can decompose the intent of the terminal device into network function requirements of one or more service domains, and then determine the tasks for that service domain based on the network function requirements of each service domain. Optionally, the second intelligent agent can also schedule network services based on the task orchestration results (e.g., the orchestration results of the first task) to complete the task execution. For example, the second intelligent agent can generate orchestration instructions that can be recognized by network elements (e.g., a fourth network element) based on the task orchestration results, and then issue the orchestration instructions to the fourth network element to trigger the execution of the task. As an example, the functional modules included by the second intelligent agent are as follows: Figure 5 As shown in (c). The network task management module organizes the first and second agents into a task intelligent orchestration work group, and enables intelligent orchestration collaboration of a specific task among the group agents to obtain instructions that drive the fourth network element to perform service scheduling and execution. The agent topology management module manages the topology of local agents, providing functions such as agent selection, agent discovery, agent registration, and deregistration. The task orchestration codec module encodes the output of the network task management module, generates instructions that the fourth network element can understand and recognize, and calls the fourth network element interface to issue instructions to the fourth network element for scheduling services to execute tasks. The agent connection management module implements the underlying transmission connection management and state maintenance for information interaction and communication among multiple agents. The underlying transmission protocol can be Transmission Control Protocol (TCP), Hypertext Transfer Protocol (HTTP), or other protocols, without limitation.

[0170] For example, the third network element supports automatic online deployment of agents within the network, capability registration, and inter-agent discovery. As an example, the functional modules included in the third network element are as follows: Figure 5As shown in (d). The agent registration management provides agent registration and / or deregistration interfaces. When an agent goes online, it can call the registration interface to report its information to the third-party network element, such as at least one of the following: agent identifier, capabilities, roles, open interfaces, supported protocols, or location information. When an agent goes offline, it can call the deregistration interface to request the deletion of its information from the third-party network element. The agent discovery management provides a discovery interface. An agent (e.g., a sys-agent) can call the discovery interface to discover service agents in a specific service domain. The input information for the discovery interface can be at least one of the agent's capabilities, roles, or location information. The agent information database stores agent information and provides interfaces for adding, deleting, and modifying information for agent registration and discovery. Optionally, the third-party network element can also be called an agent repository, agent storage node, or agent information storage network element, etc.

[0171] For example, a message bus can be viewed as a distributed message bus for collaboration and dialogue among multiple intelligent agents. In one implementation, the message bus can be coupled to an intelligent agent (e.g., a first or second intelligent agent), or in other words, the message bus can be embedded within the agent as an internal functional module. In this implementation, the second intelligent agent can directly send task orchestration requests to the first intelligent agent, thereby achieving rapid point-to-point communication among multiple intelligent agents. In another implementation, the message bus can be decoupled from an intelligent agent (e.g., a first or second intelligent agent), or in other words, the message bus can act as an independent routing node. In this implementation, the first intelligent agent can forward task orchestration requests to the second intelligent agent through the agent message bus. For example, after receiving a task orchestration request from the first intelligent agent, the message bus can perform rapid message routing and forwarding based on the identifier and / or address of the second intelligent agent, thereby improving efficient collaboration among multiple intelligent agents and ultimately realizing the intent of the terminal device. As an example, the message bus includes functional modules such as... Figure 5 As shown in (e). The agent routing module stores the relationship between agent identifiers and agent addresses, and routes and forwards messages based on the agent identifiers. The agent reachability management module stores the reachability status of agent addresses. If the agent address is reachable, the message can be routed; otherwise, message routing fails and an error code is returned. Agent reachability can be checked periodically. The agent connection management module manages the underlying transmission connections and maintains the state of information interaction and communication between multiple agents.

[0172] Optionally, the agent connection management module in the first and / or second agent can be connected to the agent message bus to realize functions such as routing management, status reporting, and message reception and forwarding.

[0173] For example, the fourth network element supports receiving task instructions from the second intelligent agent, scheduling network services to execute tasks, and realizing the intent of the terminal device. The services involved in this application can be understood as: NF in the current network, or a service within an NF, or a sub-function within an NF, etc. The services in this application can be described as: network service, or atomic service, or network atomic service, or network function service, or atomic function service, or network atomic function service, or other services, as long as they can provide a service interface for the fourth network element to perform scheduling.

[0174] For example, the services in this application may include at least one of the following: access service, session service, computing power service, perception service, or other services.

[0175] For example, the terminal device can act as a mobile terminal requesting services. In one possible implementation, the terminal device can send its intent, such as requesting computing resources, to a second intelligent agent or a fourth network element.

[0176] in addition, Figure 5 The network architecture shown may also include a first network element and a second network element (not shown in the figure).

[0177] For example, the first network element can be a service repository or a service storage node. In this application, the first network element supports functions such as service registration, service discovery, and storage of service information. Optionally, the first network element can also be referred to as a service repository, service storage node, or service information storage network element, etc.

[0178] For example, the second network element can be an atomic service. An atomic service can be understood as a network function in the current network, or a service or sub-function within a network function, or a microservice in the IT field, etc., and its form of expression is not limited.

[0179] As one implementation approach, the first intelligent agent, second intelligent agent, first network element, second network element, third network element, or fourth network element in the above network architecture can be deployed independently as independent network elements. Additionally, the message bus can also be deployed independently as an independent network element, such as as an intelligent agent message router, or it can be deployed as a functional module within the system intelligent agent and / or service intelligent agent; there are no limitations on this.

[0180] It should be understood that the above Figure 5 The network element names shown in the network architecture are defined solely for the purpose of distinguishing different functions and do not constitute a limitation on this application. This application does not preclude the possibility of using other names for various network elements in mobile network architectures and other future networks, and makes no limitation in this regard.

[0181] Figure 6 This is a flowchart illustrating the process by which a second network element (e.g., an atomic service) requests registration from a first network element (e.g., a service repository) based on its service type. In other words, the second network element requests service registration from the first network element at the service level. Figure 6 As shown, it includes the following steps.

[0182] Step 1: The second network element classifies the services it supports according to the service type and constructs information (e.g., service profile) of at least one service based on the service type.

[0183] For example, each service profile includes the service type to which the service belongs (e.g., servicetype) and information about at least one tool corresponding to the service (e.g., tools profile list). Optionally, each service profile may also include the service identifier (e.g., service name) of the corresponding service.

[0184] It should be noted that at least one service may include one or more services, and the service types of these one or more services may be the same or different, without limitation. For example, at least one service includes service #1, and the service type of service #1 is service type #1 (e.g., connection service type); optionally, at least one service also includes service #2 and service #3, where service #2 belongs to service type #2 (e.g., computing power service type), and service #3 belongs to service type #1. This indicates that service #1 and service #2 belong to different service types, while service #1 and service #3 belong to the same service type.

[0185] In other words, the second network element can classify one or more services it supports according to different service types (e.g., service type) and then construct service information (e.g., service profile). In one possible example, the services supported by the second network element include connection service 1, connection service 2, and sensing service 3. Therefore, the second network element determines that the service type includes connection service type and sensing service type. Connection service 1 and connection service 2 belong to the connection service type, and sensing service 3 belongs to the sensing service type. The service information constructed by the first network element may include: the information for connection service 1 is service01 profile, the information for connection service 2 is service02 profile, and the information for sensing service 3 is service03 profile. The tools profile list included in service01 profile may include tool profile (tool 1) and tool profile (tool 2); the tools profile list included in service02 profile may include tool profile (tool 3) and tool profile (tool 4); and the tools profile list included in service03 profile may include tool profile (tool 4) and tool profile (tool 5). This is not limited.

[0186] For example, a tool profile includes at least one of the following: a callable tool type or a callable service interface type (e.g., tooltype), the mobile network range supported by the service (e.g., plmn list), the network slice service type supported by the service (e.g., single network slice selection assistance information (S-NSSAI)), or the capabilities supported by the service (e.g., supporting capabilities). The supported capabilities may include at least one of the following: whether it supports intermediate session management function (I-SMF), V2X, or proximity-based services (prose), etc.

[0187] Optionally, the plmn list and S-NSSAI in the tools profile list can be stored in the tool profile or in the service profile; there is no limitation on this.

[0188] Step 2: The second network element initiates a registration request to the first network element. The registration request includes information (e.g., service profile) of at least one service supported by the second network element.

[0189] For example, when the second network element goes online, or when the second network element provides services for the first time, the second network element sends a registration request to the first network element.

[0190] In one example, if the address information of the first network element is configured on the second network element, the second network element can initiate a registration request to the first network element based on the address of the first network element.

[0191] Optionally, for multiple service profiles supported by the second network element, the second network element may initiate one or more registration requests to the first network element, without limitation.

[0192] Step 3: The first network element receives a registration request from the second network element and saves information about at least one service (e.g., service profile). In other words, the first network element stores information about at least one service at the service level.

[0193] Step 4: Optionally, the first network element sends a registration response to the second network element to indicate that at least one service has been successfully registered. In other words, the first network element stores information about at least one service, i.e., stores a service profile.

[0194] Based on the above method, a second network element (e.g., an atomic service) can request service registration from a first network element (e.g., a service repository) based on the service type. The first network element stores information (e.g., a service profile) of at least one service supported by the second network element at the service level. It should be understood that the above... Figure 6 This is merely an example to facilitate understanding of the proposed solution; other solutions are not excluded.

[0195] Figure 7 This is a diagram illustrating the service discovery process initiated by a first network element (e.g., a service repository) and a first intelligent agent (e.g., a service agent, also known as a requesting agent) based on the service type (e.g., service type). Figure 7 As shown, it includes the following steps.

[0196] Step 1: The first intelligent agent sends a discovery request to the first network element, carrying discovery request parameters, which include service type (e.g., service type) and requester type (e.g., requester type), wherein the requester type (e.g., requester type) is optional.

[0197] Optionally, the discovery request parameters may also include a list of PLMNs supported by the requester, such as PLMN1, without limitation.

[0198] For example, in the discovery request parameters sent by the first intelligent agent to the first network element, the requester type is also the type of the first intelligent agent. The requester type can be a service intelligent agent (e.g., a service agent), and the service type can include connection service type and computing power service type.

[0199] Step 2: The first network element selects information about a service that meets the discovery requirements from the information of at least one service stored in the discovery request parameters based on the service type carried in the discovery request parameters, and sends a discovery response to the first intelligent agent, which carries information about the service that meets the discovery requirements.

[0200] In one example, assume that the first network element locally stores service01 profile, service02 profile, and service03 profile, where service01 belongs to the connection service type, service02 belongs to the computing power service type, and service03 belongs to the awareness service type. For specific implementation details, please refer to the above. Figure 6 The relevant descriptions will not be repeated here. Based on step 1 above, the service types requested by the first intelligent agent include connection service types and computing power service types. Then, the first network element can filter out the information of services that meet the discovery requirements based on the information of at least one service stored locally and the service types sent by the first intelligent agent, including: service01 profile and service02 profile.

[0201] Optionally, if the discovery request parameter in step 1 carries a requester type, the first network element can determine that the discovery requester is a service agent, which can be understood as a service discovery request. Then, based on the service type of the request, it can filter out the information of services that meet the discovery requirements from the information of at least one service stored locally.

[0202] For example, the service01 profile includes the service type to which service01 belongs (e.g., connection service type) and information about at least one tool corresponding to service01 (e.g., tools profile (tool 1) and tools profile (tool 2)), and the service02 profile includes the service type to which service02 belongs (e.g., computing power service type) and information about at least one tool corresponding to service02 (e.g., tools profile (tool 3) and tools profile (tool 4)).

[0203] Furthermore, based on the received service01 profile and service02 profile, the first intelligent agent can determine that the available services are service01 and service02. The information for at least one tool corresponding to service01 is tools profile (tool 1) and tools profile (tool 2), and the information for at least one tool corresponding to service02 is tools profile (tool 3) and tools profile (tool 4). That is, for service01, the tools that the first intelligent agent can invoke are tools 1 and tools 2; for service02, the tools that the first intelligent agent can invoke are tools 3 and tools 4. In other words, the first intelligent agent can invoke tools 1 and tools 2 to perform task orchestration related to service01, and can invoke tools 3 and tools 4 to perform task orchestration related to service02.

[0204] Based on the above method, the first intelligent agent (e.g., a service agent) can request information from the first network element (e.g., a service repository) based on the service type to discover available services and information on at least one tool corresponding to that service, for subsequent task orchestration to realize the intent of the terminal device. It should be understood that the above... Figure 7 This is merely an example to facilitate understanding of the proposed solution; other solutions are not excluded.

[0205] Figure 8This is a schematic diagram illustrating the process by which a first intelligent agent (e.g., a service agent) initiates a registration process with a third network element (e.g., an agent repository), a second intelligent agent (e.g., a system agent) requests information from the third network element to discover the first intelligent agent's information, and the process by which the first and second intelligent agents collaborate to achieve the intent of the terminal device. Figure 8 As shown, it includes the following steps.

[0206] Step 1: The intelligent agent (e.g., the first intelligent agent, the third intelligent agent, and the fourth intelligent agent) constructs the agent's information (e.g., agent profile) and initiates a registration request to the third network element, requesting to register the agent's information with the third network element.

[0207] For example, the agent's information may include information about at least one service supported by the agent (e.g., serviceInfo or serviceprofile). Optionally, the agent's information may also include the agent's identifier (ID) and / or the agent's type, as shown in the figure. For a detailed explanation of service profile, please refer to the above. Figure 6 The relevant descriptions will not be repeated here.

[0208] In one implementation, one or more intelligent agents (e.g., a first intelligent agent, a third intelligent agent, and a fourth intelligent agent) request information about one or more services belonging to a certain service type from a first network element (e.g., a service repository), then construct their own information and initiate a registration process with the third network element, which is beneficial for the discovery of other intelligent agents in the future.

[0209] Step 2: The terminal device sends its intent to the second intelligent agent, such as requesting computing resources;

[0210] Step 3: The second intelligent agent decomposes the intent of the terminal device to obtain tasks in multiple service domains, such as computing resource application task (corresponding to service01) and computing session creation task (corresponding to service02);

[0211] Step 4: The second agent requests the third network element to discover service agents that support the orchestration of tasks in multiple service domains. Based on the discovery request, the third network element filters service agents (e.g., the first agent) that meet the discovery requirements from the information of one or more agents (e.g., agent profiles) (e.g., including information of the first agent, the third agent, and the fourth agent).

[0212] For example, a third network element can match service information (serviceInfo or service profile) from the information of one or more intelligent agents stored in its database with the task description information (e.g., computing resource application task and computing session creation task) carried in the received discovery request, and then filter and feed back service agents that meet the discovery requirements to the second intelligent agent. For example, the information of the first intelligent agent can be determined from the information of the first intelligent agent that has already completed registration, the information of the second intelligent agent, and the information of the third intelligent agent, that is, the first intelligent agent supports the orchestration of computing resource application tasks and computing session creation tasks.

[0213] For example, the third network element can determine and feed back information of multiple agents that meet the discovery requirements (e.g., information of the first agent and information of the third agent) based on the service type (or PLMN and service type) contained in the information of the agents received in step 1. Then, the second agent matches the tools profile list carried in the information of the multiple agents with the task requirements corresponding to the multiple service domains obtained from the intent decomposition in step 2, thereby determining the information of the first agent, that is, the first agent supports the orchestration of computing resource application tasks and computing session creation tasks.

[0214] Step 5: The second agent sends a task orchestration request to the first agent, such as requesting to orchestrate the computing resource application task and the computing session creation task. The first agent calls the available tools in service01 profile to orchestrate the computing resource application task and the available tools in service02 profile to orchestrate the computing session creation task, and then feeds back the task orchestration results to the second agent.

[0215] Step 6: The second agent sends the task orchestration results to the fourth network element (e.g., TCF) to schedule network services to perform tasks in multiple different service domains.

[0216] Based on the above method, after the first intelligent agent requests network service (e.g., service01 and service02) synchronization from the first network element, it constructs its information and registers with the third network element. The second intelligent agent, after decomposing the terminal device's intent, obtains tasks for different service domains, corresponding to service01 and service02 respectively. It then requests the third network element to discover service agents supporting service01 and service02, i.e., obtains the first intelligent agent's information from the third network element. This allows the first intelligent agent to orchestrate tasks for different service domains to realize the terminal device's intent. It should be understood that the above... Figure 8 This is merely an example to facilitate understanding of the proposed solution; other solutions are not excluded.

[0217] Figure 9 This is a schematic diagram illustrating the process where a second intelligent agent (e.g., a system agent) requests a first intelligent agent (e.g., a service agent) to perform task orchestration, and the first intelligent agent completes the task orchestration based on at least one tool corresponding to the service. Figure 9 As shown, it includes the following steps.

[0218] Step 1: The terminal device sends its intent to the second intelligent agent, such as requesting computing resources;

[0219] Step 2: The second intelligent agent decomposes the intent of the terminal device to obtain tasks in multiple service domains, such as computing resource application task (corresponding to service01) and computing session creation task (corresponding to service02);

[0220] Step 3: The second agent sends a task orchestration request to the first agent to request the orchestration of tasks in multiple service domains, such as requesting the orchestration of computing resource application tasks and computing session creation tasks.

[0221] For example, the task orchestration request includes task description information for multiple service domains, and / or the output format of the task orchestration results.

[0222] Step 4: The first intelligent agent requests the first network element to discover the corresponding callable tools for task orchestration based on the task requirements. That is, it requests information on at least one tool corresponding to service01 and at least one tool corresponding to service02.

[0223] Correspondingly, the first network element sends the tools profiles corresponding to service01 and service02, such as tools profile list01 and tools profile list02, to the first intelligent agent, thereby allowing the first intelligent agent to determine at least one callable tool for each task. For example, the first intelligent agent can use a large language model for task orchestration; for instance, it can use tool 1 to orchestrate computing resource request tasks and tool 2 to orchestrate computing session creation tasks, thus obtaining the task orchestration results.

[0224] The model's input can be task description information from multiple service domains, and its output can be a task orchestration chain. It should be noted that the representation of the task description information and the task orchestration chain can be in natural language, structured format, semi-structured format, etc., without specific limitations.

[0225] Step 5: The first agent sends the task orchestration results to the second agent.

[0226] For example, the task orchestration result includes two steps. The service type corresponding to step one is service01, and the corresponding callable tools profile is tools profile(tool 1). The service type corresponding to step two is service02, and the corresponding callable tools profile is tools profile(tool 2), which is the task orchestration chain.

[0227] Step 6: The second agent sends the task orchestration results to the fourth network element (e.g., TCF) to schedule network services to perform tasks in multiple different service domains.

[0228] Based on the above method, the second intelligent agent can initiate a task orchestration request to the first intelligent agent after decomposing the intent of the terminal device. Correspondingly, the first intelligent agent requests information from the first network element to discover at least one callable tool based on the task requirements, and performs task orchestration based on the callable tool. It should be understood that the above... Figure 9 This is merely an example to facilitate understanding of the solution; other solutions are not excluded.

[0229] In summary, this application can be applied to AI-native network system architectures for multi-agent collaboration in mobile networks. The main application scenarios include, but are not limited to: a first agent synchronously discovering callable tools corresponding to its own service type and orchestrating a function scheduling chain; or, a first agent synchronously discovering callable tools corresponding to its own service type, constructing its information based on the callable tools, and initiating agent registration with a third network element; a second agent decomposing the terminal device's intent to obtain tasks in different service domains and requesting a third network element to discover service agents that meet the task requirements to complete task orchestration, etc.

[0230] Below, in conjunction with Figures 10 to 14The communication method provided in this application is illustrated and can be applied to the network architecture described above. This application uses a first intelligent agent (e.g., a service agent), a second network element (e.g., an atomic service), and a third network element (e.g., a service repository) as the execution entities for illustration. The execution entities, such as the first intelligent agent, the first network element, and the second network element, can be the device itself, or components within the device (e.g., processors, chips, or chip systems, such as circuits or chips responsible for communication functions within the device (e.g., modem chips, also known as baseband chips, or SoC chips or SIP chips containing modem cores)), or logic modules or software capable of implementing all or part of the functions.

[0231] Figure 10 This is a schematic flowchart of a communication method 1000 provided in an embodiment of this application. Figure 10 As shown, this document mainly describes the registration process for at least one service completed through signaling interaction between the first network element and the second network element, and the discovery process for information about the first service completed through signaling interaction between the first intelligent agent and the first network element. This method includes several steps; for details not covered herein, please refer to the above. Figures 6 to 9 For the sake of brevity, the relevant descriptions will not be repeated here.

[0232] S1010, the first network element obtains information about at least one service.

[0233] The information for at least one service includes the service type (e.g., service type) to which each service belongs and the information for at least one tool (e.g., toolsprofile list) corresponding to each service.

[0234] It should be noted that the "at least one service" may include one or more services, and the service types of these one or more services may be the same or different, without limitation. For example, the "at least one service" may include service #1, and the service type of service #1 is connection service. Optionally, the "at least one service" may also include service #2 and service #3, where service #2 is computing power service and service #3 is connection service. This indicates that service #1 and service #2 belong to different service types, while service #1 and service #3 belong to the same service type.

[0235] For example, suppose the information of at least one service obtained by the first network element includes service01 profile and service02 profile, where service01 belongs to the connection service type and service02 belongs to the computing power service type. The tools profile list corresponding to service01 includes toolprofile (tool 1) and tool profile (tool 2), and the tools profile list corresponding to service02 includes tool profile (tool 3) and tool profile (tool 4). The service01 profile and service02 profile can be seen in Tables 2 and 3 below. For the parameters included in the tool profile and their specific interpretations, please refer to the above. Figure 6 For the sake of brevity, the relevant descriptions are not explained here.

[0236] Table 2

[0237]

[0238] Table 3

[0239]

[0240] Optionally, the information for at least one service may also include a service identifier (e.g., service name) for each service within the at least one service. For example, the service01 profile may also include the service identifier of service01, representing the name of the service 01 instance under the connection service type, and the service02 profile may also include the service identifier of service02, representing the name of the service 02 instance under the computing power service type, without limitation.

[0241] The following is an example illustrating how the first network element obtains information about at least one service.

[0242] In the first implementation, assuming at least one service includes a first service (e.g., service01) and a second service (e.g., service02), the first network element obtains information about the at least one service by acquiring first information and second information. The first information includes information about the service type to which the first service belongs and information about at least one tool corresponding to the first service. The second information includes information about the service type to which the second service belongs and information about at least one tool corresponding to the second service. In other words, the first network element can obtain information about the first service (service01 profile) by acquiring the first information, such as information about the service type to which the first service belongs and information about at least one tool corresponding to the first service. Furthermore, the first network element can obtain information about the second service (service02 profile) by acquiring the second information, such as information about the service type to which the second service belongs and information about at least one tool corresponding to the second service.

[0243] In the second implementation, the first network element obtains information about at least one service, which can be achieved through the following step S1020. For specific implementation details or other aspects not covered herein, please refer to the above. Figure 6 Related descriptions.

[0244] S1020, the second network element (e.g., an atomic service) sends a first registration request to the first network element;

[0245] Correspondingly, the first network element receives the first registration request from the second network element.

[0246] The first registration request includes information about at least one service supported by the second network element. This information includes the service type of each service and information about at least one tool corresponding to each service. In other words, the second network element determines the service type of a service and the information of at least one corresponding tool based on the service type, and requests registration of at least one service from the first network element, facilitating the subsequent discovery of available services by the first intelligent agent. For example, the second network element constructs service profiles for registration based on the service type, such as service01 profile and service02 profile, as specifically explained in Tables 2 and 3 above. For simplicity, these will not be elaborated further here.

[0247] In one example, at least one service includes a first service and a second service, and the first registration request includes a first information element and a second information element. The first information element includes information about the service type to which the first service belongs and information about at least one tool corresponding to the first service. The second information element includes information about the service type to which the second service belongs and information about at least one tool corresponding to the second service.

[0248] The registration process initiated by the second network element can be found above. Figure 6 For the sake of brevity, the relevant descriptions are not repeated here. Furthermore, this application does not limit the message format of the first registration request, but it generally follows specific protocols and data structures to ensure correct information exchange between the first network element and the second network element. For example, the message format of the first registration request may include a request header and a request body. The request header contains the basic metadata of the first registration request (e.g., the address information of the first network element) to enable the second network element to correctly address and process the message. The request body carries the main content of the message (e.g., information on multiple services (service profiles) requested by the second network element for registration, such as service01 profile and service02 profile).

[0249] In one example, the message format of the first registration request can be as follows:

[0250]

[0251] It is understood that the message format of the first registration request provided above is only an example for ease of understanding, and other solutions are not excluded.

[0252] In one example, after receiving the first registration request, the first network element stores information about the at least one service, or in other words, the first network element updates its local storage record of service information, for example, by adding information about the at least one service.

[0253] Optionally, in response to the first registration request, the first network element may send a first registration response to the second network element to indicate that the at least one service has been successfully registered or the registration is complete, or in other words, to indicate that the first network element has stored the information of the at least one service.

[0254] Understandably, the specific implementation methods or parts not detailed in the following steps S1030-S1040 can be found above. Figure 7 Related descriptions.

[0255] S1030, the first intelligent agent sends a discovery request to the first network element;

[0256] Correspondingly, the first network element receives a discovery request from the first intelligent agent.

[0257] The discovery request includes the first service type.

[0258] For example, the first service type may include at least one of the following: connection service type, computing power service type, sensing service type, or other service type, without limitation. This application does not limit the number of services belonging to the first service type; for example, it may include one or more.

[0259] It should be noted that the service type requested by the first intelligent agent in this application may be the same as or partially the same as the service type of each of the at least one services obtained by the first network element in step S1010, and there is no limitation thereto. For example, the service type of the at least one service obtained in step S1010 may be a connection service type, and the first service type may be a connection service type; or, for another example, the service types of the at least one service obtained in step S1010 may include both connection service type and computing power service type, and the first service type may be a connection service type. Optionally, if the first service type does not belong to the service type of the at least one service, for example, if the service types of the at least one service include both connection service type and computing power service type, and the first service type is a perception service type, then subsequent steps do not need to be performed.

[0260] For example, based on the above step S1010, the information of at least one service obtained by the first network element includes service01 profile and service02 profile. Assuming that the services of the first service type requested by the first intelligent agent include service01 and / or service02, then the first service type requested by the first intelligent agent belongs to the service type to which at least one service belongs; or, the services of the first service type requested by the first intelligent agent include service01 and service03, then service01 requested by the first intelligent agent belongs to the service type to which at least one service belongs, and service03 requested by the first intelligent agent does not belong to the service type to which at least one service belongs.

[0261] Optionally, the discovery request may also include a requester type, such as the first agent being a service agent. For ease of description, the first service type and the requester type included in the discovery request can be collectively referred to as discovery request parameters, as detailed in Table 4 below.

[0262] Table 4

[0263]

[0264] As shown in Table 4, the discovery request parameters carried by the first intelligent agent include the requester type and the first service type. The requester type is a service agent, such as the first intelligent agent. The first service type includes service01 and service03. For example, service01 belongs to the connection service type, and service03 belongs to the perception service type.

[0265] S1040, the first network element sends a discovery response to the first intelligent agent;

[0266] Correspondingly, the first intelligent agent receives a discovery response from the first network element.

[0267] The discovery response includes information about at least one tool corresponding to the first service, the at least one service includes the first service, and the first service type includes the service type to which the first service belongs.

[0268] In one implementation, the first network element determines the information of the first service and at least one tool corresponding to the first service based on the information of at least one service and the first service type.

[0269] For example, when the service type to which the first service belongs is the same as the service type to which at least one service belongs, the first network element determines the information of the first service and at least one tool corresponding to the first service from the information of at least one service.

[0270] For example, based on the above step S1010, the information of at least one service may include service01 profile and service02 profile. As shown in Table 4, the first service type includes service01 and service03. Then the first network element determines that service01 belongs to the service type to which at least one service belongs, and service03 does not belong to the service type to which at least one service belongs. Then the first network element can feed back service01 profile, that is, the information of the first service, to the first intelligent agent.

[0271] The presentation of the first service information carried in the discovery response, such as information about the first service and at least one corresponding tool, is shown in Table 5 below.

[0272] Table 5

[0273]

[0274] As shown in Table 5, the information of the first service sent by the first network element to the first intelligent agent includes the information of the first service type and at least one corresponding tool. The first service is service01, and the information of the at least one corresponding tool includes tool profile (tool 1) and tool profile (tool 2). In other words, the available service supported by the first intelligent agent is service01, and the corresponding callable tools include tool 1 and tool 2.

[0275] Optionally, the first network element may send a cause value to the first intelligent agent to indicate that the first intelligent agent cannot obtain the service03 profile, or in other words, to indicate that the first network element has not stored the service03 profile. Optionally, this cause value may be carried in the discovery response, and there is no limitation thereto.

[0276] Based on this, the first intelligent agent can construct its own information (e.g., agent profile) based on the acquired first service (e.g., service01) and the information of at least one corresponding tool (e.g., tool profile (tool 1) and tool profile (tool 2)), and initiate a registration process with the third network element. Optionally, the method further includes the following steps S1001-S1002 (not shown in the figure), and the specific implementation or parts not detailed can be referred to the above. Figure 8 The relevant description of step 1.

[0277] S1001, the first intelligent agent sends a second registration request to the third network element;

[0278] Correspondingly, the third network element receives the second registration request from the first intelligent agent.

[0279] The second registration request includes information about the first intelligent agent, which includes information about at least one tool corresponding to the first service.

[0280] For example, the first intelligent agent constructs information about itself (e.g., agent profile) based on the information obtained about the first service and at least one corresponding tool. The representation of the agent profile can be seen in Table 6 below.

[0281] Table 6

[0282] property Description Identifier (ID) ××× Type service agent Service information (serviceInfo or service profile) {service type01, tools profile list01} … …

[0283] As shown in Table 6, the information of the first intelligent agent may include, but is not limited to: the identifier of the first intelligent agent, the type of the first intelligent agent, or the service information supported by the first intelligent agent. Specifically, the type of the first intelligent agent is a service intelligent agent (e.g., a service agent), and the service information includes {service type01, tools profile list01}, indicating that the first intelligent agent supports service type01 and its corresponding list of callable tools, toolsprofile list01.

[0284] S1002, Optionally, the third network element sends a second registration response to the first intelligent agent;

[0285] Correspondingly, the first intelligent agent receives a second registration response from the third network element, which indicates that the first intelligent agent has successfully registered or completed registration, or in other words, the third network element has stored the information of the first intelligent agent for subsequent discovery of other intelligent agents.

[0286] Based on the above implementation, the first intelligent agent can construct its information (e.g., agent profile) based on the information of the available first service (e.g., service01) and its corresponding at least one tool (e.g., tool profile (tool 1) and tool profile (tool 2)) and initiate a registration process with the third network element carrying the information of the first intelligent agent.

[0287] To obtain information about the service corresponding to the first service type and at least one corresponding tool in a timely manner, the first intelligent agent can initiate a subscription request to the first network element. That is, when the information of one or more services belonging to the first service type (i.e., the first service) stored by the first network element changes, the first network element can send the updated information of the first service to the first intelligent agent. Furthermore, the first intelligent agent can also reconstruct its own information based on the updated service information and then send the updated information of the first intelligent agent to the third network element to initiate an update registration process. Specifically, the method further includes the following steps S1003-S1005 (not shown in the figure).

[0288] S1003, the first intelligent agent sends a subscription request to the first network element, the subscription request including the first service type;

[0289] Correspondingly, the first network element receives a subscription request from the first intelligent agent;

[0290] For example, if the first service type includes service01 and service03, then the first intelligent agent requests to subscribe to the update information of service01 profile and service03 profile by sending a subscription request to the first network element.

[0291] S1004, the first network element sends the updated information of one or more services (i.e., the first service) to the first intelligent agent in accordance with the subscription request if the information of one or more services belonging to the first service type is updated.

[0292] Correspondingly, the first intelligent agent receives updated information about one or more services belonging to the first service type from the first network element.

[0293] Understandably, updating the information of one or more services belonging to the first service type refers to a change in the information of those one or more services. For example, it could be an increase in the number of services belonging to the first service type, such as service registration by other network elements, for example, other network elements initiating service registration with the first network element carrying the service03 profile; or it could be an update to the information of services already stored by the first network element, such as an increase or decrease in the number of callable tools corresponding to the one or more services already stored by the first network element, or a decrease in the number of the one or more services already stored by the first network element, etc., without limitation.

[0294] For example, based on the above steps S1030 and Table 4, the first service type requested by the first network element includes service01 and service03. When the service01 profile stored by the first network element changes (for example, the information of at least one tool corresponding to service01 is added to toolprofile (tool 3)), the first network element can synchronize the service01 information with the first intelligent agent. The updated service01 profile can be shown in Table 7 below. And / or, when other network elements initiate registration for the service03 profile with the first network element, the first network element can synchronize the service03 information with the first intelligent agent. The updated service03 profile can be shown in Table 8 below.

[0295] Table 7

[0296]

[0297] As shown in Table 7, service01 belongs to the connection service type. The descriptions of the tools that can be called include toolprofile (tool 1), toolprofile (tool 2) and tool profile (tool 3). Compared with the service01 profile shown in Table 2, a new available tool tool profile (tool 3) has been added.

[0298] Table 8

[0299]

[0300] As shown in Table 8, service03 belongs to the awareness service type. The descriptions of the corresponding callable tools include toolprofile (tool 1) and toolprofile (tool 4). For details on the parameters included in the tool profile and their specific interpretations, please refer to the above. Figure 6 For the sake of brevity, the relevant descriptions are not explained here.

[0301] Furthermore, the first intelligent agent can store updated information of multiple services (e.g., service01 and service03) belonging to the first service type (e.g., connection service type and perception service type). In other words, the first intelligent agent can update the information of at least one service stored in step S1010, such as adding an available tool profile (tool 3) corresponding to service01 and adding a profile for service03, thereby reconstructing the information (agentprofile) of the first intelligent agent.

[0302] S1005, the first intelligent agent sends an update request to the third network element;

[0303] Correspondingly, the third network element receives the update request from the first intelligent agent.

[0304] The update request is used to update the information of the first intelligent agent, and the update request includes the updated information of at least one service belonging to the first service type.

[0305] For example, the first agent reconstructs its information (agent profile) based on the acquired updated information of at least one service belonging to the first service type. The representation of the agent profile can be seen in Table 9 below.

[0306] Table 9

[0307]

[0308]

[0309] As shown in Table 9, the information of the first agent may include, but is not limited to: the identifier of the first agent, the type of the first agent, or the service information supported by the first agent. Compared with the agent profile shown in Table 6, the difference lies in the change of the service information supported by the first agent. For example, the tool list toolsprofile list01 corresponding to service type01 is updated from tool profile (tool 1) and tool profile (tool 2) to tool profile (tool 1), tool profile (tool 2), and tool profile (tool 3). In addition, the service information supported by the first agent is updated to {service type03, tools profile list03}, indicating that the first agent supports service type03 and its corresponding tool list tools profile list03 (e.g., including tool profile (tool 1) and tool profile (tool 4)).

[0310] Based on the above implementation, the second network element can initiate registration for at least one service with the first network element based on the service type. The first intelligent agent carries the first service type and initiates a service discovery process with the first network element to obtain information about the first service belonging to the first service type. Furthermore, the first intelligent agent can construct its own information after obtaining information about available services and at least one corresponding callable tool, and register its own information with the third network element so that other intelligent agents (e.g., the second intelligent agent) can obtain the information of the first intelligent agent through the third network element, which helps to realize discovery among multiple intelligent agents.

[0311] To realize the intent of the terminal device, the second intelligent agent (e.g., sys-agent) can, after obtaining the intent of the terminal device, decompose the intent into multiple sub-tasks (collectively referred to as the first task) in different service domains, and then request the first intelligent agent to orchestrate the first task. That is, the method also includes the following steps S1006-S1008 (not shown in the figure), and the specific implementation or other details can be found above. Figure 8 or Figure 9 Related descriptions.

[0312] S1006, the second agent sends an orchestration request to the first agent, the orchestration request being used to request the orchestration of the first task;

[0313] Correspondingly, the first agent receives an orchestration request from the second agent.

[0314] In one implementation, the second agent can send an orchestration request to the first agent via a message bus.

[0315] Optionally, before executing step S1006, the second intelligent agent can decompose the intent of the terminal device, and the resulting multiple sub-tasks correspond to service01 and service03 respectively. That is, after determining the first task, the second intelligent agent can call the discovery interface of the third network element to discover the service intelligent agent (e.g., the first intelligent agent) that supports orchestrating the first task, such as the service agent that supports service01 and service03.

[0316] The input information of the discovery interface can be the discovery request parameters carried by the second agent, such as information describing at least one of the following characteristics of the service agent making the request: role, supported open interfaces, or capabilities.

[0317] For example, if the first task includes a computing resource application task and a computing session creation task, then the orchestration request is used to request the first agent to orchestrate the computing resource application task and to perform task orchestration for the computing session creation task.

[0318] For example, the orchestration request may include a description of the first task, and / or the output format of the orchestration result of the first task (e.g., json or yaml, etc.), which is not limited.

[0319] S1007, the first intelligent agent orchestrates the first task according to at least one tool corresponding to the first service, and obtains the orchestration result of the first task. The orchestration result is used to call the first service in the network to execute the first task.

[0320] In one implementation, the first agent can invoke a local or remote model to perform inference and task orchestration based on the information of the first service (e.g., service01profile and service03 profile) obtained in step S1004, and obtain the orchestration result of the first task.

[0321] For example, the orchestration result of the first task may include: interface information of the first network element in the calling network; optionally, it may also include the type of network element in the calling network, and / or, information such as input parameters. It is understood that the network element in the network supports the execution of the first task, and may be, for example, a computing network element, a session network element, or a sensing network element.

[0322] S1008, the first intelligent agent sends the arrangement result of the first task to the second intelligent agent;

[0323] Correspondingly, the second agent receives the arrangement result of the first task from the first agent, as detailed in Table 10 below.

[0324] Table 10

[0325] step Completed service type Call tools profile Step 1 service01 tools profile (tool 1) step2 service03 tools profile (tool 3)

[0326] As shown in Table 10, the orchestration result of the first task includes two steps. The service type corresponding to step 1 is service01, and the corresponding callable tool information is tools profile (tool 1). The service type corresponding to step 2 is service03, and the corresponding callable tool information is tools profile (tool 3).

[0327] Optionally, after receiving the orchestration result of the first task, the second agent reviews and determines that the orchestration result of the first task meets the requirements. If the orchestration result does not meet the requirements, the second agent can interact with the first agent multiple times until it obtains an orchestration result that meets the requirements.

[0328] Furthermore, the second intelligent agent can send a request message to the fourth network element (e.g., TCF) to trigger / cause the fourth network element to schedule network services to perform the first task and realize the intent of the terminal device.

[0329] Based on the above scheme, the second network element can initiate registration for at least one service with the first network element based on the service type. The first intelligent agent and the first network element obtain information about the first service and its corresponding at least one tool by executing a discovery process. Furthermore, the first intelligent agent can construct its own information upon obtaining information about available services and their corresponding tools, and register this information with the third network element. This allows the second intelligent agent to obtain the first intelligent agent's information through the third network element, facilitating discovery between intelligent agents. Additionally, the first intelligent agent can initiate a subscription request to the first network element to obtain information about the service corresponding to the first service type and its corresponding at least one tool in a timely manner, facilitating task orchestration requests. This technical solution, while realizing the intent of the terminal device, can reduce signaling overhead and improve service discovery efficiency.

[0330] To facilitate understanding, the following will be combined with Figures 11 to 14The methods described above are explained in detail for different scenarios. These examples are provided for ease of understanding only and should not be construed as limiting this application. In the examples below, the first network element is a service repository, the second network element includes atomic service a and atomic service b, the first intelligent agent is a service agent, the third network element is an agent repository, and the second intelligent agent is a system agent. It is understood that the processes described below are only illustrative examples, and the embodiments of this application are not limited thereto. For content not described in detail below, please refer to [reference needed]. Figures 6 to 10 The description of the method shown will not be repeated below.

[0331] Figure 11 This is a schematic flowchart of a communication method 1100 provided in an embodiment of this application. Figure 11 As shown, this method mainly describes the process of an atomic service initiating a service registration process with a service agent at the service granularity, the process of a service agent requesting to discover information about one or more services of a certain service type, and the process of a service agent initiating a registration process with a service agent repository. This method is used to realize the intent of the terminal device. The method includes the following steps.

[0332] S1101, atomic service a sends a registration request message #a (i.e., the first registration request) to the service repository;

[0333] Correspondingly, the service repository receives the registration request message #a from the atomic service a.

[0334] In one implementation, atomic service 'a' is classified into tools based on service type and registered with the service repository.

[0335] In one example, atomic service 'a' constructs a service profile (i.e., information about at least one service) for registration based on the service type, for example, categorized into three types: service01, service02, and service03.

[0336] For example, the service01 profile is shown in Table 11. The descriptions of the tools that service01 can call include tool profile (tool 1) and tool profile (tool 2).

[0337] Table 11

[0338]

[0339] For example, the service02 profile is shown in Table 12. The descriptions of the tools that service02 can call include tool profile (tool 3) and tool profile (tool 4).

[0340] Table 12

[0341]

[0342] For example, the service03 profile is shown in Table 13. The descriptions of the tools that service03 can call include tool profile (tool 5) and tool profile (tool 6).

[0343] Table 13

[0344]

[0345] S1102, atomic service b sends a registration request message #b (i.e., the first registration request) to the service repository;

[0346] Correspondingly, the service repository receives the registration request message #b from the atomic service b.

[0347] In one implementation, atomic service b is classified into tools based on service type and registered with the service repository.

[0348] In another example, atomic service b constructs a service profile (i.e., information about at least one service) for registration based on the service type, and is divided into three categories: service02, service03, and service04.

[0349] For example, the service02 profile is shown in Table 14. The descriptions of the tools that service02 can call include tool profile (tool 3) and tool profile (tool 7).

[0350] Table 14

[0351]

[0352] For example, as shown in Table 15, the descriptions of the tools that service03 can call include tool profile (tool 3) and tool profile (tool 8).

[0353] Table 15

[0354]

[0355] For example, the service04 profile is shown in Table 16. The descriptions of the tools that service04 can call include tool profile (tool 1) and tool profile (tool 9).

[0356] Table 16

[0357]

[0358] S1103, the service repository updates the information of atomic service a and atomic service b.

[0359] Understandably, the service repository updates service storage records, such as adding services and tools for atomic services a and b.

[0360] In one implementation, the service repository stores services and corresponding callable tools profiles according to service type. After atomic services a and b register with the service repository, the service repository updates the service storage records, for example, updating them to four service types: service01, service02, service03, and service04.

[0361] For example, the service01 profile is shown in Table 17. The descriptions of the tools that service01 can call include tool profile (tool 1) and tool profile (tool 2).

[0362] Table 17

[0363]

[0364]

[0365] For example, as shown in Table 18, the descriptions of the tools that service02 can call include tool profile (tool 3), tool profile (tool 4), and tool profile (tool 7).

[0366] Table 18

[0367]

[0368] For example, as shown in Table 19, the descriptions of the tools that service03 can call include tool profile (tool 3), tool profile (tool 5), tool profile (tool 6), and tool profile (tool 8).

[0369] Table 19

[0370]

[0371] For example, the service04 profile is shown in Table 20. The descriptions of the tools that service04 can call include tool profile (tool 1) and tool profile (tool 9).

[0372] Table 20

[0373]

[0374] S1104, the service agent sends a discovery request message (i.e., a discovery request) to the service repository;

[0375] Correspondingly, the service repository receives discovery request messages from the service agents.

[0376] The discovery request message is used to discover services.

[0377] In one implementation, the service agent sends a service discovery request based on the service type to the service repository, carrying discovery request parameters.

[0378] For example, the discovery request parameters carried by the service agent include: requester type and service type defined by the requester, as shown in Table 21.

[0379] Table 21

[0380]

[0381] S1105, the service repository sends a discovery response message (i.e., discovery response) to the service agent;

[0382] Correspondingly, the service agent receives a discovery response message from the service repository.

[0383] The discovery response message includes information about available services (e.g., service profile).

[0384] In one implementation, based on step S1103, it is known that the services stored in the service repository include service01, service02, service03, and service04. Based on step S1104, it is known that the services defined by the service agent include service01, service02, and service05. Therefore, after the services are synchronized, the service repository returns a list of tools corresponding to service01 and service02 to the service agent, as shown in Table 22.

[0385] Table 22

[0386]

[0387] S1106, The tools that the service agent determines to invoke, and the information that builds the agent (e.g., agent profile).

[0388] For example, the service agent synchronizes the available service types and selects tools for the available services.

[0389] In one implementation, based on step S1105, it is known that the available services of the service agent include service01 and service02, and the tools to be invoked are selected from the tools list returned from the service repository for service01 and service02, as shown in Table 23.

[0390] Table 23

[0391]

[0392] Therefore, the information of the tools that service01 can call includes: tool profile (tool 1) and tool profile (tool 2), and the information of the tools that service02 can call includes: tool profile (tool 3) and tool profile (tool 4).

[0393] In one implementation, the service agent constructs an agent profile based on the available services and their corresponding callable toolsprofile list, as well as other self-attributes, as shown in Table 24.

[0394] Table 24

[0395]

[0396] S1107, the service agent sends a registration request message #c (i.e., the second registration request) to the agent repository;

[0397] Correspondingly, the agent repository receives registration request messages #c from the service agents.

[0398] The registration request message #c includes information about the service agent, such as the agent profile, as shown in Table 24.

[0399] Based on the above scheme, a service type-based registration mechanism is defined for network atomic services. Network atomic services categorize their service interfaces according to service type and construct service profile information based on service type, registering it with the service repository. This satisfies the need for service requesters to select the interface to call based on service type. Service agents and network atomic services can synchronize, and service agents can also register their own information in the agent storage, facilitating the discovery of other agents and improving collaboration among multiple agents.

[0400] It should be understood that detailed explanations of each step in Method 1100 can be found in the above text. Figure 10 The relevant descriptions in Method 1000 will not be repeated here. Furthermore, the technical solution shown in Method 1100 corresponds to that shown in Method 1000, and therefore the beneficial effects are similar, which will not be repeated here either.

[0401] It should also be understood that Figure 11 The process shown is just to Figure 10 The illustrated method 1000 is one possible implementation and should not be construed as limiting this application. Those skilled in the art can make simple substitutions or modifications to one or more steps of method 1000 based on the same concept to achieve the same effect. Therefore, simple modifications or substitutions should fall within the protection scope of this application.

[0402] Figure 12 This is a schematic flowchart of a communication method 1200 provided in an embodiment of this application. Figure 12 As shown, this method mainly describes the process by which a service agent (e.g., a service agent) requests available tools corresponding to a service from an agent repository (e.g., an agent repository) based on the service type to complete the task orchestration process, which is used to subsequently realize the user intent of the UE. The method includes the following steps.

[0403] S1201, the UE sends the user intent (or task requirement) to the system agent;

[0404] Correspondingly, the system agent receives user intent from the UE.

[0405] In this application, the user intent can be replaced with the intent of the terminal device, or the intent of the user using the terminal device, or the UE intent; its name is not limited. For example, the intent may be that the UE requests computing resources.

[0406] In this application, the user intent description can be a natural language description, such as natural language text, voice, or images, or a formatted intent expression model, such as the intent expression model defined by the intent driven management service (IDMS) of the 3GPP management standards working group. It can also be other description methods such as pictures, text, voice, video, binary code files, or application (APP) installation packages. This application does not limit the form, content, or format of the UE's intent description.

[0407] S1202, the system agent understands and decomposes the user's intent to obtain one or more subtasks (e.g., subtask, i.e., the first task).

[0408] For example, the system agent understands the user's intent and breaks down the task into multiple subtasks, such as subtask01 and subtask02.

[0409] In one implementation, after acquiring the user's intent, the system agent can use an AI model, such as a Large Language Model (LLM), to understand the user's intent, obtain one or more network function requirements, and then plan one or more subtasks based on these requirements. One network function requirement can correspond to one or more tasks; this is not limited.

[0410] For example, assuming the user's intention is to request computing resources for the UE, after the first agent uses LLM to understand the UE's intention, it can infer that service agents in the computing power service domain and the connectivity service domain need to collaborate to complete the orchestration of multiple sub-tasks. For example, the multiple sub-tasks include a computing resource request task (e.g., subtask01) and a computing session creation task (e.g., subtask02).

[0411] S1203, the system agent sends a task orchestration request message (i.e., task orchestration) to the service agent;

[0412] Correspondingly, the service agent receives task orchestration request messages from the system agent.

[0413] The task orchestration request message is used to request the orchestration of multiple subtasks.

[0414] For example, the system agent can discover service agents that support the orchestration of the above-mentioned subtasks from the agent repository. The specific discovery process can be found in the relevant description above, and for the sake of brevity, it is not specifically limited here. For example, the system agent requests the service agent to orchestrate subtasks subtask01 and subtask02.

[0415] For example, the task orchestration request message may include descriptions of subtasks and / or the output format of the orchestration results of the subtasks. The descriptions of multiple subtasks may include: requesting the service agent to orchestrate computing resource request tasks (e.g., the size or bandwidth of the requested computing, storage, or network resources), and orchestrating computing session creation tasks (e.g., creating a session, where the session type is a computing session). The output format of the orchestration results of multiple subtasks may be JSON, YAML, etc., and is not limited thereto.

[0416] S1204, the service agent sends a discovery request message (i.e., a discovery request) to the service repository;

[0417] Correspondingly, the service repository receives discovery request messages from the service agents.

[0418] The discovery request message is used to request information about at least one callable tool corresponding to the discovery subtask.

[0419] For example, if the completion of subtask01 requires calling service instance service01 and the completion of subtask02 requires calling service instance service02, then the service agent sends a discovery request to the service repository based on service01 and service02 to obtain the list of callable tool profiles corresponding to service01 and service02. The discovery request parameters carried in the discovery request message can be shown in Table 25 below.

[0420] Table 25

[0421]

[0422]

[0423] S1205, the service repository sends a discovery response message to the service agent;

[0424] Correspondingly, the service agent receives a discovery response message from the service repository.

[0425] The discovery response message includes the tool profilelist that can be called by service01 and service02, as shown in Table 26 below.

[0426] Table 26

[0427]

[0428] S1206, the service agent orchestrates subtasks according to the invoked tools and obtains the task orchestration result.

[0429] For example, the service agent selects callable tools for subtask01 and subtask02 from the tools profile list, and then completes the task orchestration of subtask01 and subtask02 according to the selected tools. For example, tool 1 is selected to orchestrate subtask01, and tool 4 is selected to orchestrate subtask02, to obtain the task orchestration result. For example, the task orchestration result includes two steps: the service type corresponding to step 1 is service01, and the corresponding callable tool information is tools profile (tool 1); the service type corresponding to step 2 is service02, and the corresponding callable tool information is tools profile (tool 4), etc.

[0430] S1207, The service agent sends the task orchestration results to the system agent;

[0431] Correspondingly, the system agent receives the task orchestration results from the service agent.

[0432] Optionally, after receiving the task orchestration results, the system agent reviews and determines whether the orchestration results of multiple subtasks meet the requirements. If the orchestration results do not meet the requirements, the system agent can interact with the service agent multiple times until a satisfactory orchestration result is obtained. This application does not limit the specific implementation method of the system agent reviewing whether the task orchestration results meet the requirements.

[0433] S1208, the system agent sends a task execution request message to the TCF;

[0434] Correspondingly, the TCF receives task execution request messages from the system's intelligent agents.

[0435] The task execution request message may carry task orchestration results, including interface information for calling TCF, such as calling the computing resource allocation interface or calling the session creation interface.

[0436] S1209, TCF performs the task.

[0437] For example, TCF schedules the corresponding interface to execute tasks according to the task function scheduling chain.

[0438] Based on the above scheme, a service repository discovery mechanism based on service type is defined. When a requester initiates a discovery request, it provides the service type to be discovered to the service repository. The service repository then matches and retrieves the corresponding service type's storage information (including the service type and the corresponding tools profile list) from its storage records and returns it to the requester. This enables the requesting party to quickly synchronize available services and their corresponding callable tools, thus confirming its own service capabilities. Service agents request available tools from the agent repository based on their services, facilitating efficient task orchestration and planning, thereby realizing user intent, meeting user business needs, and improving user experience.

[0439] It should be understood that detailed explanations of each step in Method 1200 can be found above. Figure 10 The relevant descriptions will not be repeated here. Furthermore, the technical solution shown in method 1200 corresponds to the technical solution shown in method 1000, and therefore the beneficial effects obtained are similar, which will not be repeated here.

[0440] It should also be understood that Figure 12 The process shown is just to Figure 10 The illustrated method 1000 is one possible implementation and should not be construed as limiting this application. Those skilled in the art can make simple substitutions or modifications to one or more steps of method 1000 based on the same concept to achieve the same effect. Therefore, simple modifications or substitutions should fall within the protection scope of this application.

[0441] Figure 13 This is a schematic flowchart of a communication method 1300 provided in an embodiment of this application. Figure 13As shown, this method mainly describes the process by which a service agent (e.g., a service agent) initiates a service subscription based on the service type and updates the service information, in order to realize the intent of the terminal device. The method includes the following steps.

[0442] S1301, the service agent sends a discovery request message (i.e., a discovery request) to the service repository;

[0443] Correspondingly, the service repository receives discovery request messages from the service agents.

[0444] The discovery request message is used to request the discovery of available services.

[0445] For example, the service agent sends a discovery request to the service repository based on the service type (e.g., service01, service02, service05) carrying discovery request parameters. For example, the discovery request parameters include: the requester type and the service type defined by the requester, as shown in Table 27.

[0446] Table 27

[0447]

[0448] S1302, the service repository sends a discovery response message (i.e., discovery response) to the service agent;

[0449] Correspondingly, the service agent receives a discovery response message from the service repository.

[0450] For example, assuming that the records currently stored in the service repository include tool profiles of four types of services: service01, service02, service03, and service04, the service repository can return available service01, service02, and their tool profiles to the service agent after matching and discovering the request parameters.

[0451] S1303, The service agent determines the available services and their callable tools, and constructs the agent's information (e.g., agent profile).

[0452] For example, based on the discovery response message, the service agent determines that the actual services that can be called are service01 and service02, and then selects the tools to be called for service01 and service02 respectively, and constructs an agent profile.

[0453] For the specific implementation of step S1303 above, please refer to the relevant description of step S1106 of method 1100 above. For the sake of brevity, it will not be described here again.

[0454] S1304, the service agent sends a subscription request message (i.e., a subscription request) to the service repository;

[0455] Correspondingly, the service repository receives subscription request messages from the service agent.

[0456] For example, the service agent initiates a subscription service based on service01, service02, and service05 to the service repository.

[0457] S1305, atomic service c sends a registration request message #c (i.e., the first registration request) to the service repository;

[0458] Correspondingly, the service repository receives the registration request message #c from the atomic service c.

[0459] S1306, Atomic service d sends a registration request message #d (i.e., the first registration request) to the service repository;

[0460] Correspondingly, the service repository receives the registration request message #d from the atomic service d.

[0461] In other words, in steps S1305 and S1306 above, atomic services c and d bring the new service online, classify tools based on service type, and register with the service repository.

[0462] For example, atomic service c builds a service profile based on service type (e.g., service01, service05) and sends the tools profile corresponding to service01 and service05 to the service repository; atomic service d builds a service profile based on service type (e.g., service05, service06) and sends the tools profile corresponding to service05 and service06 to the service repository.

[0463] For details on the implementation of steps S1305 and S1306 above, please refer to the relevant descriptions of steps S1101 and S1102 of method 1100 above. For the sake of brevity, they will not be described here again.

[0464] S1307, the service repository updates the information of atomic service c and atomic service d (i.e., information of at least one service).

[0465] In other words, the service repository updates the service storage records, such as adding services and tools for atomic services c and d.

[0466] In one implementation, the service repository stores services and their corresponding callable tools profiles according to service type. After atomic services c and d register with the service repository, the service repository updates the service storage records. For example, the service repository storage records are updated to include tools profiles for six service types: service01, service02, service03, service04, service05, and service06.

[0467] For the specific implementation of step S1307 above, please refer to the relevant description of step S1103 of method 1100 above. For the sake of brevity, it will not be described here again.

[0468] S1308, the service repository sends a subscription response message (i.e., subscription response) to the service agent;

[0469] Correspondingly, the service agent receives subscription response messages from the service repository.

[0470] The subscription response message includes the updated service (e.g., service05) and its tools profile.

[0471] S1309, the service agent determines the available services and their callable tools, and updates the agent's information (e.g., agent profile#).

[0472] Understandably, the updated agent information (e.g., agent profile#) is different from the agent information (e.g., agent profile) created in step S1303 above.

[0473] For example, the service agent updates the available services (service01, service02, and service05) based on the updated services and tools, and updates the callable tools corresponding to the available services, thereby updating the agent's information (e.g., agent profile#).

[0474] S1310, the service agent sends an update request message (i.e., an update request) to the agent repository;

[0475] Correspondingly, the agent repository receives update request messages from the service agents.

[0476] The update request message is used to request an update to the agent's information, such as updating to agent profile#.

[0477] Based on the above scheme, the service agent can request to subscribe to services from the agent repository based on the service type. It can obtain updated service information in a timely manner and complete the information update process of the service and its corresponding at least one tool. This facilitates efficient task orchestration and planning, as well as the discovery of other agents, and improves the mutual cooperation among multiple agents to achieve the user's intent.

[0478] It should be understood that detailed explanations of each step in Method 1300 can be found above. Figure 10 The relevant descriptions will not be repeated here. Furthermore, the technical solution shown in method 1300 corresponds to the technical solution shown in method 1000, and therefore the beneficial effects obtained are similar, which will not be repeated here.

[0479] It should also be understood that Figure 13 The process shown is just to Figure 10 The illustrated method 1000 is one possible implementation and should not be construed as limiting this application. Those skilled in the art can make simple substitutions or modifications to one or more steps of method 1000 based on the same concept to achieve the same effect. Therefore, simple modifications or substitutions should fall within the protection scope of this application.

[0480] Figure 14 This is a schematic flowchart of a communication method 1400 provided in an embodiment of this application. Figure 14 As shown, this method mainly describes two registration methods initiated by atomic services based on service type and service instance, which are used to realize the user intent of UE. The method includes the following steps.

[0481] S1401, the atomic service sends a registration request message #1 to the service repository (e.g., the service repository);

[0482] Correspondingly, the service repository receives registration request message #1 (i.e., the first registration request) from the atomic service.

[0483] In other words, after an atomic service goes live, it initiates a registration request to the service repository based on the service type. For example, an atomic service builds a service profile based on the service type and sends the service profile (i.e., information about at least one service) to the service repository.

[0484] S1402, the atomic service sends a registration request message #2 to the NRF;

[0485] Correspondingly, NRF receives registration request message #2 from the atomic service.

[0486] In other words, after an atomic service goes live, it initiates a registration request to the NRF based on the atomic service instance. For example, the atomic service builds an NF profile based on the atomic service instance and sends the NF profile to the NRF, as shown in Table 28.

[0487] Table 28

[0488]

[0489]

[0490] S1403, the service agent sends discovery request message #1 (i.e., discovery request) to the service repository;

[0491] Correspondingly, the service repository receives discovery request message #1 from the service agent.

[0492] Among them, the discovery request message #1 is used to request the discovery of available services.

[0493] For example, the service agent initiates a discovery request based on the service type to the service repository.

[0494] S1404, the service repository sends discovery response message #1 (i.e., discovery response) to the service agent;

[0495] Correspondingly, the service agent receives discovery response message #1 from the service repository.

[0496] The discovery response message #1 includes information about the available services of the service agent (e.g., service profile).

[0497] S1405, the UE sends the user intent (or task requirement) to the system agent;

[0498] Correspondingly, the system agent receives user intent from the UE.

[0499] S1406, the system agent understands and decomposes the user's intent, resulting in multiple sub-tasks.

[0500] For example, the system agent understands the user's intent and breaks down the task into multiple sub-tasks, such as service01 and service02.

[0501] S1407, The system agent sends a discovery request message #2 to the agent repository;

[0502] Correspondingly, the agent repository receives discovery request message #2 from the system agents.

[0503] Among them, the discovery request message #2 is used to request the discovery of service agents that support the orchestration of multiple subtasks.

[0504] S1408, the agent repository sends discovery response message #2 to the system agent;

[0505] Correspondingly, the system agent receives discovery response message #2 from the agent repository.

[0506] Among them, the discovery response message #2 includes information about the service agent.

[0507] S1409, The system agent sends a task orchestration request message to the service agent;

[0508] Correspondingly, the service agent receives task orchestration request messages from the system agent.

[0509] The task orchestration request message is used to request the orchestration of multiple subtasks.

[0510] S1410, the service agent orchestrates the subtasks according to the available tools, and obtains the orchestration results, as shown in Table 29.

[0511] Table 29

[0512] step Completed service type Call tools profile Step 1 service01 tools profile (tool 1) step2 service02 tools profile (tool 2) Step 3 service03 tools profile (tool 3) … … …

[0513] As shown in Table 29, the task orchestration result includes three steps. Step 1 corresponds to the service type service01, and the corresponding callable tool information is tools profile (tool 1). Step 2 corresponds to the service type service02, and the corresponding callable tool information is tools profile (tool 2). Step 3 corresponds to the service type service03, and the corresponding callable tool information is tools profile (tool 3).

[0514] It should be noted that the number of service agents discovered in steps S1407 and S1408 can be multiple, and the sys-agent can call multiple service agents (e.g., connection agents and computation agents) to complete different sub-task orchestrations. The task orchestration process of multiple service agents is similar and will not be described here.

[0515] Tables 2 to 29 above are merely illustrative examples to facilitate understanding of the solutions. Other solutions and other forms of representation are not excluded, such as code, functions, text, strings, or other ways that can be used to indicate relevant information.

[0516] S1411, The service agent sends the task orchestration results to the system agent;

[0517] Correspondingly, the system agent receives the task orchestration results from the service agent.

[0518] S1412, the system agent sends a task execution request message to the TCF;

[0519] Correspondingly, the TCF receives task execution request messages from the system's intelligent agents.

[0520] S1413, TCF sends Discovery Request Message #3 to NRF;

[0521] Correspondingly, the NRF receives discovery request message #3 from the TCF.

[0522] Among them, the discovery request message #3 is used to request the discovery of instances of atomic services that support the execution of multiple subtasks.

[0523] For example, the TCF sends a discovery request to the NRF based on the task orchestration and scheduling chain, carrying tools type information, to discover the tools that can be called at each step and the corresponding atomic service instances.

[0524] S1414, NRF sends discovery response message #3 to TCF;

[0525] Correspondingly, the TCF receives discovery response message #3 from the NRF.

[0526] Among them, the discovery response message #3 includes instance information of the atomic service, such as the NF profile.

[0527] For example, TCF can match multiple atomic service instances that meet the requirements. TCF can prioritize NF instances based on rules such as geographical location, load, fault recovery capability, or resource availability, select the most suitable atomic service instance, and call the corresponding tools to complete each step of the service based on the IP information in the NF profile it returns.

[0528] S1415, TCF performs the mission.

[0529] For example, TCF schedules corresponding atomic service instances to execute tasks according to the task function scheduling chain.

[0530] Based on the above solution, two registration and storage methods for atomic services are provided: one based on service type and the other on instance. Service type-based discovery enables discovery requesters to quickly synchronize available services and their corresponding callable tools, thus confirming their own service capabilities. This technical solution, while fulfilling user intent, reduces signaling overhead and improves service discovery efficiency.

[0531] It should be understood that detailed explanations of each step in Method 1400 can be found in the above text. Figure 10 The relevant descriptions in Method 1000 will not be repeated here. Furthermore, the technical solution shown in Method 1400 corresponds to the technical solution shown in Method 1000, and therefore the beneficial effects obtained are similar, and will not be repeated here either.

[0532] It should also be understood that Figure 14 The process shown is just to Figure 10 The illustrated method 1000 is one possible implementation and should not be construed as limiting this application. Those skilled in the art can make simple substitutions or modifications to one or more steps of method 1000 based on the same concept to achieve the same effect. Therefore, simple modifications or substitutions should fall within the protection scope of this application.

[0533] The above text combined Figures 1 to 14 This application describes in detail the communication method provided in the embodiments of the present application from the perspective of the interaction between the first network element, the second network element and the first intelligent agent, so as to meet the service needs of the first intelligent agent.

[0534] Those skilled in the art will recognize that, based on the units and algorithm steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is implemented in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0535] The following combination Figures 15 to 17 The communication device provided in this application is described in detail. It should be understood that the description of the device embodiments corresponds to the description of the method embodiments. Therefore, for details not described in detail, please refer to the method embodiments above; for brevity, some details are omitted.

[0536] This application embodiment can divide the transmitting or receiving device into functional modules according to the above method examples. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The following description uses the division of functional modules according to each function as an example.

[0537] Figure 15 This is a schematic block diagram of the communication device 10 provided in an embodiment of this application. Figure 15 As shown, the device 10 includes a transceiver module 11 and a processing module 12. The transceiver module 11 can implement corresponding communication functions, or in other words, the transceiver module 11 is used to perform receiving and sending related operations. The transceiver module 11 can also be called a communication interface, transceiver unit, input / output circuit, input / output interface, communication module, transceiver circuit, interface unit, or communication unit, etc. The transceiver unit includes a receiving unit and / or a sending unit; the sending unit can also be called an output unit, and the receiving unit can also be called an input unit. The processing module 12 is used to perform data processing, or in other words, the processing module 12 is used to perform operations other than receiving and sending. For example, the processing module 12 can read instructions and / or data from the storage unit 1001 to enable the device to implement the aforementioned method embodiment.

[0538] In one possible implementation, the device 10 may further include a storage module 13, which can be used to store instructions and / or data. The processing module 12 can read the instructions and / or data in the storage module to enable the device to perform the actions of the device in the aforementioned method embodiments.

[0539] In one design, the device 10 may correspond to the first network element in the above method embodiment, or a component of the first network element (e.g., a communication module, processor, circuit, chip, or chip system, etc.), or it may be a logic module or software that can implement all or part of the functions of the first network element.

[0540] The device 10 can implement the steps or processes corresponding to the first network element in the above method embodiment. The transceiver module 11 can be used to perform the transceiver-related operations of the first network element in the above method embodiment, and the processing module 12 can be used to perform the processing-related operations of the first network element in the above method embodiment.

[0541] For example, the processing module 12 is used to obtain information about at least one service, the information about at least one service including the service type to which each service belongs and the information about at least one tool corresponding to each service; the transceiver module 11 is used to receive a discovery request from a first agent, the discovery request including a first service type; the transceiver module 11 is also used to send a discovery response to the first agent, the discovery response including the information about at least one tool corresponding to the first service, the at least one service including the first service, and the first service type including the service type to which the first service belongs.

[0542] In one possible implementation, at least one service further includes a second service, and the processing module 12 is further configured to obtain information about the first service and the second service. The information about the first service includes the service type to which the first service belongs and information about at least one tool corresponding to the first service. The information about the second service includes the service type to which the second service belongs and information about at least one tool corresponding to the second service.

[0543] In one possible implementation, the transceiver module 11 is further configured to receive a first registration request from the second network element, the first registration request including information on at least one service supported by the second network element.

[0544] In one possible implementation, at least one service further includes a second service. The first registration request includes a first information element and a second information element. The first information element includes information about the service type to which the first service belongs and information about at least one tool corresponding to the first service. The second information element includes information about the service type to which the second service belongs and information about at least one tool corresponding to the second service.

[0545] In one possible implementation, in response to the first registration request, the processing module 12 is also used to store information about at least one service.

[0546] In one possible implementation, the processing module 12 is further configured to determine, based on the information of at least one service and the first service type, the information of the first service and at least one tool corresponding to the first service.

[0547] In one possible implementation, the processing module 12 is further configured to determine, from the information of at least one service, the information of the first service and the information of at least one tool corresponding to the first service, if the service type to which the first service belongs is the same as the service type to which at least one service belongs.

[0548] In one possible implementation, the information of at least one service may also include the service identifier of each service within at least one service.

[0549] In one possible implementation, the transceiver module 11 is further configured to receive a subscription request from the first intelligent agent, the subscription request including a first service type; the processing module 12 is further configured to send updated information of one or more services to the first intelligent agent in the event of an update to information of one or more services belonging to the first service type, based on the subscription request.

[0550] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0551] In another design, the device 10 may correspond to the second network element in the above method embodiment, or a component of the second network element (e.g., a communication module, processor, circuit, chip, or chip system), or it may be a logic module or software that can implement all or part of the functions of the second network element.

[0552] The device 10 can implement the steps or processes corresponding to the second network element in the above method embodiment. The transceiver module 11 can be used to perform the transceiver-related operations of the second network element in the above method embodiment, and the processing module 12 can be used to perform the processing-related operations of the second network element in the above method embodiment.

[0553] For example, the transceiver module 11 is used to send a first registration request to the first network element. The first registration request includes information about at least one service supported by the second network element. The information about the at least one service includes the service type to which each service belongs and information about at least one tool corresponding to each service.

[0554] In one possible implementation, at least one service includes a first service and a second service. The first registration request includes a first information element and a second information element. The first information element includes information about the service type to which the first service belongs and information about at least one tool corresponding to the first service. The second information element includes information about the service type to which the second service belongs and information about at least one tool corresponding to the second service.

[0555] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here.

[0556] In one design, the device 10 may correspond to the first intelligent agent in the above method embodiments, or a component of the first intelligent agent (e.g., a communication module, processor, circuit, chip, or chip system, etc.), or it may be a logic module or software that can implement all or part of the functions of the first intelligent agent.

[0557] The device 10 can implement the steps or processes corresponding to those executed by the first intelligent agent in the above method embodiments. The transceiver module 11 can be used to execute the transceiver-related operations of the first intelligent agent in the above method embodiments, and the processing module 12 can be used to execute the processing-related operations of the first intelligent agent in the above method embodiments.

[0558] For example, the transceiver module 11 is configured to send a discovery request to the first network element, the discovery request including a first service type; the transceiver module 11 is also configured to receive a discovery response from the first network element, the discovery response including information on at least one tool corresponding to the first service, the at least one service including the first service, and the first service type including the service type to which the first service belongs.

[0559] In one possible implementation, the transceiver module 11 is further configured to receive an orchestration request from the second agent, the orchestration request being used to request orchestration of the first task; the processing module 12 is configured to orchestrate the first task according to at least one tool corresponding to the first service, to obtain the orchestration result of the first task, the orchestration result being used to call the first service to execute the first task; the transceiver module 11 is further configured to send the orchestration result of the first task to the second agent.

[0560] In one possible implementation, the transceiver module 11 is further configured to send a second registration request to a third network element. The second registration request includes information about a first intelligent agent, and the information about the first intelligent agent includes information about at least one tool corresponding to the first service.

[0561] In one possible implementation, the transceiver module 11 is further configured to send a subscription request to the first network element, the subscription request including a first service type; the transceiver module 11 is further configured to receive updated information of one or more services belonging to the first service type from the first network element.

[0562] In one possible implementation, the transceiver module 11 is also used to send an update request to a third network element. The update request is used to update the information of the first intelligent agent and includes information of at least one service after the update.

[0563] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here.

[0564] It should also be understood that the device 10 here is embodied in the form of a functional module. The term "module" here may refer to application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memories for executing one or more software or firmware programs, integrated logic circuits, and / or other suitable components that support the described functions.

[0565] In an alternative example, those skilled in the art will understand that device 10 may specifically be a first network element in the above embodiments, and may be used to execute the various processes and / or steps corresponding to the first network element in the above method embodiments; or, device 10 may specifically be a second network element in the above embodiments, and may be used to execute the various processes and / or steps corresponding to the second network element in the above method embodiments; or, device 10 may specifically be a first intelligent agent in the above embodiments, and may be used to execute the various processes and / or steps corresponding to the first intelligent agent in the above method embodiments. For the sake of brevity, further details are omitted here.

[0566] The apparatus 10 of each of the above-described schemes has the function of implementing the corresponding steps performed by the device (such as the first network element, the second network element, or the first intelligent agent) in the above-described methods. This function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described functions; for example, the transceiver module can be replaced by a transceiver (for example, the transmitting unit in the transceiver module can be replaced by a transmitter, and the receiving unit in the transceiver module can be replaced by a receiver), and other units, such as processing modules, can be replaced by processors, which respectively execute the transceiver operations and related processing operations in each method embodiment.

[0567] In addition, the transceiver module 11 can also be a transceiver circuit (for example, it may include a receiving circuit and a transmitting circuit), and the processing module can be a processing circuit.

[0568] Figure 16 This is a schematic diagram of another communication device 20 provided in an embodiment of this application. For example... Figure 16 As shown, the device 20 includes a transceiver 23 and a processor 21. The transceiver 23 is used for receiving and / or transmitting signals. The processor 21 and the transceiver 23 communicate with each other through an internal connection path. The processor 21 is used to execute computer programs or instructions stored in the memory 22, or to read data / signaling stored in the memory 22, in order to control the transceiver 23 to transmit and / or receive signals, so as to perform the methods in the above method embodiments.

[0569] In one possible implementation, the device 20 further includes a memory 22 for storing computer programs or instructions and / or data. The memory 22 may be integrated with the processor 21 or may be separately configured. The memory 22 communicates with the processor 21 and the transceiver 23 via internal interconnection paths.

[0570] Alternatively, there may be one or more transceivers 23.

[0571] Optionally, there may be one or more processors 21.

[0572] Optionally, the memory 22 may be one or more.

[0573] Optionally, transceiver 23 may include a transmitter and / or a receiver to respectively implement the sending and receiving operations in the embodiment; if transceiver 23 is an input / output interface, it sends the corresponding output and receives the corresponding input.

[0574] As a design, the device 20 is used to implement the operations performed by the first network element, the second network element, or the first intelligent agent in the various method embodiments described above.

[0575] Alternatively, if the transceiver 23 is replaced with an input / output circuit or an input / output interface, the communication device 20 can be considered as a chip or chip system.

[0576] It should be understood that the processor mentioned in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0577] It should also be understood that the memory mentioned in the embodiments of this application can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0578] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0579] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0580] Figure 17 This is a schematic diagram of a chip system 30 provided in an embodiment of this application. Figure 17 As shown, the chip system 30 (or processing system) includes logic circuits 31 and input / output interface 32.

[0581] The logic circuit 31 can be a processing circuit in the chip system 30. The logic circuit 31 can be coupled to a memory unit, calling instructions from the memory unit, enabling the chip system 30 to implement the methods and functions of the embodiments of this application. The input / output interface 32 can be an input / output circuit in the chip system 30, outputting processed information from the chip system 30, or inputting data or signaling information to be processed into the chip system 30 for processing.

[0582] As one approach, the chip system 30 is used to implement the operations performed by the first network element, the second network element, or the first intelligent agent in the various method embodiments described above.

[0583] For example, logic circuit 31 is used to implement processing-related operations performed by the first network element, the second network element, or the first intelligent agent in the above method embodiments; input / output interface 32 is used to implement sending and / or receiving-related operations performed by the first network element, the second network element, or the first intelligent agent in the above method embodiments.

[0584] This application also provides a computer-readable storage medium storing computer instructions for implementing the methods executed by the device in the above-described method embodiments. For example, when the computer program is executed by a computer, the computer can implement the methods executed by the first network element, the second network element, or the first intelligent agent in the above-described method embodiments.

[0585] This application also provides a computer program product comprising instructions that, when executed by a computer, implement the methods performed by the first network element, the second network element, or the first intelligent agent in the above-described method embodiments.

[0586] This application also provides a communication system, including at least one of the aforementioned first network element, second network element, or first intelligent agent.

[0587] The explanations and beneficial effects of the relevant contents in any of the devices provided above can be found in the corresponding method embodiments provided above, and will not be repeated here.

[0588] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0589] 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.

[0590] 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.

[0591] 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 the technical solution in this application, depending on actual needs.

[0592] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0593] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0594] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, The first network element applied in the network includes: Obtain information about at least one service, wherein the information about the at least one service includes the service type to which each service belongs and information about at least one tool corresponding to each service; Receive a discovery request from a first intelligent agent, the discovery request including a first service type; A discovery response is sent to the first intelligent agent. The discovery response includes information about at least one tool corresponding to the first service. The at least one service includes the first service. The type of the first service includes the service type to which the first service belongs.

2. The method according to claim 1, characterized in that, The at least one service further includes a second service, and obtaining information about the at least one service includes: Obtain first information and second information. The first information includes the service type to which the first service belongs and information about at least one tool corresponding to the first service. The second information includes the service type to which the second service belongs and information about at least one tool corresponding to the second service.

3. The method according to claim 1 or 2, characterized in that, The acquisition of information for at least one service includes: Receive a first registration request from a second network element, the first registration request including information about the at least one service supported by the second network element.

4. The method according to claim 3, characterized in that, The at least one service further includes a second service. The first registration request includes a first information element and a second information element. The first information element includes information about the service type to which the first service belongs and information about at least one tool corresponding to the first service. The second information element includes information about the service type to which the second service belongs and information about at least one tool corresponding to the second service.

5. The method according to claim 3 or 4, characterized in that, The method further includes: In response to the first registration request, information about the at least one service is stored.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Based on the information of the at least one service and the first service type, determine the information of the first service and at least one tool corresponding to the first service.

7. The method according to claim 6, characterized in that, The step of determining the information of the first service and at least one tool corresponding to the first service based on the information of the at least one service and the first service type includes: If the service type to which the first service belongs is the same as the service type to which the at least one service belongs, the information of the first service and at least one tool corresponding to the first service shall be determined from the information of the at least one service.

8. The method according to any one of claims 1 to 7, characterized in that, The information of the at least one service also includes the service identifier of each of the at least one service.

9. The method according to any one of claims 1 to 8, characterized in that, The method further includes: Receive a subscription request from a first intelligent agent, the subscription request including the first service type; Based on the subscription request, if the information of one or more services belonging to the first service type is updated, the updated information of the one or more services is sent to the first agent.

10. A communication method, characterized in that, The second network element applied in the network includes: A first registration request is sent to a first network element. The first registration request includes information about at least one service supported by the second network element. The information about the at least one service includes the service type to which each service belongs and information about at least one tool corresponding to each service.

11. The method according to claim 10, characterized in that, The at least one service includes a first service and a second service. The first registration request includes a first information element and a second information element. The first information element includes information about the service type to which the first service belongs and information about at least one tool corresponding to the first service. The second information element includes information about the service type to which the second service belongs and information about at least one tool corresponding to the second service.

12. A communication method, characterized in that, Applied to the first intelligent agent, including: Send a discovery request to the first network element, the discovery request including a first service type; The system receives a discovery response from the first network element. The discovery response includes information about at least one tool corresponding to the first service. The at least one service includes the first service, and the first service type includes the service type to which the first service belongs.

13. The method according to claim 12, characterized in that, The method further includes: Receive an orchestration request from a second agent, the orchestration request being used to request the orchestration of a first task; Based on at least one tool corresponding to the first service, the first task is orchestrated to obtain an orchestration result of the first task, and the orchestration result is used to call the first service to execute the first task; The arrangement result of the first task is sent to the second intelligent agent.

14. The method according to claim 12 or 13, characterized in that, The method further includes: A second registration request is sent to a third network element. The second registration request includes information about the first intelligent agent, and the information about the first intelligent agent includes information about at least one tool corresponding to the first service.

15. The method according to any one of claims 12 to 14, characterized in that, The method further includes: Send a subscription request to the first network element, the subscription request including the first service type; Receive updated information from the first network element about one or more services belonging to the first service type.

16. The method according to claim 15, characterized in that, The method further includes: An update request is sent to a third network element. The update request is used to update the information of the first intelligent agent. The update request includes the updated information of the at least one service.

17. A communication device, characterized in that, The method includes at least one processor for executing a computer program or instructions to cause the method as described in any one of claims 1 to 9 to be performed, or to cause the method as described in claims 10 or 11 to be performed, or to cause the method as described in any one of claims 12 to 16 to be performed.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program or instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 16.

19. A computer program product, characterized in that, It includes a computer program or instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 16.

Images