Communication method and communication apparatus

Abstract

A communication method and a communication apparatus. By means of messages, a first device in a first domain and a second device in a second domain can implement a cross-domain exchange of capability information of an agent, so as to support cross-domain update of the capability information of the agent, such that a task can be executed on the basis of the latest capability information of the agent, helping to increase the probability of successfully executing the task.

Description

Method and communication apparatus for communication

[0001] The present application claims priority from the Chinese patent application No. 202411331869.4 filed on September 23, 2024, and entitled "Method and communication apparatus for communication", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, and more particularly, to a method and communication apparatus for communication. BACKGROUND

[0003] In an artificial intelligence (AI) based multi-agent architecture, there is interaction and cooperation between agents. Currently, in the interaction and cooperation process of multi-agents across business domains, each agent can perform task decomposition, distribution and coordination based on local configuration. In this way, the probability of successful task execution is low. SUMMARY

[0004] Embodiments of the present application provide a method and communication apparatus for communication to improve the probability of successful task execution.

[0005] In a first aspect, a method for communication is provided, which can be performed by a first device. Unless otherwise specified, the "first device" can refer to the first device itself, a component (e.g., a processor, a chip, or a chip system, etc.) in the first device, or a logical module or software that can realize all or part of the functions of the first device.

[0006] The method includes: a first device in a first domain receiving a first message from a second device in a second domain, the first message including first capability information of a first agent, the first agent running in the second device; and the first device performing a task according to the first capability information.

[0007] In the above method, the first device and the second device can realize the interaction of the capability information of the agents across domains through messages, thereby supporting the update of the capability information of the agents across domains, so that the first device can perform the task based on the latest capability information of the agents, which helps to improve the probability of successful task execution.

[0008] In combination with the first aspect, in some implementations, the first capability information includes: a capability supported by the first agent, and information of an agent associated with the capability of the first agent.

[0009] In the implementation manner, the second device provides the first device with the capability supported by the first agent and a list of other agents associated with the capability, which helps the first device to generate a reasonable workflow, thereby improving the success probability of task execution.

[0010] With reference to the first aspect or the implementation manners thereof, in some other implementation manners, the first message further includes an identifier of the first agent.

[0011] In the implementation manner, the second device can indicate the capability information in the first message as the capability information of the first agent by carrying the identifier of the first agent in the first message, so that the first device can accurately update.

[0012] With reference to the first aspect or the implementation manners thereof, in some other implementation manners, the first message further includes first information or / and information of the second domain, the first information being used to indicate cross-domain configuration.

[0013] In the implementation manner, the first device can learn that the first capability information of the first agent is the capability information of the first agent of another domain by carrying the first information and / or the information of the second domain in the first message, so as to perform relevant operations for cross-domain by the first device.

[0014] With reference to the first aspect or the implementation manners thereof, in some other implementation manners, the first message further includes second information, the second information being used to indicate that the first message comes from the first agent and is sent to a second agent running in the first device.

[0015] In the implementation manner, the second information can explicitly indicate that the first capability information comes from the first agent and is sent to the second agent in the first device, so that the second agent can perform a task based on the first capability information.

[0016] With reference to the first aspect or the implementation manners thereof, in some other implementation manners, the first device performs a task according to the first capability information, including that the second agent performs the task according to the first capability information.

[0017] With reference to the first aspect or the implementation manners thereof, in some other implementation manners, the first message further includes a first communication type, the first communication type being used to indicate that the first message is used to update capability information of an agent; and the method further includes that the first device updates the capability information of the first agent stored locally as the first capability information according to the first message.

[0018] With reference to the first aspect or the implementation forms thereof, in some other implementation forms, before the first device of the first domain receives the first message from the second device of the second domain, the method further includes: the first device sending a second message to the second device, the second message being used to request capability information of the agent.

[0019] In the implementation forms described above, the first device can request the capability information of the agent from the first device, and the second device can send the first message to the first device based on the request of the first device to provide the first device with the first capability information of the first agent. This way can reduce the signaling overhead.

[0020] With reference to the first aspect or the implementation forms thereof, in some other implementation forms, the first device sending the second message to the second device includes: the first device periodically sending the second message to the second device; or the first device sending the second message to the second device when orchestrating the task.

[0021] With reference to the first aspect or the implementation forms thereof, in some other implementation forms, the second message includes: an identifier of the first agent.

[0022] In the implementation forms described above, the first device can request the capability information of the specified agent from the second device through the second message. This way can avoid the second device feeding back unnecessary capability information, which helps to reduce the signaling overhead.

[0023] With reference to the first aspect or the implementation forms thereof, in some other implementation forms, the second message includes: third information, the third information being used to indicate all agents running in the second device.

[0024] In the implementation forms described above, the first device can request the capability information of all agents from the second device through the second message.

[0025] With reference to the first aspect or the implementation forms thereof, in some other implementation forms, the first message further includes: capability information of an agent other than the first agent among the all agents.

[0026] With reference to the first aspect or the implementation forms thereof, in some other implementation forms, the second message further includes: a second communication type, the second communication type being used to indicate that the second message is used to request the capability information of the agent.

[0027] With reference to the first aspect or the implementation forms thereof, in some other implementation forms, the first domain is a master domain, and the second domain is a slave domain of the first domain; or the first domain and the second domain are peers. In other words, the implementation forms described above are applicable to both the centralized structure scenario and the decentralized structure scenario.

[0028] In a second aspect, a method for communication is provided, which can be performed by a second device. Unless specifically stated, the "second device" can refer to the second device itself, a component (e.g., a processor, a chip, or a chip system, etc.) in the second device, or a logical module or software capable of realizing all or part of the functions of the second device. The same terms or features in the second aspect or its implementation as in the first aspect or its implementation can refer to the first aspect or its implementation, and the technical effects of the second aspect or its implementation can refer to the technical effects in the first aspect or its implementation, which will not be repeated herein.

[0029] The method comprises: a second device of a second domain generating a first message, the first message comprising first capability information of a first agent, the first agent running in the second device; and the second device sending the first message to a first device in a first domain.

[0030] In some implementations of the second aspect, the first capability information comprises: a capability supported by the first agent, and information of an agent associated with the capability of the first agent.

[0031] In some implementations of the second aspect or its implementations, the first message further comprises: an identifier of the first agent.

[0032] In some implementations of the second aspect or its implementations, the first message further comprises: first information and / or information of the second domain, the first information being used to indicate cross-domain configuration.

[0033] In some implementations of the second aspect or its implementations, the first message further comprises: second information, the second information being used to indicate that the first message comes from the first agent and is sent to a second agent, the second agent running in the first device.

[0034] In some implementations of the second aspect or its implementations, the first message further comprises: a first communication type, the first communication type being used to indicate that the first message is used to update capability information of an agent.

[0035] In some implementations of the second aspect or its implementations, before the second device sends the first message to the first device, the method further comprises: the second device receiving a second message from the first device, the second message being used to request capability information of an agent; and the second device generating the first message, comprising: the second device generating the first message according to the second message.

[0036] In some other implementations, in combination with the second aspect or the implementation of the second aspect, the second message includes: an identifier of the first agent. The second device generates the first message according to the second message, including: the second device acquires the first capability information according to the identifier of the first agent; and the second device generates the first message according to the first capability information.

[0037] In some other implementations, in combination with the second aspect or the implementation of the second aspect, the second message includes: third information, the third information being used to indicate all agents running in the second device, the all agents including the first agent. The second device generates the first message according to the second message, including: the second device acquires capability information of the all agents according to the third information, the capability information of the all agents including the first capability information; and the second device generates the first message according to the capability information of the all agents.

[0038] In some other implementations, in combination with the second aspect or the implementation of the second aspect, the second message further includes: a second communication type, the second communication type being used to indicate that the second message is used to request capability information of an agent.

[0039] In some other implementations, in combination with the second aspect or the implementation of the second aspect, the second device generates the first message, including: when the capability of the first agent changes, the second device generates the first message according to the changed capability of the first agent.

[0040] In the above implementations, the second device can actively send the updated capability information of the agent to the first device in the case that the capability information of the agent in the second device is updated, so that the first device performs a task based on the updated capability information. This manner can reduce the number of interactions between the first device and the second device.

[0041] In some other implementations, in combination with the second aspect or the implementation of the second aspect, the first domain is a master domain, and the second domain is a slave domain of the first domain; or the first domain and the second domain are at the same level.

[0042] In a third aspect, a method for communication is provided, which can be performed by a first device and a second device. Unless otherwise specified, the first device or the second device can refer to the first device or the second device itself, a component (for example, a processor, a chip, or a chip system, etc.) in the first device or the second device, or a logic module or software capable of realizing all or part of the functions of the first device or the second device.

[0043] The method comprises: a second device of a second domain generating a first message, the first message comprising first capability information of a first agent, the first agent running in the second device; the second device sending the first message to a first device in a first domain; the first device receiving the first message; and the first device performing a task according to the first capability information.

[0044] The steps performed by the first device in the third aspect or implementation modes thereof can refer to the first aspect or implementation modes thereof, the steps performed by the second device in the third aspect or implementation modes thereof can refer to the second aspect or implementation modes thereof, the same terms or features in the third aspect or implementation modes thereof as those in the first aspect, implementation modes of the first aspect, the second aspect or implementation modes of the second aspect can refer to the first aspect, implementation modes of the first aspect, the second aspect or implementation modes of the second aspect, and the technical effects of the third aspect or implementation modes thereof can refer to the technical effects in the first aspect, implementation modes of the first aspect, the second aspect or implementation modes of the second aspect, which will not be described herein again.

[0045] In a fourth aspect, a communication apparatus is provided, which is configured to execute the method in any of the above aspects or implementation modes. Specifically, the apparatus can comprise units and / or modules for executing the method in any of the above aspects or implementation modes, such as a processing unit and / or a transceiving unit. The processing unit is configured to perform the processing steps in the method in any of the above aspects or implementation modes. The transceiving unit is configured to perform the transceiving steps in the method in any of the above aspects or implementation modes.

[0046] In an implementation mode, the apparatus is the first device or the second device. When the apparatus is the first device or the second device, the transceiving unit can be a transceiver, or an input / output interface, or a communication interface; and the processing unit can be at least one processor. Optionally, the transceiver is a transceiving circuit. Optionally, the input / output interface is an input / output circuit.

[0047] In another implementation mode, the apparatus is a chip, a chip system or a circuit used in the first device or the second device. When the apparatus is a chip, a chip system or a circuit used in the first device or the second device, the transceiving unit can be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin or related circuit on the chip, the chip system or the circuit; and the processing unit can be at least one processor, a processing circuit or a logic circuit.

[0048] In a fifth aspect, a communication apparatus is provided, which comprises: a memory configured to store a program; and at least one processor configured to execute the computer program or instructions stored in the memory to perform the method in any of the above aspects or implementation modes.

[0049] In an implementation, the apparatus is a first device or a second device.

[0050] In another implementation, the apparatus is a chip, a chip system or a circuit for the first device or the second device.

[0051] In a sixth aspect, a communication apparatus is provided, which comprises at least one processor and a communication interface, the at least one processor being configured to acquire a computer program or instructions stored in a memory through the communication interface, so as to execute the method provided in any one of the aspects or the implementation manners thereof. The communication interface can be implemented by hardware or software.

[0052] In an implementation, the apparatus further comprises the memory.

[0053] In a seventh aspect, a processor is provided, which is configured to execute the method provided in the aspects.

[0054] For the sending and acquiring / receiving operations of the processor, if no special description is made, or if it is not contrary to the actual role or inherent logic in the related description, it can be understood as the output and receiving, input operations of the processor, or the sending and receiving operations performed by the radio frequency circuit and the antenna, which are not limited in the present application.

[0055] In an eighth aspect, a computer readable storage medium is provided, which stores program codes for execution by a device, and the program codes comprise codes for executing the method provided in any one of the aspects or the implementation manners thereof.

[0056] In a ninth aspect, a computer program product containing instructions is provided, which comprises computer programs or instructions, and when the computer programs or instructions are run on a computer, the steps of the method provided in any one of the aspects or the implementation manners thereof are implemented.

[0057] In a tenth aspect, a chip is provided, which comprises a processor and a communication interface, the processor reads instructions stored in a memory through the communication interface, and executes the method provided in any one of the aspects or the implementation manners thereof. The communication interface can be implemented by hardware or software.

[0058] Optionally, as an implementation, the chip further comprises a memory, the memory stores computer programs or instructions, and the processor is configured to execute the computer programs or instructions stored in the memory, and when the computer programs or instructions are executed, the processor is configured to execute the method provided in any one of the aspects or the implementation manners thereof.

[0059] When the method provided in the present application is executed by a chip, the present application does not limit the number of chips that implement the method of the present application, for example, it can be executed by one chip, or two or more chips. Moreover, when the number of chips that implement the method of the present application is two or more, the chip manufacturers are not limited, and can be the same manufacturer or different manufacturers.

[0060] In an eleventh aspect, a communication system is provided, which includes at least one of the first device or the second device described above.

[0061] In a twelfth aspect, a computer program is provided, which, when running on a computer, causes the method provided in any one of the aspects or the implementation manners thereof to be executed. BRIEF DESCRIPTION OF DRAWINGS

[0062] FIG. 1 is a schematic structural diagram of a system architecture to which embodiments of the present application are applicable.

[0063] FIG. 2 is another schematic structural diagram of a system architecture to which embodiments of the present application are applicable.

[0064] FIG. 3 is another schematic structural diagram of a system architecture to which embodiments of the present application are applicable.

[0065] FIG. 4 is a schematic flowchart of a method 400 for communication provided in the present application.

[0066] FIG. 5 is a schematic flowchart of a method 500 for communication provided in the present application.

[0067] FIG. 6 is a schematic flowchart of a method 600 for communication provided in the present application.

[0068] FIG. 7 is a schematic flowchart of a method 700 for communication provided in the present application.

[0069] FIG. 8 is a schematic flowchart of a method 800 for communication provided in the present application.

[0070] FIG. 9 is a schematic flowchart of a method 900 for communication provided in the present application.

[0071] FIG. 10 is a structural schematic diagram of an apparatus provided in an embodiment of the present application.

[0072] FIG. 11 is another structural schematic diagram of an apparatus provided in an embodiment of the present application.

[0073] FIG. 12 is a schematic diagram of a chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] Before introducing the embodiments of the present application, the following explanations are made.

[0075] "Indicative of" or "indicate" can include both direct and indirect indication, or "indicative of" or "indicate" can explicitly and / or implicitly indicate. The first, second, and the like various numerical designations are merely for the convenience of description and do not limit the scope of embodiments of the present application, for example, to distinguish different messages, different information, and the like. "Predefined" can be implemented by pre-storing corresponding codes, tables, or other means for indicating related information in the device, and the present application does not limit the specific implementation manner thereof. The "protocol" referred to can refer to a standard protocol in the communication field, for example, can include a long term evolution (LTE) protocol, a new radio (NR) protocol, and a related protocol applied in a future communication system, and the present application does not limit the same. The words "example", "for example", "exemplary", "as an example", and the like are used to indicate an example, illustration, or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. The terms "include", "contain", "have", and their variants mean "including but not limited to", unless otherwise specifically emphasized. "Multiple" refers to two or more. "And / or", which describes the association relationship of associated objects, means that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or the like means any combination of these items, including any combination of single item or multiple 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. Where a, b, and c can be single or multiple. The description related to the network element A sending a message, information, or data to the network element B, and the network element B receiving the message, information, or data from the network element A, is intended to indicate which network element the message, information, or data is intended to send to, and does not limit whether they are directly sent or indirectly sent via other network elements. "When", "in the case of", "if", and the like all refer to the device making corresponding processing under certain objective circumstances, and are not limited to time, and do not require the device to have a judgment action when implemented, nor does it mean that there are other limitations.

[0076] In addition, the network architecture and service scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of network architecture and the emergence of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0077] The technical solutions of the present application can be applied to various network function virtualization (NFV) systems, which can use a standard formal language to describe the current operator's service technical solutions and network construction schemes and network operation methods as modes and strategies, and implement the technical solutions and construction schemes based on these modes and strategies. For example, the technical solutions of the present application can be applied to one or more of the following systems: a wireless intent driven network (wIDN) system, an experiential networked intelligence (ENI) system, an intent driven management service (IDMS) system, or an open network automation platform (ONAP) system, etc.

[0078] In order to facilitate understanding of the embodiments of the present application, some terms related to the embodiments of the present application are first explained.

[0079] 1. Network management and network management service

[0080] Network management: refers to management of network resources, including but not limited to monitoring, controlling and recording the performance and usage of network resources, and issuing a group of management actions to network resources (such as devices in the network) based on the detected network conditions, so that the network operates effectively. Illustratively, network management can be at least one of monitoring, testing, configuring, analyzing, evaluating or controlling network resources. Network management can also be the ability to report and handle network failures in a timely manner, and coordinate and maintain the efficient operation of the network system. Among them, network resources are the objects of network management, which can also be called network objects or managed entities. Illustratively, network resources can be base station devices, routers, switches, core network devices, etc.

[0081] Network management service: refers to a service that provides network management functions. The producer entity of the service usually provides network management functions to the consumer entity of the service through a network interface (for example, a service based interface).

[0082] 2. Large model

[0083] A large model is used to provide a large model service. A large model refers to a neural network model containing a super large scale of parameters. A large model can also be referred to as a foundation model. Large models play an important role in many fields and applications. Common application scenarios include natural language processing, computer vision, speech recognition and synthesis, recommendation systems, financial risk control, intelligent dialogue systems, game artificial intelligence (AI), and medical health, etc. Large models will evolve towards multi-modal in the future. A multi-modal large model can process data of multiple modalities, for example, a multi-modal large model can process both natural language and text, pictures, or videos, etc.

[0084] A large language model (LLM) is a type of large model, which is a deep learning model trained using a large amount of text data. LLMs can generate natural language text or understand the meaning of language text. LLMs can handle a variety of natural language tasks, such as text classification, question answering, and dialogue, etc.

[0085] 3. Large model application framework

[0086] A large model application framework is a framework for large model application development. Based on components such as models, prompts, and memories, it provides capabilities such as prompt templates, model orchestration, large model services, or security isolation, etc. to help developers achieve a simple, secure, and trusted large model application construction experience.

[0087] 4. Framework and application paradigm of AI agent

[0088] An AI agent can be an intelligent agent instance in a communication device. In this application, an AI agent instance can be generated by a large model application framework based on a large model.

[0089] The AI agent framework can include the following key components:

[0090] 1) Brain: based on a large model, providing storage and decision-making capabilities;

[0091] 2) Perception: responsible for accepting external input, perceiving information from the environment, and providing it to the brain;

[0092] 3) Execution: responsible for executing the action instructions given by the brain, can generate text, call tools and control embodied devices, etc. Among them, embodied devices usually refer to devices with physical form and sensing ability, which can communicate and interact with humans naturally.

[0093] The application paradigm of AI agent can include:

[0094] 1) Machine guard, that is, single agent, which can handle simple tasks;

[0095] 2) Man-machine co-pilot, that is, agent-human interaction, which can handle complex tasks;

[0096] 3) Swarm intelligence, that is, agent-agent interaction, which can handle cross-team collaborative tasks.

[0097] In the embodiments of the present application, the AI agent can also be referred to as agent.

[0098] 5. Interaction and cooperation between AI agents and AI agents

[0099] In the multi-agent architecture based on AI agent, there is interaction and cooperation between AI agents and AI agents. The following takes the wireless base station service failure repair process as an example to simply describe the interaction and cooperation between AI agents and AI agents.

[0100] The wireless base station withdrawal failure involves multiple fields, such as the wireless field, the core network field (such as a cloud core network), the data communication field, the optical field, and the dynamic environment field. The network management system of the wireless field and / or the core network field can be a mobile broadband automation engine (MAE), and the network management system of the data communication field and / or the optical field can be a network cloud engine (NCE). Through the autonomous cooperation of the MAE agent (that is, a wireless intelligent agent) and the NCE agent (that is, a transmission intelligent agent), the positioning and repair of the base station withdrawal failure can be completed. For example, when batch base station withdrawal alarms occur in a certain district of a certain city, maintenance personnel can issue a task to ask the MAE agent and the NCE agent to assist in troubleshooting and solving. After receiving the task, the MAE agent detects that the dynamic environment is normal, and identifies a list of base stations with transmission failures through regular troubleshooting. The MAE agent can provide the list of base stations with transmission failures to the NCE agent to ask the NCE agent to cooperate in troubleshooting. After receiving the list of base stations with transmission failures, the NCE agent can troubleshoot the base stations in the list one by one, generate a work order for the faulty base stations, and repair the faulty base stations. If a base station with non-transmission failure is identified, the NCE agent can provide a list of base stations with non-transmission failure to the MAE agent to ask the MAE agent to troubleshoot the base stations in the list of base stations with non-transmission failure in detail. After receiving the list of base stations with non-transmission failure, the MAE agent can troubleshoot the base stations in the list in detail, generate a work order for the faulty base stations, and troubleshoot the base stations with non-transmission failure. After repairing the base stations with transmission failure, the NCE agent can notify the MAE agent that the base stations with transmission failure have been completely repaired, and the MAE agent confirms the repair result. After the MAE agent confirms that the base stations with transmission failure have been repaired and the base stations with non-transmission failure have also been completely repaired, the positioning and repair process of the base station withdrawal failure ends.

[0101] It should be noted that the above-mentioned "MAE agent" or "NCE agent" can refer to an agent with a wireless base station fault elimination function or capability inside the MAE or NCE. The MAE or NCE can also have other functional or capable agents inside. That is, different agents can be set in the MAE or NCE for different functions or capabilities. The above-mentioned "MAE agent" or "NCE agent" can also refer to an agent representing the MAE or NCE. In addition to having a wireless base station fault elimination function or capability, the agent can also have other functional or capable agents. That is, there is only one agent representing the MAE or NCE inside the MAE or NCE, and the agent can have one or more functions or capabilities.

[0102] The above describes related terms related to the embodiments of the present application. The system architecture to which the embodiments of the present application are applicable is described below with reference to FIGS. 1-3.

[0103] By way of example, FIG. 1 is a schematic structural diagram of a system architecture to which the embodiments of the present application are applicable.

[0104] The system architecture shown in FIG. 1 includes a plurality of network management service production entities (such as network management service production entities 210 and 220). The provider of network management services is referred to as a network management service production entity. The network management service production entity can also be referred to as a network management service providing entity, a network management provider, a management service provider (MnS provider), an intent provider, or an intent handler, a network management service production network element, an intent management service provider, an intent service provider, or a network management service producer, etc. In future communication systems, the network management service production entity can also have other names, which are not particularly limited by the present application. For ease of description, the network management service production entity is referred to as a production entity hereinafter.

[0105] The capabilities or functions of the production entity can be deployed on a network element, which is referred to as a network management service production network element. The capabilities or functions of the production entity can also be deployed on other devices, which are not limited by the embodiments of the present application. The production entity can be a management function, or a management function entity, or a management entity, or a network device, or a network element, etc., which are not limited by the present application. For ease of description, the embodiments of the present application are described by way of example of the production entity, but other devices on which the capabilities or functions of the production entity are deployed can also be used.

[0106] The production entity can include a large model application framework. The large model application framework can be a large model application function module inside the production entity, which is a usage module of a large model instance and can provide functions such as generation of an agent instance and storage of agent local configuration information. The agent instance generated by the large model application framework of the production entity can run in the production entity. The agent instance in the production entity can interact with the agent instance in the production entity of another domain to achieve a business goal. In the present application, the agent instance can also be referred to simply as an agent. As the sender and receiver of the interaction message between agents, the production entity can perform corresponding operations such as sending or updating agent capability information according to the received message, as described below.

[0107] The above entities can be network components in a hardware device, or software functions running on special hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform). It can be understood that the above entities can be implemented by one device, or can be implemented by multiple devices together. In addition, the above entities can also be functional modules within a system, such as a network management system (NMS) or an equipment management system (EMS), or the above entities can also be functional modules within a device, such as one or more functional modules within a network equipment (NE), which can be an access network device or a core network device, etc. As an example, the production entities can be deployed in different EMSs. As another example, the production entities can be deployed in different NEs.

[0108] Embodiments of the present application can be applied to message interaction between agents of different domains.

[0109] Exemplarily, FIG. 2 is another schematic structural diagram of a system architecture to which embodiments of the present application are applicable.

[0110] As shown in FIG. 2, the production entities in multiple domains can be deployed in a centralized structure. In the process of task execution, there is a central decision node, such as production entity 1 of domain 1 in FIG. 2, which internally performs business requirement decomposition and workflow generation and execution through agent_coordinate, and the interaction of messages (such as AgentMessage) between agents of the production entities of each domain is controlled and decided by the agent_coordinate.

[0111] In the central decision point, in addition to running the agent instance of the current domain, the information of the agents of other domains, such as the capability information of the agents of other domains, is also configured. For example, as shown in FIG. 2, in the agent configuration library of production entity 1, in addition to the configuration information of agent_coordinate and agent1 running locally, the capability information of agent2_1 of domain 2 and the capability information of agent3 of domain 3 are also pre-configured, so as to coordinate the agents by agent_coordinate.

[0112] The domain where the central decision point is located can be referred to as a master domain, and the domains where the other production entities are located can be referred to as slave domains.

[0113] It should be noted that the central decision point in the system architecture can be different for different tasks. For example, the production entity receiving the task can serve as the central decision point. It should also be noted that the production entity serving as the central decision point can be at the same level as other production entities, or can be at a higher level than other production entities, such as a high-level production entity with a global perspective, and no specific limitation is made in this regard.

[0114] Exemplarily, FIG. 3 is another schematic structural diagram of a system architecture to which the embodiments of the present application are applicable.

[0115] As shown in FIG. 3, the production entities in the multiple domains can be deployed in a decentralized structure. During task execution, there is no central decision node among the production entities in the multiple domains, and the agents in each production entity freely negotiate task decomposition, generate a workflow and execute it, during which the agents of the production entities in each domain freely send messages (such as AgentMessage) for collective business control and decision-making.

[0116] It should be noted that the agent system of each domain can receive a northbound task and become the initiator of the agent collaboration process, and therefore the agent system of each domain can be preconfigured with the information (such as capability information) of the agent for cross-domain collaboration and the agents of other domains.

[0117] The scheme of the present application can also be applied to other systems containing corresponding entities, and the present application does not make any limitation.

[0118] Currently, in the cross-domain agent collaboration process, each agent performs task decomposition, allocation and coordination based on local configuration and in combination with the workflow of the relevant task. This approach has the following disadvantages:

[0119] 1) Local configuration information is outdated, resulting in a reduced probability of successful task execution

[0120] Taking the centralized structure as an example, the agent_coordinate of the master domain generates the workflow based on the configuration information of the agents of the slave domain configured locally, and completes the decomposition, allocation and coordination of the task. When the configuration information of other agents in the agent configuration library of the master domain is aging, such as the capability of a certain agent is strengthened but the master domain is not aware, it will lead to unreasonable workflow generated by the agent_coordinate, and further lead to the probability of successful task execution is reduced. For example, in the base station off-service diagnosis use case, the capability information of the SPN fault diagnosis agent of the slave domain is pre-configured in the master domain. Subsequently, the SPN fault diagnosis agent in the slave domain has the capability of processing "PTN clock single board fault" after being strengthened, and using this capability requires providing "three-party agent" information (such as the information of the alarm diagnosis agent of the core network) for the SPN fault diagnosis agent in the workflow additionally, but the master domain is not aware of the change, that is, the capability information of the SPN fault diagnosis agent in the agent configuration library of the master domain is not updated in time, which will lead to that the PTN clock single board fault diagnosis cannot be completed effectively.

[0121] 2) The newly added agent information needs to be manually configured in each domain, which is very costly

[0122] As described above, the agent system of each domain is configured with the information (such as capability information) of the "cross-domain cooperation" agent and the agent of other domains. Therefore, when a new agent of a certain function is added in a certain domain, according to the current mode, manual configuration of the new agent needs to be performed for each domain, and the relationship between the existing agent and the new agent needs to be updated, which is very costly. For example, the "SPN fault diagnosis agent" is added in the NCE domain, which needs to be manually configured in the wireless domain and the core network domain.

[0123] From the above, it can be seen that the current configuration information perception between the agents across the domains is mainly based on local pre-configuration and manual configuration. The local pre-configuration mode will lead to the probability of successful task execution is reduced, and the cost of manual configuration is very high.

[0124] In view of the above problems, the embodiments of the present application provide a method and a communication device for communication, so as to improve the probability of successful task execution and reduce the system maintenance cost.

[0125] The method embodiments of the present application are described below.

[0126] FIG. 4 is a schematic flowchart of the method 400 for communication provided by the present application.

[0127] The method shown in FIG. 4 can be performed by a first device in a first domain and a second device in a second domain. Unless otherwise specified, the "first device" or the "second device" can refer to the first device or the second device itself, a component (e.g., a processor, a chip, or a chip system, etc.) in the first device or the second device, or a logic module or software capable of implementing all or part of the functions of the first device or all or part of the functions of the second device.

[0128] The method 400 includes at least part of the following.

[0129] At step 401, the second device in the second domain generates a first message.

[0130] The first message includes first capability information of a first agent running in the second device.

[0131] The first capability information of the first agent includes a capability supported by the first agent and information of an agent associated with the capability of the first agent. The capability supported by the first agent can be one capability or multiple capabilities. When the capability supported by the first agent is multiple capabilities, the first capability information can include information of an agent associated with each capability. For example, the capability supported by the first agent is capability 1 and capability 2, and the first capability information includes capability 1 and information of an agent associated with the capability 1 of the first agent, and capability 2 and information of an agent associated with the capability 2 of the first agent.

[0132] The agent associated with the capability of the first agent can also be replaced by an agent cooperating with the first agent to complete a task related to the capability. The task related to the capability can be understood as a task implemented based on the capability. For example, agent 1 supports a "clock board fault diagnosis" capability, a "clock board fault diagnosis" task is based on the "clock board fault diagnosis" capabilities of agent 1, agent 2, and agent 3, and is completed through the cooperation of agent 1, agent 2, and agent 3. In this case, the agent associated with the "clock board fault diagnosis" capability of agent 1 is agent 2 and agent 3.

[0133] Embodiments of the present application do not limit the implementation of the first capability information. As an example, the first capability information can include: a capability identifier and an agent list. The capability identifier is used to uniquely determine a capability, such as the name of the capability or the ID of the capability. The agent list is a list of identifiers of agents associated with the capability of the first agent. The identifier of the agent is used to uniquely determine an agent, such as the name of the agent or the ID of the agent, etc. For example, the agent 1 supports the "clock board fault diagnosis" capability, and the agents associated with the "clock board fault diagnosis" capability of the agent 1 are the agent 2 and the agent 3. In this case, the capability identifier can be the capability name "clock board fault diagnosis", and the agent list can include the identifier of the agent 2 and the identifier of the agent 3.

[0134] Embodiments of the present application do not limit the division manner of the domain. For example, the domain can be divided according to the business, and different domains can correspond to different businesses. For another example, the domain can be divided according to the geographical area, and different domains correspond to different geographical areas.

[0135] Step 402, the second device sends a first message to the first device in the first domain. Correspondingly, the first device receives the first message from the second device.

[0136] Step 403, the first device performs a task according to the first capability information of the first agent.

[0137] Exemplarily, the first device can perform task decomposition, allocation and coordination according to the first capability information of the first agent, generate a workflow, and complete the task according to the workflow.

[0138] In the method 400, the first device and the second device can realize the interaction of the capability information of the agent across the domains through the message, thereby supporting the update of the capability information of the agent across the domains, so that the first device can perform the task based on the latest capability information of the agent, which helps to improve the probability of successful task execution.

[0139] In some implementations, the second device can actively send the first message to the first device. Exemplarily, the second device can actively send the first message to the first device in the case that the capability of the first agent changes, so as to provide the first device with the changed capability information of the first agent. In this case, step 401 specifically includes: when the capability of the first agent changes, the second device generates the first message according to the changed capability of the first agent. Exemplarily, the second device can periodically send the latest capability information of the first agent to the first device.

[0140] In some implementations, the first device can request the capability information of the agent from the second device. In this case, the method 400 can further include step 402: the first device sends a second message to the second device, and the second device receives the second message from the first device, where the second message is used to request the capability information of the agent. Step 401 specifically includes: the second device generates the first message according to the second message.

[0141] Embodiments of the present application do not limit the timing of the first device sending the second message. As an example, the first device can periodically request the capability information of the agent from the second device, in which case step 404 specifically includes: the first device periodically sends the second message to the second device. As another example, the first device can request the capability information of the agent from the second device on demand, for example, the first device discovers that the capability information of the first agent is outdated when orchestrating a task, and the first device can request the capability information of the agent from the second device. In this case, step 404 specifically includes: the first device sends the second message to the second device when orchestrating a task.

[0142] In some implementations, the first device can request the capability information of one or more specified agents from the second device through the second message. In this case, the second message can include the identity of the one or more agents to indicate to the second device which capability information of which agents is requested. For example, the second message includes the identity of the first agent, which can indicate that the first device requests the capability information of the first agent from the second device. In this case, step 401 specifically includes: the second device obtains the first capability information of the first agent according to the identity of the first agent in the second message; and the second device generates the first message according to the first capability information of the first agent.

[0143] In some implementations, the second message further includes a second communication type, the second communication type being used to indicate that the second message is used to request the capability information of the agent. In other words, the second message can be a capability request type in an AgentMessage, such as a capabilityRequest type, an abilityRequest type, a capability type, or an ability type. Through the second communication type, the second device can know that the first device is requesting the capability information of the agent.

[0144] In some implementations, the second message further includes a second communication type, the second communication type being used to indicate that the second message is used to request the capability information of the agent. In other words, the second message can be a capability request type in an AgentMessage, such as a capabilityRequest type, an abilityRequest type, a capability type, or an ability type. Through the second communication type, the second device can know that the first device is requesting the capability information of the agent.

[0145] In some implementations, the first message further includes the first information and / or the information of the second domain. The first information is used to indicate a cross-domain configuration, for example, the first information can be a bit of information, when the value of the bit is 1, it represents a cross-domain configuration, and when the value of the bit is 0, it represents a local configuration. The information of the second domain can be the name or ID of the second domain. By carrying the first information and / or the information of the second domain in the first message, the receiving end device of the first message can know that the first capability information of the first agent is the capability information of the first agent of another domain, so that the receiving end device of the first message can perform related operations for cross-domain, for example, the receiving end device of the first message can store the first capability information in a storage area for cross-domain, for example, the receiving end device of the first message can simplify the content of storage (such as not storing general information related to the first agent, such as information based on a large model, scene, tool set, knowledge base, deployment mode, etc.), for example, the receiving end device of the first message can store the first capability information but not generate an instance of the first agent, etc.

[0146] In some implementations, the first message further includes second information, the second information being used to indicate that the first message is from the first agent and is sent to a second agent, the second agent being running in the first device. The first capability information is explicitly indicated as from the first agent and sent to the second agent in the first device through the second information, so that the second agent performs the task based on the first capability information. In this case, the step 403 specifically includes that the second agent performs the task according to the first capability information.

[0147] Embodiments of the present application do not limit the implementation of the second information. For example, the second information can include a sendFrom field and a sendTo field, the sendFrom field being used to carry the identity of the first agent, and the sendTo field being used to carry the identity of the second agent.

[0148] It should be noted that when the second device actively sends the first message to the first device, the first message includes the second information. When the second device sends the first message to the first device based on the request of the first device, the first message can not include the second information, or can not include the second information. When the first message does not include the second information, the first message can further include the identity of the first agent, to indicate to the first device that the capability information in the first message is the capability information of the first agent.

[0149] In some implementations, the first message further includes a first communication type, the first communication type being used to indicate that the first message is used to update the capability information of the agent. In other words, the first message can be a capability update type in an agent type message (AgentMessage), such as a capabilityUpdate type, an abilityUpdate type, a capability type or an ability type. Through the first communication type, the first device can know that the second device is updating the capability information of the agent. In this case, the method 400 further includes that the first device updates the locally stored capability information of the first agent to the first capability information received in the step 402 according to the first message.

[0150] It should be noted that when the second device actively sends the first message to the first device, the first message can include the first communication type. When the second device sends the first message to the first device based on the request of the first device, the first message can not include the first communication type, or can not include the first communication type.

[0151] In some implementations, the first domain where the first device is located is a master domain, and the second domain where the second device is located is a slave domain of the first domain. In other words, embodiments of the present application are applicable to a centralized structure scenario as shown in FIG. 2. In the centralized structure scenario, the devices or agents of each slave domain send the first messages to the devices or agents of the master domain, and the devices or agents of the master domain send the second messages to the devices or agents of each slave domain. For example, the first domain is domain 1 shown in FIG. 2, the first device is a production entity in domain 1, the second agent is agent coordinate in domain 1, the second domain is domain 2 or domain 3 in FIG. 2, the second device is a production entity in domain 2 or domain 3, the first agent is agent2_1 in domain 2 or agent3 in domain 3.

[0152] In some other implementations, the first domain where the first device is located is on the same level as the second domain where the second device is located. In other words, embodiments of the present application are applicable to a decentralized structure scenario as shown in FIG. 3. In the decentralized structure scenario, the devices or agents of each domain can send the first messages or the second messages to each other. For example, the first domain is domain 1 shown in FIG. 3, the first device is a production entity in domain 1, the second agent is agent1 in domain 1, the second domain is domain 2 in FIG. 3, the second device is a production entity in domain 2, and the first agent is agent2 in domain 2. For another example, the first domain is domain 1 shown in FIG. 3, the first device is a production entity in domain 1, the second agent is agent1 in domain 1, the second domain is domain 3 in FIG. 3, the second device is a production entity in domain 3, and the first agent is agent3 in domain 3.

[0153] The following describes the updating scheme of the capability information of the specified agent in the centralized structure scenario.

[0154] FIG. 5 is a schematic flowchart of a method 500 for communication provided by the present application. The MnS producer 1, the MnS producer 2, the message #1, and the message #2 in the method 500 can correspond to the first device of the first domain, the second device of the second domain, the second message, and the first message respectively. In the method 500, the MnS producer 1 is taken as an example of the central decision point, and domain 2 is one of the slave domains. FIG. 5 takes an agent as an AI agent for example.

[0155] In the method shown in FIG. 5, the MnS producer 2 sends the capability information of one or more agents specified by the MnS producer 1 to the MnS producer 1 based on the request of the MnS producer 1, so that the MnS producer 1 updates the corresponding agent capability information.

[0156] At step 501, the AI agent management module of the MnS producer 1 in the domain 1 sends a message #1 to the AI agent management module of the MnS producer 2 in the domain 2, and correspondingly, the AI agent management module of the MnS producer 2 receives the message #1 sent by the AI agent management module of the MnS producer 1.

[0157] The message #1 is used to request the capability information of the specified agent.

[0158] Exemplarily, the message #1 can include an AgentMessage instance constructed based on a general service interface (e.g., creatMOI), where the AgentMessage instance can include the information of the specified agent. Exemplarily, the message #1 can be a capability request message. Table 1 is an example of the correspondence between the general service and the large model related information model.

[0159] Table 1: Correspondence between general service and large model related information model

[0160] Exemplarily, the AgentMessage instance can include a session identifier, a sendFrom field, a sengTo field, and a commuType field. The session identifier is used to uniquely identify a session between two agents. The sendFrom field is used to carry the information of the agent requesting the capability information, such as the identification information of the agent, e.g., the name of the agent or the ID of the agent. The sengTo field is used to carry the information of the specified agent(s), such as the identification information of the agent, e.g., the name of the agent or the ID of the agent. The commuType field is used to carry the communication type, e.g., the capability request type (capabilityRequest type, abilityRequest type, capability type, or ability type). It should be noted that the capability request type can be replaced by other names as long as it is used to represent the capability request. Table 2 is an example of the structure of the AgentMessage instance, where M represents mandatory, CM represents conditional mandatory, and T represents true.

[0161] Table 2: Structure of AgentMessage instance

[0162] Exemplarily, an example of the information included in the AgentMessage instance can be as follows:

[0163] In this example, the session identifier is 1, the agent2 is requested to specify the capability information, and the communication type is the capability request type.

[0164] At step 502, the AI Agent management module of the MnS producer 2 sends a message #2 to the AI Agent management module of the MnS producer 1, and correspondingly, the AI agent management module of the MnS producer 1 receives the message #2 sent by the AI agent management module of the MnS producer 2.

[0165] In this example, the session identifier is 1, the agent2 is requested to specify the capability information, and the communication type is the capability request type.

[0166] In a possible implementation, after receiving the request message in step 501, the AI agent management module of the MnS producer 2 extracts the information in the To field in the AgentMessage instance, and based on the extracted information, sends the local latest capability information of the specified one or more agents to the AI agent management module of the MnS producer 1.

[0167] In a possible implementation, the capability information of the specified one or more agents can be transmitted through an agent-related information model. For example, the agent-related information model can be an AgentEntity information model. The agent-related information model can be a structured information model. The agent-related information model can also be referred to as an agent-related structure, such as an AgentEntity structure.

[0168] For example, the AgentEntity information model can include two parts, a general attribute and an enhanced attribute, and the details are as follows.

[0169] 1) General attribute

[0170] The general attributes can include some or all of the following information: agent identification (agentID), domain, agent name (agentName), Chinese name of the agent (chineseName), description, ability, information of the underlying model (e.g., LLM), scenario, tool set, knowledge base, deployment mode, external API, or version.

[0171] 2) Enhancement attributes

[0172] The enhancement attributes can include some or all of the following information: type, or external agent list. By way of example, Table 3 shows one structure of the enhancement attributes, where M denotes mandatory, CM denotes conditional mandatory, and T denotes true.

[0173] Table 3 Structure of enhancement attributes

[0174] The type is used to indicate whether the specified one or more agents are local running agents or cross-domain configured agents, so that the AI Agent Management Module of the MnS Producer 1 performs corresponding processing, such as if the type indicates that the specified one or more agents are local running agents, then after receiving the capability information of the specified one or more agents, generating or updating the corresponding agent instance based on the received information, and for example, if the type indicates that the specified one or more agents are cross-domain configured agents, then after receiving the capability information of the specified one or more agents, generating or updating the capability description of the corresponding agent in the agent configuration library based on the received information.

[0175] The external agent list is used to record a list of other agents associated with the agent capability for task orchestration. For example, the external agent list can include: a capability name and a list of agents corresponding to the capability name, the agents in the agent list are associated with the capability corresponding to the capability name, the agent list can include information of one or more agent instances, specifically, the agent can record the unique identification information of the one or more agents, such as the name of the agent (agent name) or the ID of the agent (agent ID). For example, Table 4 shows one structure of the external agent list, where CM represents conditional mandatory, and T represents true.

[0176] Table 4 Structure of external agent list

[0177] For example, one example of the information included in the AgentEntity information model can be as follows:

[0178] In this example, the ID of the specified agent is 1, the domain where the specified agent is located is the NCE domain, the name of the specified agent is agent2, the configuration type is cross-domain configuration, the capability name is clock board fault diagnosis, and the other agents associated with the clock board fault diagnosis capability are agent3 and agent4.

[0179] After receiving the message #2 sent by the MnS producer 2, the AI agent management module of the MnS producer 1 can update the capability information of the corresponding agent based on the message #2.

[0180] In the method shown in FIG. 5, an AgentMessage message of a capability request type is introduced, and an agent that needs to update capability information can be specified. The capability information of the agent returned by the MnS producer 2 carries, for each capability possessed by the agent, a list of other agents associated with the capability, thereby completing the update of the capability information of the specified agent in the MnS producer 1. The method shown in FIG. 5 can effectively help the agent_coordinate in the main domain to generate a workflow and improve the success probability of task execution by introducing a capability update mechanism between agents across domains.

[0181] The following describes a capability information update scheme of a full-amount agent, taking a centralized structure scenario as an example.

[0182] FIG. 6 is a schematic flowchart of a method 600 for communication provided by the present application. The MnS producer 1, the MnS producer 2, the message #3, and the message #4 in the method 600 can correspond to the first device of the first domain, the second device of the second domain, the second message, and the first message respectively. In FIG. 6, the MnS producer 1 is taken as an example of a central decision node, and the domain 2 is taken as an example of one of the domains. In FIG. 6, an agent is taken as an example of an AI agent.

[0183] In the method shown in FIG. 6, the MnS producer 2 sends, to the MnS producer 1, capability information of all agents running in the MnS producer 2 based on a request of the MnS producer 1, so that the MnS producer 1 updates the corresponding agent capability information.

[0184] In step 601, the AI agent management module of the MnS producer 1 in the domain 1 sends a message #3 to the AI agent management module of the MnS producer 2 in the domain 2. Correspondingly, the AI agent management module of the MnS producer 2 receives the message #3 sent by the AI agent management module of the MnS producer 1.

[0185] Step 601 can refer to step 501, except that the message #3 is used to request capability information of all agents running in the MnS producer 2. Instead of specifying one or more agents, the message #3 requests capability information of all agents, for example, the to field can be set as “all”, so that the MnS producer 2 can know that capability information of all agents needs to be fed back according to the message #3.

[0186] Exemplarily, an example of information included in the AgentMessage instance in step 601 can be as follows:

[0187] In this example, the session identifier is 1, the agent coordinate requests the full amount of agent capability information, and the communication type is the capability request type.

[0188] At step 602, the AI Agent management module of the MnS producer 2 sends a message #4 to the AI Agent management module of the MnS producer 1, and correspondingly, the AI agent management module of the MnS producer 1 receives the message #4 sent by the AI agent management module of the MnS producer 2.

[0189] Step 602 can refer to step 502, except that the message #4 includes the capability information of all agents running in the MnS producer 2. Exemplarily, the message #4 can include the capability name of each agent and an agent list, and the agents in the agent list are associated with the capability corresponding to the capability name.

[0190] In a possible implementation, after receiving the request message in step 601, the AI agent management module of the MnS producer 2 extracts the information in the to field in the AgentMessage instance, and based on the extracted information, sends the local latest capability information of all agents to the AI agent management module of the MnS producer 1.

[0191] The transmission manner of the capability information of the agent can refer to step 502, except that the AgentEntity information model can include the external agent list corresponding to each agent running in the MnS producer 2.

[0192] Exemplarily, one example of the information included in the AgentEntity information model can be as follows:

[0193] The agentID field is used for the ID of the agent, the domain field is used for the information of the domain where the agent is located, the name field is used to carry the name of the agent, the type field is used to carry the configuration type, the ability field in the externalAgentsList field is used to carry the ability name, and the requiredAgentIndicates field in the externalAgentsList field is used to carry the agent list corresponding to the ability name. In this example, the ID of the first agent is 1, the domain where the first agent is located is the NCE domain, the name of the first agent is agent2_1, the configuration type is cross-domain configuration, the ability name is clock board fault diagnosis, the other agents associated with the clock board fault diagnosis capability are agent3 and agent4, the ID of the second agent is 2, the domain where the second agent is located is the NCE domain, the name of the second agent is agent2_2, the configuration type is cross-domain configuration, the ability name is ability2, and the other agent associated with the ability2 is agent5, the ID of the third agent is 3, the domain where the third agent is located is the NCE domain, the name of the third agent is agent2_3, the configuration type is cross-domain configuration, the ability name is ability3, and the other agent associated with the ability3 is agent6.

[0194] After receiving the message #4 sent by the MnS producer 2, the AI agent management module of the MnS producer 1 can update the capability information of the corresponding agent based on the message #4.

[0195] In the method shown in FIG. 6, an AgentMessage message of the capability request type is introduced, and the update of the capability information of all agents is represented by assigning the sendTo field to “all”. The MnS producer 2 returns the capability information of all agents, wherein for each capability possessed by an agent, the list of other agents associated with the capability is carried at the same time, thereby completing the update of the capability information of the corresponding agent in the MnS producer 1. The method shown in FIG. 6 can effectively help the agent_coordinate in the main domain to generate a workflow and improve the success probability of task execution by introducing the capability update mechanism between agents in different domains.

[0196] Next, the update scheme of the capability information of a specified agent is described by taking a decentralized structure scenario as an example.

[0197] FIG. 7 is a schematic flow chart of a method 700 for communication provided by the present application. The MnS producer 1 in the method 700 can correspond to the first device of the first domain above, the MnS producer 2 can correspond to the second device of the second domain above, the MnS producer 2 can correspond to the second device of the second domain above when interacting with the MnS producer 1, and the MnS producer 2 can correspond to the first device of the first domain above when interacting with the MnS producer 3. The message #5, the message #7 can correspond to the second message above, and the message #6, the message #8 can correspond to the first message above. FIG. 7 takes the AI agent as an example.

[0198] In the method shown in FIG. 7, the MnS producer 3 sends the MnS producer 2 the capability information of one or more agents specified by the MnS producer 2 based on the request of the MnS producer 2, and the MnS producer 2 sends the MnS producer 1 the capability information of one or more agents specified by the MnS producer 1 based on the request of the MnS producer 1.

[0199] Step 701, the AI agent management module of the MnS producer 1 in the domain 1 sends the message #5 to the AI agent management module of the MnS producer 2 in the domain 2, and correspondingly, the AI agent management module of the MnS producer 2 receives the message #5 sent by the AI agent management module of the MnS producer 1.

[0200] In this example, the message #5 is used to request the capability information of the specified agent.

[0201] Step 701 can refer to step 501, except that the agent indicated by the from field included in the message #5 is not the agent_coordinate responsible for control and decision, but the agent equal to the agent.

[0202] Exemplarily, one example of the information included in the AgentMessage instance in step 701 can be as follows:

[0203] In this example, the session identifier is 1, the agent 1 requests the capability information of the specified agent 2, and the communication type is the capability request type.

[0204] Step 702, the AI agent management module of the MnS producer 2 sends the message #6 to the AI agent management module of the MnS producer 1, and correspondingly, the AI agent management module of the MnS producer 1 receives the message #6 sent by the AI agent management module of the MnS producer 2.

[0205] Step 702 can refer to step 502, which will not be described in detail here.

[0206] Step 703, the AI agent management module of the MnS producer 2 in the domain 2 sends a message #7 to the AI agent management module of the MnS producer 3 in the domain 3, and correspondingly, the AI agent management module of the MnS producer 2 receives the message #7 sent by the AI agent management module of the MnS producer 1.

[0207] In this example, the message #7 is used to request the capability information of the specified agent.

[0208] Step 703 can refer to step 501, except that the agent indicated by the from field in the message #7 is not the agent_coordinate responsible for control and decision, but an agent equal to the agent.

[0209] Exemplarily, an example of the information included in the AgentMessage instance in step 703 can be as follows:

[0210] In this example, the session identifier is 2, the agent 2 requests the capability information of the specified agent 3, and the communication type is the capability request type.

[0211] Step 704, the AI Agent management module of the MnS producer 3 sends a message #8 to the AI Agent management module of the MnS producer 2, and correspondingly, the AI agent management module of the MnS producer 2 receives the message #8 sent by the AI agent management module of the MnS producer 3.

[0212] Step 704 can refer to step 502, which will not be described in detail here.

[0213] In the method shown in FIG. 7, the AgentMessage message of the capability request type is introduced, and the agent whose capability information needs to be updated can be specified. In the capability information of the agent returned by the MnS producer in each domain, for the capability possessed by the agent, the list of other agents associated with the capability will be carried at the same time, so as to complete the update of the capability information of the agent between the MnS producers in each domain. The method shown in FIG. 7 helps to generate a more reasonable workflow and improve the success probability of task execution by introducing the capability update mechanism between the agents across the domains.

[0214] Next, taking the centralized structure scenario as an example, the update scheme of the capability information of the intelligent agent using the polling mechanism is described.

[0215] FIG. 8 is a schematic flow chart of a method 800 for communication provided by the present application. The MnS producer 1 in the method 800 can correspond to the first device of the first domain above, and the MnS producer 2, the MnS producer 3 can correspond to the second device of the second domain above. The message #3, the message #9 can correspond to the second message above, and the message #4, the message #10 can correspond to the first message above. In FIG. 8, the decision point centered on the MnS producer 1 is taken as an example, and the domain 2 and the domain 3 are taken as two from the domains. FIG. 8 takes the AI agent as an example.

[0216] In the method shown in FIG. 8, the MnS producer 1 periodically sends a capability update request to the MnS producer 2 and the MnS producer 3 to realize the polling update of the capability information of the specified agent.

[0217] Step 801, the AI agent management module of the MnS producer 1 periodically sends a message #3 to the AI agent management module of the MnS producer 2 in the domain 2, and correspondingly, the AI agent management module of the MnS producer 2 receives the message #3 sent by the AI agent management module of the MnS producer 1. Wherein, the message #3 is used to request the capability information of the specified agent. Step 802 can refer to step 601, which will not be described here in detail.

[0218] Step 802, the AI agent management module of the MnS producer 2 sends a message #4 to the AI agent management module of the MnS producer 1, and correspondingly, the AI agent management module of the MnS producer 1 receives the message #4 sent by the AI agent management module of the MnS producer 2. Wherein, the message #4 includes the capability information of the target agent. Step 803 can refer to step 602, which will not be described here in detail.

[0219] Step 803, the AI agent management module of the MnS producer 1 periodically sends a message #9 to the AI agent management module of the MnS producer 3 in the domain 3, and correspondingly, the AI agent management module of the MnS producer 2 receives the message #9 sent by the AI agent management module of the MnS producer 1. Wherein, the message #9 is used to request the capability information of the specified agent. Step 803 can refer to step 601, which will not be described here in detail.

[0220] At step 804, the AI Agent management module of the MnS producer 3 sends a message #10 to the AI Agent management module of the MnS producer 1, and accordingly, the AI agent management module of the MnS producer 1 receives the message #10 sent by the AI agent management module of the MnS producer 3. The message #10 includes the capability information of the target agent. The step 804 can refer to the step 602, and will not be described in detail here.

[0221] After receiving the message #10 sent by the MnS producer 3, the AI agent management module of the MnS producer 1 can update the capability information of the corresponding agent based on the message #10.

[0222] The embodiments of the present application do not limit the sequence of the steps 801 and 803.

[0223] The method shown in FIG. 8 can realize the periodic polling of the agent capability information of the dependent node by the central decision node, so as to realize the update of the capability information of the agent of the other domain in the MnS producer 1. The method shown in FIG. 8 can effectively help the agent_coordinate of the master domain to generate the workflow and improve the success probability of the task execution by introducing the capability update mechanism between the agents across the domains.

[0224] The update scheme of the capability information of the intelligent agent using the active reporting mechanism will be described below.

[0225] FIG. 9 is a schematic flowchart of a method 900 for communication provided by the present application. The MnS producer 1 and the MnS producer 2 in the method 900 can correspond to the first device of the first domain and the second device of the second domain respectively, and the message #11 can correspond to the first message.

[0226] In the method shown in FIG. 9, the MnS producer 2 actively sends the updated capability information of the agent to the MnS producer 1 in the case that the capability information of the agent in the MnS producer 2 is updated, so as to update the corresponding agent capability information by the MnS producer 1. The method shown in FIG. 9 is applicable to both the centralized scenario and the decentralized scenario. FIG. 9 takes the intelligent agent as an example of the AI agent.

[0227] At step 901, the capability of the agent 2 in the MnS producer 2 is updated.

[0228] At step 902, the AI Agent management module of the MnS producer 2 sends a message #11 to the AI Agent management module of the MnS producer 1, and accordingly, the AI agent management module of the MnS producer 1 receives the message #11 sent by the AI agent management module of the MnS producer 2.

[0229] The message #11 includes the capability information of the agent that has the capability update. For example, the message #11 can include an AgentMessage instance that is constructed based on a general service interface (e.g., creatMOI), and the AgentMessage instance can include the capability information of the agent that has the capability update. For example, the message #11 can be a capability update message.

[0230] The AgentMessage instance can include a session identifier, a from field, a to field, a communication type field, and an agent-related information model. The session identifier is used to uniquely identify a session between two agents. The from field is used to carry the information of the agent that requests the capability information, such as the identification information of the agent, e.g., the name or the ID of the agent. The to field is used to carry the information of the specified agent or agents, such as the identification information of the agent, e.g., the name or the ID of the agent. In the method 900, the agent indicated by the to field can be a certain agent or agents that are pre-configured to report. The communication type field is used to carry the communication type, such as the capability update type (capabilityUpdate type, abilityUpdate type, capability type, or ability type). It should be noted that the capability update type can be replaced by other names as long as it is used to represent the capability update. The agent-related information model can refer to the related description in step 501, and will not be described in detail.

[0231] For example, one example of the information included in the AgentMessage instance can be as follows:

[0232] In this example, the agentID of the agent that has the capability update is 1, the domain in which the agent that has the capability update is located is the NCE domain, the name of the agent that has the capability update is agent2, the configuration type is the cross-domain configuration, the capability name is the clock board fault diagnosis, and the other agents associated with the clock board fault diagnosis capability are agent3 and agent4.

[0233] After receiving the message #11 sent by the MnS producer 2, the AI agent management module of the MnS producer 1 can update the capability information of the corresponding agent based on the message #11.

[0234] In some other implementations, the method can further include step 903, which is specifically as follows.

[0235] Step 903, the AI agent management module of the MnS producer 1 sends a message #12 to the AI agent management module of the MnS producer 2 to inform the AI agent management module of the MnS producer 2 that the update of the capability information of the agent is completed.

[0236] Exemplarily, the message #12 can include a response for the AgentMessage instance in the message #11.

[0237] In addition, for which MnS producer(s) the MnS producer 2 reports the updated agent capability information to, it can be configured in the MnS producer 2.

[0238] In the method shown in FIG. 9, the AgentMessage message of the capability update type is introduced. When the capability information of an agent in a certain domain MnS producer changes, the updated information can be reported to the target domain, so that the MnS producer of the target domain updates the capability information of the corresponding agent. The method shown in FIG. 9 helps to generate a more reasonable workflow and improve the success probability of task execution by introducing the capability update mechanism between agents across domains.

[0239] The method embodiments provided by the present application are described in detail above in combination with FIGS. 1 to 9. The device embodiments of the present application will be described below in combination with FIGS. 10 to 12.

[0240] It can be understood that, in order to implement the functions in the above embodiments, the devices in FIGS. 10 to 12 include the hardware structure and / or software modules for performing the respective functions. Those skilled in the art should easily realize that, in combination with the embodiments disclosed in the present application, the units and method steps of the examples described in the present application can be realized in the form of hardware or a combination of hardware and computer software.

[0241] FIGS. 10 and 11 are structural schematic diagrams of possible devices provided by the embodiments of the present application. These devices can be used to implement the functions of the first device or the second device in the above method embodiments, and thus can also achieve the beneficial effects possessed by the above method embodiments.

[0242] As shown in FIG. 10, the device 10 includes a transceiver unit 11 and a processing unit 12.

[0243] When the apparatus 10 is configured to implement the functions of the first device in the above method embodiments, the transceiver unit 11 is configured to perform the transceiving steps of the first device, such as steps 402, 407, 501, 502, 601, 602, 701, 702, 703, 704, 801, 802, 803, 804, 902 or 903, and the processing unit 12 is configured to perform the processing steps of the first device, such as step 403. When the apparatus 10 is configured to implement the functions of the second device in the above method embodiments, the transceiver unit 11 is configured to perform the transceiving steps of the second device, such as steps 402, 404, 501, 502, 601, 602, 701, 702, 703, 704, 801, 802, 803, 804, 902 or 903, and the processing unit 12 is configured to perform the processing steps of the second device, such as steps 401 or 901.

[0244] For more details of the transceiver unit 11 and the processing unit 12, please refer to the descriptions in the above method embodiments, which will not be repeated here.

[0245] As shown in FIG. 11, the apparatus 20 includes a processor 21. The processor 21 is coupled with a memory 23, which is configured to store instructions. When the apparatus 20 is configured to implement the above method, the processor 21 is configured to execute the instructions in the memory 23 to implement the functions of the processing unit 12.

[0246] Optionally, the apparatus 20 further includes the memory 23.

[0247] Optionally, the apparatus 20 further includes an interface circuit 22. The processor 21 and the interface circuit 22 are coupled with each other. It can be understood that the interface circuit 22 can be a transceiver or an input / output interface. When the apparatus 20 is configured to implement the above method, the processor 21 is configured to execute the instructions to implement the functions of the processing unit 12, and the interface circuit 22 is configured to implement the functions of the transceiver unit 11.

[0248] For example, when the apparatus 20 is a chip applied to the first device or the second device, the chip implements the functions of the first device or the second device in the above method embodiments. The chip receives information from other modules (such as a radio frequency module or an antenna) in the first device or the second device, and the information is sent by other devices to the first device or the second device; or the chip sends information to other modules (such as a radio frequency module or an antenna) in the first device or the second device, and the information is sent by the first device or the second device to other devices.

[0249] FIG. 12 is a schematic diagram of a chip system 30 according to an embodiment of the present application. The chip system 30 (or also referred to as a processing system) includes a logic circuit 31 and an input / output interface 32.

[0250] The logic circuit 31 can be a processing circuit in the chip system 30. The logic circuit 31 can be coupled to a storage unit, and invoke instructions in the storage unit, so that the chip system 30 can implement the methods and functions of the embodiments of the present application. The input / output interface 32 can be an input / output circuit in the chip system 30, and output processed information of the chip system 30, or input data or signaling information to be processed into the chip system 30 for processing.

[0251] As an option, the chip system 30 is configured to implement the operations performed by the first device or the second device in the above method embodiments.

[0252] For example, the logic circuit 31 is configured to implement the processing-related operations performed by the first device or the second device in the above method embodiments; and the input / output interface 32 is configured to implement the sending and / or receiving-related operations performed by the first device or the second device in the above method embodiments.

[0253] The present application also provides a communication apparatus, including a processor and a memory. The memory is configured to store computer programs or instructions and / or data. The processor is configured to execute the computer programs or instructions stored in the memory, or read the data stored in the memory, to implement the methods in the above method embodiments. Optionally, the processor is one or more. Optionally, the communication apparatus includes the memory. Optionally, the memory is one or more. Optionally, the memory is integrated with the processor, or is separately arranged.

[0254] The present application also provides a chip, including a processor and a memory. The memory is configured to store computer programs or instructions. The processor is configured to execute the computer programs or instructions stored in the memory, to implement the methods performed by the first device or the second device in the above method embodiments.

[0255] The present application also provides a computer readable storage medium, which stores computer instructions for implementing the methods performed by the first device or the second device in the above method embodiments.

[0256] The present application also provides a computer program product, including computer programs or instructions, which are executed by a computer to implement the methods performed by the first device or the second device in the above method embodiments.

[0257] The application also provides a communication system, comprising at least one of the first device or the second device in the above embodiments.

[0258] The application also provides a computer program, which, when executed by a computer, implements the method performed by the first device or the second device in the above method embodiments.

[0259] The explanations and advantages of the related content in any of the above devices can refer to the corresponding method embodiments provided above, and will not be repeated here.

[0260] It can be understood that the processor in the embodiments of the application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor can be a microprocessor or any conventional processor.

[0261] The method steps in the embodiments of the application can be realized in the form of hardware or by the processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, a register, a hard disk, a mobile hard disk, a compact disc read-only memory (CD-ROM) or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in the first device or the second device. Of course, the processor and the storage medium can also exist as discrete components in the first device or the second device.

[0262] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer programs or instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are performed. The computer can be a general purpose computer, a special purpose computer, a computer network, a network device, a user equipment or other programmable apparatus. The computer programs or instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer programs or instructions can be transferred from one website site, computer, server or data center to another website site, computer, server or data center through wired or wireless manner. The computer readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center and the like integrated with one or more available media. The available media can be a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape; an optical medium, such as a digital video disc; and a semiconductor medium, such as a solid state disk.

[0263] In various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be referred to each other if there is no special description and logical conflict. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0264] Unless otherwise defined, all technical and scientific terms used in the embodiments of the present application have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used in the present application are only for the purpose of describing the specific embodiments and are not intended to limit the scope of the present application. It should be understood that the above is for illustration only, and the examples above are only to help those skilled in the art to understand the embodiments of the present application, and are not intended to limit the embodiments of the present application to the specific values or specific scenarios shown. Those skilled in the art can obviously make various equivalent modifications or changes according to the examples given above, and such modifications and changes also fall within the scope of the embodiments of the present application.

Claims

1. A method for communication, comprising: The method comprises: a first device in a first domain receives a first message from a second device of a second domain, the first message comprising first capability information of a first agent running in the second device; the first device performs a task according to the first capability information.

2. The method of claim 1, wherein the first capability information comprises a capability supported by the first agent and information of an agent associated with the capability of the first agent.

3. The method of claim 1 or 2, wherein the first message further comprises first information for indicating cross-domain configuration or / and information of the second domain.

4. The method of any one of claims 1 to 3, wherein the first message further comprises second information for indicating that the first message is from the first agent and is to a second agent running in the first device.

5. The method of claim 4, wherein, the first device performs a task according to the first capability information, comprising: the second agent performs the task according to the first capability information.

6. The method of any one of claims 1 to 5, wherein the first message further comprises a first communication type for indicating that the first message is for updating capability information of an agent; the method further comprises that the first device updates locally stored capability information of the first agent to the first capability information according to the first message.

7. The method according to any one of claims 1 to 6, characterized in that, Before the first device in the first domain receives the first message from the second device of the second domain, the method further comprises: the first device sends a second message to the second device, the second message being for requesting capability information of an agent.

8. The method of claim 7, wherein, the first device sends the second message to the second device, comprising: the first device periodically sends the second message to the second device; or the first device sends the second message to the second device when orchestrating the task.

9. The method of claim 7 or 8, wherein the second message comprises an identification of the first agent.

10. The method of claim 7 or 8, wherein the second message comprises third information for indicating all agents running in the second device.

11. The method of any one of claims 7 to 10, wherein the second message further comprises a second communication type for indicating that the second message is for requesting capability information of an agent.

12. The method of any one of claims 1 to 11, wherein the first domain is a master domain and the second domain is a slave domain of the first domain; or the first domain and the second domain are peers.

13. A method for communication, comprising: The method comprises: a second device of a second domain generates a first message, the first message comprising first capability information of a first agent running in the second device; the first device performs a task according to the first capability information. The second device sends the first message to a first device in a first domain.

14. The method of claim 13, wherein, the first capability information comprises: a capability supported by the first agent, and information of an agent associated with the capability of the first agent.

15. The method of claim 13 or 14, wherein, the first message further comprises: first information and / or information of the second domain, the first information being used to indicate cross-domain configuration.

16. The method of any one of claims 13-15, wherein, the first message further comprises: second information, the second information being used to indicate that the first message is from the first agent and is destined for a second agent running in the first device.

17. The method of any one of claims 13-16, wherein, the first message further comprises: a first communication type, the first communication type being used to indicate that the first message is used to update capability information of an agent.

18. The method according to any one of claims 13 to 17, characterized in that, Before the second device sends the first message to the first device, the method further comprises: the second device receives a second message from the first device, the second message being used to request capability information of an agent; the second device generates the first message, comprising: the second device generating the first message according to the second message.

19. The method of claim 18, wherein, the second message comprises: an identification of the first agent; the second device generating the first message according to the second message, comprising: the second device obtaining the first capability information according to the identification of the first agent; the second device generating the first message according to the first capability information.

20. The method of claim 18, wherein, the second message comprises: third information, the third information being used to indicate all agents running in the second device, the all agents comprising the first agent; the second device generating the first message according to the second message, comprising: the second device obtaining capability information of the all agents according to the third information, the capability information of the all agents comprising the first capability information; the second device generating the first message according to the capability information of the all agents.

21. The method of any one of claims 18-20, wherein, the second message further comprises: a second communication type, the second communication type being used to indicate that the second message is used to request capability information of an agent.

22. The method of any one of claims 13-17, wherein, the second device generating the first message, comprising: when the capability of the first agent changes, the second device generating the first message according to the changed capability of the first agent.

23. The method of any one of claims 13-22, wherein, the first domain is a master domain, and the second domain is a slave domain of the first domain; or, the first domain and the second domain are peers.

24. A method for communication, comprising: the method comprises: a second device of a second domain generating a first message, the first message comprising first capability information of a first agent, the first agent running in the second device; The second device sends the first message to a first device in the first domain; The first device receives the first message; The first device performs a task according to the first capability information.

25. A communications device, characterized by The apparatus comprises modules or units for implementing the method of any one of claims 1 to 24.

26. A communications device, characterized by The apparatus comprises a processor and an interface circuit for receiving signals from other devices outside the communication apparatus and transmitting to the processor or sending signals from the processor to other devices outside the communication apparatus, the processor being used for implementing the method of any one of claims 1 to 24 by logic circuit or executing code instructions.

27. The communication apparatus according to claim 26, wherein The communication apparatus is a chip or a chip system.

28. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions, when the computer program or instructions are executed by the communication apparatus, the method of any one of claims 1 to 24 is implemented.

29. A communication system, characterized by The apparatus comprises at least one of the following: a communication apparatus for executing the method of any one of claims 1 to 12, or a communication apparatus for executing the method of any one of claims 13 to 23.

30. A computer program product, characterised in that, The apparatus comprises a computer program or instructions, when the computer program or the instructions are executed in a computer, the steps of the method of any one of claims 1 to 24 are implemented.

Images