Communication method and apparatus

Abstract

A communication method and apparatus, capable of improving the efficiency of communication between agents. In the method, after acquiring a message of an agent, the agent or an agent communication proxy node can determine a sending mode of the message, and send the message on the basis of the determined sending mode. The sending mode of the message may be a first sending mode or a second sending mode. In the first sending mode, sending is performed on the basis of identifier information of the agent, and in the second sending mode, sending is performed on the basis of the semantics of a task description. That is, the agent or the agent communication proxy node can dynamically and flexibly select the sending mode of the message, and select an appropriate sending mode on the basis of actual situations, thereby improving the efficiency of communication between agents. For example, in the case where the working mode of the agent is a standard workflow, the first sending mode is used; or in the case where the working mode of the agent is a dynamic workflow, the second sending mode is used.

Description

Communication methods and devices

[0001] This application claims priority to Chinese Patent Application No. 202510320265.8, filed on March 17, 2025, entitled "Communication Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to communication methods and apparatus. Background Technology

[0003] Future networks will need to support new business scenarios such as the convergence of artificial intelligence (AI) and communication, and the convergence of sensing and communication, including smart cities, digital healthcare, and smart factories. AI-based agents, possessing powerful intent understanding, reasoning capabilities, and the ability to interact with and evolve within their environment, will be widely used in core networks. In other words, the reconstruction of future core networks based on intelligent agents may become a trend.

[0004] Typically, it's difficult for a single agent to complete all the work. Therefore, future core networks may contain multiple agents that collaborate to accomplish complex tasks. Consequently, how to achieve message transmission between multiple agents has become a pressing problem to be solved. Summary of the Invention

[0005] This application provides a communication method and apparatus that enables communication between intelligent agents and improves the efficiency of communication between intelligent agents.

[0006] Firstly, a communication method is provided. This method can be executed by a first communication device, or by a component of the first communication device, such as its processor, chip, or chip system. It can also be implemented by a logic module or software capable of implementing all or part of the functions of the first communication device. For example, the first communication device can be a first intelligent agent or an intelligent agent communication proxy node. The method includes: acquiring a first message from the first intelligent agent; determining the sending method of the first message, wherein the sending method is a first sending method or a second sending method, wherein the first sending method is based on the intelligent agent's identification information, and the second sending method is based on the semantics of the task description; and sending the first message according to the sending method.

[0007] Based on this scheme, after receiving a message from an agent, the agent or agent communication proxy node can dynamically and flexibly choose the message sending method. For example, it can choose a sending method based on the agent's identification information or a sending method based on the semantics of the task description, thus supporting the coexistence of multiple sending methods in the network and selecting the appropriate sending method based on the actual situation, improving the communication efficiency between agents. Furthermore, when the agent communication proxy node chooses the sending method based on the agent's identification information, the receiving agent can be indicated by the message sender. Therefore, the agent communication proxy node does not need to redetermine the receiver, which can reduce message forwarding latency and save power consumption. When the agent communication proxy node chooses the sending method based on the semantics of the task description, it can reasonably select the appropriate receiving agent based on semantics, ensuring the accuracy of message transmission.

[0008] In one possible design, the first message includes instruction information indicating the operating mode of the first agent. If the first agent's operating mode is a standard workflow, the first message is sent in a first sending method; or, if the first agent's operating mode is a dynamic workflow, the first message is sent in a second sending method.

[0009] Based on this possible design, in a standard workflow, the order in which multiple agents process tasks is predefined. Therefore, the identification information of the next-hop agent can be found based on this predefined order, and messages can be sent accordingly. In a dynamic workflow, the order in which agents process tasks is not fixed. Therefore, it is necessary to infer the next-hop agent based on the semantics of the task description, and then send messages to the determined next-hop agent.

[0010] In one possible design, in a standard workflow, the order in which multiple agents process tasks is predefined; in a dynamic workflow, the order in which multiple agents process tasks is variable, or the order in which multiple agents process tasks is dynamically determined during the agents' work, or the order in which multiple agents process tasks may change with the changes in tasks. For example, for a certain agent (such as agent A), if agent A processes task 1, then the next-hop agent is agent B; if agent A processes task 2, then the next-hop agent is agent C.

[0011] In one possible design, the first message is sent using a first sending method; the first message also includes an identifier of a first standard workflow, and the multiple agents in the first standard workflow include the first agent. Sending the first message according to the first message sending method includes: determining a second agent based on the identifier of the first standard workflow, the second agent being the next-hop agent of the first agent in the first standard workflow; and sending the first message to the second agent.

[0012] Based on this possible design, since the first standard workflow includes a first agent, the agent that processes the business first after the first agent in the first standard workflow can be located based on the identifier of the first standard workflow, and a message can be sent to that agent. This eliminates the need for inference by the receiving agent, reducing message forwarding latency.

[0013] In one possible design, the method further includes: obtaining information about at least one standard workflow, the at least one standard workflow including a first standard workflow, the information of the standard workflow including an identifier of the standard workflow and the order in which multiple agents in the standard workflow process business.

[0014] In one possible design, the first message is sent in a first sending mode; the first message also includes the identification information of the second intelligent agent, which is the receiving intelligent agent of the first message; sending the first message according to the first message sending mode includes: sending the first message to the second intelligent agent according to the identification information of the second intelligent agent.

[0015] Based on this possible design, messages can be sent using the identifier information of the receiving agent carried in the message, eliminating the need for reasoning by the receiving agent and reducing message forwarding latency.

[0016] In one possible design, if the first message includes the identification information of the second intelligent agent, the first message is sent using a first sending method; or, if the first message does not include the identification information of the second intelligent agent, the first message is sent using a second sending method. The second intelligent agent is the receiving intelligent agent of the first message.

[0017] In one possible design, the first message is sent in a first sending mode; sending the first message according to the first message sending mode includes: sending the first message to the second intelligent agent according to the information of the second intelligent agent.

[0018] In one possible design, the first message is sent using a second sending method; the first message also includes a task description. Sending the first message according to its sending method includes: determining the semantics of the task description; determining the second agent as the receiving agent of the first message based on the semantics of the task description; and sending the first message to the second agent.

[0019] Based on this possible design, it is possible to select a suitable receiving agent based on semantics, thereby ensuring the accuracy of message transmission.

[0020] In one possible design, the agent's identification information includes the agent's identifier and / or Internet Protocol (IP) address. For example, the first agent is one of the Planning Agent, Assemble Agent, Connection Agent, or Execution Agent. The second agent is one of the Planning Agent, Assemble Agent, Connection Agent, or Execution Agent that is different from the first agent.

[0021] Secondly, a communication method is provided. This method can be executed by a first intelligent agent, or by a component of the first intelligent agent, such as its processor, chip, or chip system, or by a logic module or software capable of implementing all or part of the functions of the first intelligent agent. The method includes: generating a first message, which includes indication information or identification information of a second intelligent agent; and sending the first message. The indication information indicates that the first intelligent agent's operating mode is a standard workflow or a dynamic workflow; the second intelligent agent is the receiving intelligent agent of the first message.

[0022] Based on this scheme, the agent carries indication information or identification information of the receiving agent in the messages it sends. This enables the agent communication agent node to determine the agent's working mode based on the indication information or identification information, and thus select the appropriate message forwarding method under different working modes. That is, it can dynamically and flexibly select the message sending method, such as selecting the sending method based on the agent's identification information or the sending method based on the semantics of the task description. This supports the coexistence of multiple sending methods in the network and can select the appropriate sending method based on the actual situation, thereby improving the communication efficiency between agents.

[0023] In one possible design, in a standard workflow, the order in which multiple agents process tasks is predefined; in a dynamic workflow, the order in which multiple agents process tasks is variable.

[0024] In one possible design, if the instruction information indicates that the first agent's operating mode is a standard workflow, the first message may also include an identifier of the first standard workflow or an identifier of the second agent. Here, the multiple agents in the first standard workflow include the first agent, and the second agent is the receiving agent of the first message.

[0025] In one possible design, the method further includes: obtaining information about at least one standard workflow, the at least one standard workflow including a first standard workflow, the information of the standard workflow including an identifier of the standard workflow and the order in which multiple agents in the standard workflow process business.

[0026] In one possible design, the identification information of the second agent includes the identifier of the second agent and / or its Internet Protocol (IP) address.

[0027] The technical effects of any design in the second aspect can be referenced from the technical effects of the corresponding design in the first aspect, and will not be elaborated further here.

[0028] Thirdly, a communication device is provided for implementing various methods. The communication device includes modules, units, or means corresponding to the implementation of the methods, wherein the modules, units, or means can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the functions.

[0029] In some possible designs, the communication device may include a processing module and a transceiver module. The processing module can be used to implement the processing functions in any of the above aspects and any possible implementations thereof. The transceiver module may include a receiving module and a transmitting module, respectively used to implement the receiving function and the transmitting function in any of the above aspects and any possible implementations thereof.

[0030] In some possible designs, the transceiver module can consist of transceiver circuits, transceivers, transceivers, or communication interfaces.

[0031] Fourthly, a communication device is provided, comprising: a processor and a memory; the memory being used to store computer instructions that, when executed by the processor, cause the communication device to perform the method described in any of the above aspects and any possible design thereof.

[0032] Fifthly, a communication device is provided, comprising: a processor and a communication interface; the communication interface being used to communicate with a module outside the communication device; the processor being used to execute computer programs or instructions to cause the communication device to perform the methods described in any of the above aspects and any possible designs thereof.

[0033] A sixth aspect provides a communication device comprising: at least one processor; said processor being configured to execute a computer program or instructions stored in a memory to cause the communication device to perform the methods described in any of the foregoing aspects and any possible designs thereof. The memory may be coupled to the processor, or may be independent of the processor.

[0034] In a seventh aspect, a communication device (e.g., a chip or chip system) is provided, the communication device including a processor for implementing the functions involved in any of the above aspects and any possible designs thereof.

[0035] In some possible designs, the communication device includes a memory for storing necessary program instructions and data.

[0036] In some possible designs, when the device is a chip system, it can be composed of chips or contain chips and other discrete components.

[0037] The communication device described in the third to seventh aspects may be the first communication device in the first aspect, or a device included in the first communication device, such as a chip or chip system; or the communication device may be the first intelligent agent in the second aspect, or a device included in the first intelligent agent, such as a chip or chip system.

[0038] Eighthly, a communication device is provided. This communication device may be a first communication device, or a module or unit (e.g., a chip, chip system, or circuit) within the first communication device that performs the methods / operations / steps / actions described in the first aspect, or a module or unit that can be used in conjunction with the first communication device; or, the communication device may be a first intelligent agent, or a module or unit (e.g., a chip, chip system, or circuit) within the first intelligent agent that performs the methods / operations / steps / actions described in the second aspect, or a module or unit that can be used in conjunction with the first intelligent agent.

[0039] It is understandable that when the communication device provided by any of the third to eighth aspects is a chip, the sending action / function of the communication device can be understood as outputting information, and the receiving action / function of the communication device can be understood as inputting information.

[0040] A ninth aspect provides a computer-readable storage medium storing a computer program or instructions that, when executed on a communication device, enable the communication device to perform the methods described in any of the foregoing aspects and any possible design thereof.

[0041] In a tenth aspect, a computer program product containing instructions is provided, which, when run on a communication device, enables the communication device to perform the methods described in any of the foregoing aspects and any possible design thereof.

[0042] Eleventhly, a communication system is provided, comprising a first intelligent agent and an intelligent agent communication proxy node. The intelligent agent communication proxy node is used to implement the method described in the first aspect and any possible design thereof, and the first intelligent agent is used to implement the method described in the second aspect and any possible design thereof.

[0043] The technical effects of any of the design methods in aspects three through eleven can be found in the technical effects of different design methods in aspects one or two, and will not be repeated here. Attached Figure Description

[0044] Figure 1 is a schematic diagram of the structure of a communication system provided in this application;

[0045] Figure 2 is a schematic diagram of another communication system provided in this application;

[0046] Figure 3 is a flowchart illustrating a communication method provided in this application;

[0047] Figure 4 is a schematic diagram of a message format provided in this application;

[0048] Figures 5-8 are schematic flowcharts of the communication method provided in this application;

[0049] Figures 9 and 10 are schematic diagrams of the structure of a communication device provided in this application. Detailed Implementation

[0050] In the description of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0051] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, a and b, a and c, b and c, a and b and c, where a, b, and c can be single or multiple.

[0052] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0053] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0054] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0055] It is understood that in this application, "...when", "if", and "...under certain circumstances" all refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require a judgment action to be performed during implementation, nor do they imply any other limitations.

[0056] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0057] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, unless otherwise specified or there is a logical conflict, the terminology and / or descriptions between different embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0058] Future networks need to support new business scenarios such as the convergence of artificial intelligence (AI) and communication, and the convergence of sensing and communication, including smart cities, digital healthcare, and smart factories. Different business scenarios may have different performance requirements; therefore, future networks need strong customization capabilities to integrate end-to-end network functions, application functions, communication, computing, and data resources for service targets (such as tenants / users / applications) to build end-to-end networks and provide customized services.

[0059] However, the number of customized networks in the future may be enormous, with each network involving the flexible assembly of multiple functions and multidimensional resources, and complex parameter configurations. This presents significant challenges to network design and management. Traditional predefined network customization processes based on human expert experience are insufficient to address the complex network customization requirements. However, AI-based agents, with their powerful intent understanding, reasoning capabilities, and the ability to interact with and evolve within their environment, will be widely applied in core networks. In other words, the reconstruction of future core networks based on intelligent agents may become a trend.

[0060] Typically, it's difficult for a single agent to complete all the work. Therefore, future core networks may contain multiple agents that collaborate to accomplish complex tasks. Consequently, how to achieve message transmission between multiple agents has become a pressing problem to be solved.

[0061] Based on this, this application provides a communication method. After obtaining a message (generated or sent) by an intelligent agent, an intelligent agent communication agent node can determine the message sending method and send the message based on the determined sending method. The message sending method can be a first sending method or a second sending method. In the first sending method, the message is sent based on the intelligent agent's identification information; in the second sending method, the message is sent based on the semantics of the task description. Based on this scheme, the intelligent agent or intelligent agent communication agent node can dynamically and flexibly select the message sending method, thereby choosing the appropriate sending method based on the actual situation and improving the communication efficiency between intelligent agents. For example, if the message carries the recipient's identification information or the intelligent agent is working in a standard workflow, sending based on the (receiver) intelligent agent's identification information eliminates the need to re-determine the recipient, reducing message sending latency and saving power. Alternatively, if the message does not carry the recipient's identification information or the intelligent agent is working in a dynamic workflow, sending based on the semantics of the task description, such as inferring the recipient, and then sending the message to the recipient.

[0062] The technical solutions of this application embodiment can be used in various communication systems, including 3GPP communication systems such as 4th generation (4G) systems (e.g., Long Term Evolution (LTE) systems), 5th generation (5G) systems (e.g., New Radio (NR) systems), LTE and 5G hybrid networking systems, sensing systems, integrated communication and sensing systems, non-terrestrial networks (NTN), device-to-device (D2D) communication systems, vehicle-to-everything (V2X) communication systems, machine-type communication (MTC) systems, Internet of Things (IoT) systems, or other future communication systems. The communication system can also be a non-3GPP communication system; there is no limitation on this.

[0063] The communication systems described above are merely illustrative examples, and are not limited to those described herein. The communication systems provided in this application do not impose any limitations on the solutions described herein. This will be explained uniformly here and will not be repeated below.

[0064] Figure 1 illustrates a possible, non-limiting system diagram. As shown in Figure 1, the communication system includes multiple agents; the first and second agents are illustrated as examples in Figure 1. Optionally, the communication system may also include agent communication proxy (ACP) nodes, and further, agent coordination function (ACF) nodes.

[0065] As one possible implementation, these multiple intelligent agents can be deployed in the core network, such as in a 5G core network or the core network of a future mobile communication network. Different intelligent agents can perform different functions.

[0066] For example, as shown in Figure 2, the multiple intelligent agents may include, but are not limited to: a Planning Agent, an Assemble Agent, a Connection Agent, and an Execution Agent. The first intelligent agent can be any of the aforementioned agents, and the second intelligent agent is the receiver of messages sent by the first intelligent agent. Each intelligent agent can implement different functions, for example:

[0067] Planning Agent: Used to understand complex task requirements and break them down into a series of simple and easily executable subtasks;

[0068] Assemble Agent: Used to intelligently select the execution function based on the input task or subtask description;

[0069] Connection Agent: Used for intelligent connection management, including configuring terminal and base station functions, and establishing and updating end-to-end network topology and connections according to service requirements;

[0070] Execution Agent: Responsible for managing computing resources, including the deployment, updating, and deletion of functional instances, and the dynamic scheduling of computing resources.

[0071] As one possible implementation, agents can communicate based on forwarding from other nodes, such as through forwarding from ACP nodes; or, agents can communicate directly without restriction.

[0072] As one possible implementation, ACP nodes and ACF nodes are deployed in the core network. Furthermore, ACP nodes and ACF nodes can have other names; for example, an ACP node can also be called a first node, and an ACF node can also be called a second node, etc. This application does not specifically limit the names of ACP nodes and ACF nodes.

[0073] For example, ACP nodes are used for message forwarding between agents. When multiple forwarding mechanisms exist, the ACP node can flexibly select the appropriate forwarding mechanism based on the received message, which will be described in detail in subsequent embodiments and will not be repeated here.

[0074] For example, the ACF node is used to manage and control agents, such as selecting appropriate agents to participate in business operations based on business needs, and coordinating the working modes of agents.

[0075] It is understood that the names and functions of the various intelligent agents mentioned above are merely illustrative examples. The intelligent agents in the embodiments of this application can be any intelligent agent in the core network, such as intelligent agents applied in any business scenario or application scenario. This application does not specifically limit the names and functions of the intelligent agents.

[0076] All or part of the functions of the intelligent agent, ACP node, and ACF node in this application can be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform), or through software modules, hardware modules, or a combination of software and hardware modules. The intelligent agent / ACP node / ACF node in this application can also be a logical node, logical module, or software capable of implementing all or part of the functions of the intelligent agent / ACP node / ACF node, or a device with some of the functions of the intelligent agent / ACP node / ACF node, such as a chip system, which can be installed in the intelligent agent / ACP node / ACF node.

[0077] It should be noted that the system described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0078] The communication method provided in this application embodiment will now be described in conjunction with the aforementioned communication system. As shown in Figure 3, the communication method includes the following steps:

[0079] S301, The first agent sends a first message to the ACP node. Correspondingly, the ACP node receives the first message from the first agent.

[0080] As one possible implementation, the first message can be understood as an agent message. The first message can be generated by the first agent, for example, it can be a message generated after executing one or more tasks. That is, the first message can be a message associated with one or more tasks.

[0081] For example, the first message may include at least one task description, which describes the task that the recipient of the first message needs to perform. Furthermore, the first message may also include a task identifier corresponding to at least one task description and / or the expected output result, etc.

[0082] It should be noted that, unless otherwise specified, in this embodiment, the recipient of the first message refers to the receiving intelligent agent, which is the intelligent agent that needs to perform corresponding processing (such as executing tasks) based on the first message. The ACP node is used to forward the first message, and the ACP node is not considered to be the recipient of the first message.

[0083] As one possible implementation, the first message can indicate the operating mode of the first intelligent agent. For example, the operating mode of the first intelligent agent can also be understood as the operating mode associated with or used by the first intelligent agent, or the current operating mode of the first intelligent agent, or the operating mode of the first intelligent agent when completing the current business or task, etc.

[0084] The working modes of intelligent agents are divided into standard operating procedures (SOPs) and dynamic operating procedures.

[0085] In a standard workflow, the order in which multiple agents process tasks is predefined, or fixed and unchanging regardless of the task. For example, in a standard workflow, the order in which multiple agents process tasks might be: Planning Agent -> Assemble Agent -> Execution Agent -> Connection Agent. Then, for any task applicable to this standard workflow (such as task 1 or task 2), the Planning Agent will process it first, followed by the Assemble Agent, then the Execution Agent, and finally the Connection Agent.

[0086] In dynamic workflows, the order in which multiple agents process tasks is variable, or non-fixed, or dynamically determined during the agent's work. The order in which multiple agents process tasks may change as the task changes. For example, for task 3, after the Planning Agent processes it, the next agent to process task 3 might be the Assemble Agent; while for task 4, after the Planning Agent processes it, the next agent to process task 4 might be the Connection Agent.

[0087] It should be noted that standard workflows and dynamic workflows may have other names. For example, a standard workflow may also be called a first workflow, a fixed workflow, or a standard work mode, and a dynamic workflow may also be called a second workflow, a non-fixed workflow, or a dynamic work mode. This application does not specifically limit their names.

[0088] As one possible implementation, the first message may include the identification information of the sending agent, that is, the identification information of the first agent, so that subsequent agents know the source of the first message.

[0089] S302, the ACP node determines the method of sending the first message.

[0090] The first message is sent using either a first sending method or a second sending method. The first sending method is based on the agent's identification information, or in other words, the first sending method is based on the agent's identification information. The second sending method is based on the semantics of the task description, or in other words, the second sending method is based on the task description.

[0091] Understandably, for an ACP node, the way the first message is sent can also be understood as the way the first message is forwarded. The first sending method can also be called the first forwarding method, and the second sending method can also be called the second forwarding method.

[0092] As one possible implementation, the first sending method can also be understood as follows: the message receiving agent is determined based on the agent's identification information in the message or the identification information of the standard workflow. That is, in the first sending method, the message receiving agent is known, or explicitly indicated by the message sender, and the ACP node does not need to determine (e.g., infer) the message receiving agent based on the semantics of the task description. Correspondingly, the second sending method can also be understood as follows: the message receiving agent is determined based on the semantics of the task description in the message. That is, in the second sending method, the ACP node needs to determine the message receiving agent based on the semantics of the task description.

[0093] For example, in the embodiments of this application, the identification information of the intelligent agent is used to indicate or uniquely identify the intelligent agent. The identification information of the intelligent agent can be, for example, an identifier, an Internet protocol (IP) address, a name, an index, a number, a code, etc., and is not limited thereto.

[0094] As one possible implementation, the ACP node can determine the sending method of the first message based on the working mode of the first agent. For example, if the working mode of the first agent is a standard workflow, the first message is sent using the first sending method; if the working mode of the first agent is a dynamic workflow, the first message is sent using the second sending method.

[0095] S303 and ACP nodes send the first message according to the sending method of the first message.

[0096] As one possible implementation, if the first message is sent using the first sending method, the first agent can indicate the receiving agent (i.e., the second agent) in the first message. Then, the ACP node can send (or forward) the first message to the second agent according to the instruction of the first agent. Alternatively, if the first message is sent using the second sending method, the ACP node can determine the receiving agent as the second agent based on the semantics of the task description in the first message, and thus send (or forward) the first message to the second agent. The implementation of determining the receiving agent based on the semantics of the task description will be described in subsequent embodiments and will not be elaborated here.

[0097] In some possible implementations, step S302 above can also be replaced by: the ACP node determining the working mode of the first agent. The working mode of the first agent is either a standard workflow or a dynamic workflow. Correspondingly, step S303 above can be replaced by: when the working mode of the first agent is a standard workflow, sending a first message according to a first sending method; or, when the working mode of the first agent is a dynamic workflow, sending a first message according to a second sending method.

[0098] Based on this scheme, after receiving a message from an agent, the ACP node can dynamically and flexibly choose the message sending method. For example, it can choose a sending method based on the agent's identification information or a sending method based on the semantics of the task description. This supports the coexistence of multiple sending methods in the network and allows the selection of an appropriate sending method based on the actual situation, improving the communication efficiency between agents. For example, if the message carries the recipient's identification information or the agent is operating in a standard workflow, sending based on the (receiver's) agent's identification information eliminates the need to re-determine the recipient, reducing message sending latency and saving power. Alternatively, if the message does not carry the recipient's identification information or the agent is operating in a dynamic workflow, sending based on the semantics of the task description, such as inferring the recipient, and then sending the message to the recipient.

[0099] The overall process of the communication method provided in this application has been described above. The detailed implementation of each step above will be introduced below.

[0100] In one possible implementation, in step S301 above, before the first intelligent agent instructs the first intelligent agent's working mode through the first message, the first intelligent agent needs to know its working mode.

[0101] As one possible implementation, the operating mode of the first intelligent agent can be configured by the ACF node, or it can be determined by the first intelligent agent itself. For example, the first intelligent agent can determine its operating mode based on current business needs, user requirements, and relevant configurations, without restriction.

[0102] In one possible implementation, in step S301 above, the first intelligent agent can indicate the working mode of the first intelligent agent through the following methods one, two or three, or in other words, the first message has the following three implementation methods.

[0103] Method 1: The first message includes instruction information.

[0104] In one possible implementation, the instruction information indicates the working mode of the first intelligent agent, that is, it indicates that the working mode of the first intelligent agent is a standard workflow or a dynamic workflow.

[0105] As one possible implementation, this indication information can be carried using 1 bit. When this 1 bit is set to a first value, it indicates that the first agent's operating mode is a standard workflow; when the 1 bit is set to a second value, it indicates that the first agent's operating mode is a dynamic workflow. For example, the first value can be "1", and correspondingly, the second value can be "0"; or, the first value can be "0", and correspondingly, the second value can be "1", without limitation.

[0106] In another possible implementation, the instruction information may simply indicate that the first agent's operating mode is a standard workflow. In this case, if the first agent's operating mode is a dynamic workflow, the instruction information may not be included in the first message.

[0107] As one possible implementation, if the instruction information indicates that the first agent's operating mode is a standard workflow, the first message also includes an identifier of the first standard workflow. Here, the first standard workflow includes the first agent among multiple agents, or the first standard workflow is a standard workflow currently used or associated with the first agent.

[0108] For example, the first standard workflow may be configured by the ACF node to the first intelligent agent, or it may be determined by the first intelligent agent based on the current business, user needs, related configurations, etc., without restriction.

[0109] For example, the first intelligent agent can obtain information from at least one standard workflow and determine a first standard workflow from the at least one standard workflow. That is, the at least one standard workflow includes the first standard workflow. The information of the at least one standard workflow may be configured to the first intelligent agent by an operation administration and maintenance (OAM) platform, or it may be configured to the first intelligent agent by other devices, without limitation.

[0110] The information in the standard workflow includes the identifier (or number, index, etc.) of the standard workflow and the order in which multiple agents process the business within that workflow. The order in which multiple agents process the business can be identified by the order of their identifier information. For example, taking the agent's identifier information as ID / IP address, the information for at least one standard workflow can be represented as Table 1.

[0111] Table 1

[0112] Based on the examples in Table 1 above, in standard workflow 1, the Planning Agent processes the data first, followed by the Assemble Agent, then the Execution Agent, and finally the Connection Agent. In standard workflow 2, the Connection Agent processes the data first, followed by the Execution Agent.

[0113] Based on the example in Table 1 above, if the first intelligent agent is a Planning Agent and the first standard workflow is Standard Workflow 1, then the first message also includes the identifier of Standard Workflow 1.

[0114] For example, the instruction information and the identifier of the first standard workflow can be encapsulated in the header (or message header) of the first message. Furthermore, the identifier of the first agent can also be encapsulated in the header, while the task description, task identifier, expected output, etc., can be encapsulated as message content in the message body. Taking the instruction information indicating the working mode as the standard workflow, the identifier of the first standard workflow being 1, and the identifier of the first agent being represented as PA101 as an example, the message structure of the first message can be as shown in Figure 4(a).

[0115] It is understood that the message format of the first message described above is only an example. The first message can also adopt other encapsulation formats. For example, all the above information can be encapsulated in the message body, or the identification information of the first intelligent agent can be encapsulated in the message body, or the indication information can be encapsulated in the packet header, and other information can be encapsulated in the message body, etc., without limitation.

[0116] As another possible implementation, if the instruction information indicates that the first agent's working mode is a standard workflow, the first message also includes the identification information of the second agent. The second agent is the receiving agent of the first message. That is, the first agent can carry the identification information of the receiving agent in the first message. For example, this receiving agent (i.e., the second agent) can be configured by the ACF node to the first agent, or it can be determined by the first agent node itself; there is no limitation.

[0117] For example, the identification information of the second intelligent agent is used to indicate or uniquely identify the second intelligent agent. The identification information of the second intelligent agent can be, for example, an identifier, IP address, name, index, number, code, etc., without limitation.

[0118] For example, the instruction information and the identification information of the second agent can be encapsulated in the header of the first message. Furthermore, the identification information of the first agent can also be encapsulated in the header, while the task description, task identifier, expected output, etc., can be encapsulated as message content in the message body. Taking the instruction information indicating the working mode as the standard workflow, with the identification information of the second agent represented as PA102 and the identification information of the first agent represented as PA101, the message structure of the first message can be as shown in Figure 4(b). Of course, the first message can also use other encapsulation formats; please refer to the relevant descriptions above, which will not be repeated here.

[0119] Method 2: The first message may include the identification information of the second intelligent agent, or it may not include the information of the second intelligent agent.

[0120] In other words, in this second method, the first intelligent agent's working mode is indicated by whether the first message includes or excludes (or carries or does not carry) the identification information of the second intelligent agent.

[0121] As one possible implementation, if the first message includes the identification information of the second agent, the first agent operates in a standard workflow. In this standard workflow, the second agent is the next-hop agent of the first agent. Alternatively, if the first message does not include the identification information of the second agent, the first agent operates in a dynamic workflow.

[0122] Method 3: The first message may include an identifier for the first standard workflow, or it may not include an identifier for any standard workflow.

[0123] In other words, in this third method, the working mode of the first intelligent agent is indicated by whether the first message includes or excludes (or carries or does not carry) the identifier of the standard workflow.

[0124] As one possible implementation, if the first message includes an identifier of a first standard workflow, the first agent operates in a standard workflow mode. Alternatively, if the first message does not include an identifier of any standard workflow, the first agent operates in a dynamic workflow mode.

[0125] Corresponding to the three implementation methods of the first message mentioned above, in step S302, the ACP node may determine the implementation of the sending (or forwarding) method of the first message, which may also include the following three situations.

[0126] Scenario 1: If the first message includes instruction information, and the instruction information indicates that the working mode of the first intelligent agent is a standard workflow, the first message is sent in the first sending method; if the instruction information indicates that the working mode of the first intelligent agent is a dynamic workflow, the first message is sent in the second sending method.

[0127] In a first possible implementation, where the instruction information indicates that the first agent's operating mode is a standard workflow (i.e., the sending method is the first sending method), and the first message also includes an identifier of the first standard workflow, then step S303 above, where the ACP node sends the first message according to the first sending method, may include: the ACP node determining the second agent based on the identifier of the first standard workflow and sending the first message to the second agent. The second agent is the next-hop agent of the first agent in the first standard workflow.

[0128] As one possible implementation, the ACP node can obtain information about at least one standard workflow (or standard workflow table) and determine the second agent based on this standard workflow table. The standard workflow information includes the identifier of the standard workflow and the order in which multiple agents process business within the standard workflow, as described in the relevant explanation in Method 1 above. Furthermore, the standard workflow table can be configured to the ACP node by the OAM platform, gateway, or other devices, or it can be pre-configured within the ACP node; there are no restrictions.

[0129] For example, an ACP node can query the corresponding workflow entry in the standard workflow table based on the identifier of the first standard workflow, and then query the next agent (or next-hop agent) in the workflow based on the identifier information of the first agent, and obtain the identifier information of the agent.

[0130] Based on the example shown in Table 1 above, if the first standard workflow is standard workflow 1, the ACP node will query workflow entry 1 in the standard workflow table. Assuming the first agent is the Planning Agent, the next-hop agent in this standard workflow will be determined to be the Assemble Agent based on the Planning Agent's identification information, i.e., the second agent is the Assemble Agent. The ACP node will then obtain the Assemble Agent's ID or IP address from the standard workflow table. If the obtained ID is the Assemble Agent's ID, the ACP node will determine the Assemble Agent's IP address based on the Assemble Agent's ID, and then forward the first message based on the Assemble Agent's IP address.

[0131] Alternatively, if the first standard workflow is standard workflow 1, and assuming the first agent is the Assemble Agent, the ACP node can determine the second agent as the Execution Agent through the standard workflow table.

[0132] In a second possible implementation, if the instruction information indicates that the working mode of the first intelligent agent is the standard workflow (i.e., the sending method is the first sending method), and the first message also includes the identifier of the second intelligent agent, then in the above step S303, the ACP node sending the first message according to the first sending method may include: sending the first message to the second intelligent agent according to the identifier information of the second intelligent agent.

[0133] As one possible implementation, after receiving the first message, the ACP node determines the sending method to be the first sending method based on the indication information, thereby parsing the identification information of the second agent in the first message and forwarding the first message based on the identification information. For example, if the identification information of the second agent is its ID / index / name, the ACP node determines the IP address of the second agent based on its ID / index / name and forwards the first message based on the second agent's IP address.

[0134] For example, an ACP node can obtain the mapping relationship between the ID / index / name of each agent and the IP address of the agent, and determine the IP address of the second agent based on the mapping relationship; or, if the ID / index / name of an agent and the IP address of that agent satisfy a certain rule, the ID / index / name of the agent can be converted into the IP address of the agent according to the rule.

[0135] In a third possible implementation, if the instruction information indicates that the working mode of the first intelligent agent is a dynamic workflow (i.e., the sending method is the second sending method), and the first message also includes a task description, then in the above step S303, the ACP node sending the first message according to the second sending method may include: determining the semantics of the task description, and determining the second intelligent agent as the receiving intelligent agent of the first message according to the semantics of the task description, and sending the first message to the second intelligent agent.

[0136] As one possible implementation, after receiving the first message, the ACP node can determine the second sending method based on the indication information. Therefore, it can call a local model or an external network model (such as NetGPT) to parse the semantics of the task description and infer the receiving agent based on this semantics. For example, the ACP node performs semantic similarity matching between the semantics of the task description and the semantics of the role descriptions of multiple agents one by one, and selects the agent with the highest semantic similarity as the receiving agent.

[0137] Understandably, this embodiment uses the example of the receiving agent of the ACP node inference being the second agent. For example, among multiple agents, the semantics of the role description of the second agent have the highest similarity to the semantics of the task description in the first message.

[0138] Scenario 2: If the first message includes the identification information of the second intelligent agent, the first message is sent in the first sending method; if the first message does not include the identification information of the second intelligent agent, the first message is sent in the second sending method.

[0139] In this context, the second intelligent agent is the receiving intelligent agent of the first message. That is, if the first message indicates the receiving intelligent agent, the first message is sent in the first sending method; if the first message does not indicate the receiving intelligent agent, the first message is sent in the second sending method.

[0140] As one possible implementation, if the first message includes the identification information of the second intelligent agent, or if the first message is sent using the first sending method, then in step S303 above, the implementation of the ACP node sending the first message according to the first sending method can refer to the relevant description in the second possible implementation of the above-described situation one. If the first message does not include the identification information of the second intelligent agent, or if the first message is sent using the second sending method, then in step S303 above, the implementation of the ACP node sending the first message according to the first sending method can refer to the relevant description in the third possible implementation of the above-described situation one, and will not be repeated here.

[0141] Scenario 3: If the first message includes an identifier of the first standard workflow, the first message is sent using the first sending method; if the first message does not include any identifier of the standard workflow, the first message is sent using the second sending method.

[0142] The first standard workflow includes multiple agents, including the first agent. That is, if the first message indicates the first standard workflow, the first message is sent using the first sending method; if the first message does not indicate any standard workflow, the first message is sent using the second sending method.

[0143] As one possible implementation, in the three scenarios described above, after receiving the first message, the second agent can process it. If the second agent generates a second message after processing the first message, and this second message needs to be sent to other agents, the second agent can then send the second message to the ACP node, which in turn forwards it to other agents. The implementation of the second message can refer to the implementation of the first message described above, and the implementation of the ACP node forwarding the second message can refer to the relevant explanations regarding the ACP node forwarding the first message; these details will not be repeated here.

[0144] As one possible implementation, if the first message includes an identifier of a first standard workflow, or if the first message is sent using a first sending method, then in step S303 above, the implementation of the ACP node sending the first message according to the first sending method can refer to the relevant description in the first possible implementation of case one above. If the first message does not include any identifier of a standard workflow, or if the first message is sent using a second sending method, then in step S303 above, the implementation of the ACP node sending the first message according to the first sending method can refer to the relevant description in the third possible implementation of case one above, and will not be repeated here.

[0145] The above embodiments illustrate communication between agents via forwarding through ACP nodes. Furthermore, agents can also communicate directly. In this scenario, the first agent can also execute the above method to send a first message to the second agent. For example, in step S301, the first agent generates a first message; in step S302, the first agent determines whether the first message is sent using a first sending method or a second sending method; in step S303, the first agent sends the first message to the second agent according to the sending method of the first message. The implementation of the first agent determining the sending method of the first message, the information carried in the first message, and the implementation of sending the first message can be referred to the relevant descriptions in the above embodiments, and will not be repeated here.

[0146] It is understandable that the ACP node receiving the first message from the first agent, and the first agent generating the first message, can both be understood as acquiring the first message.

[0147] The communication method provided in the embodiments of this application has been described in detail above. The following example illustrates the communication method by taking a first intelligent agent as the Planning Agent, where intelligent agents communicate through forwarding via ACP nodes, the first intelligent agent employing a standard workflow, and the ACP nodes forwarding data by looking up a standard workflow table. As shown in Figure 5, the communication method includes the following steps:

[0148] S500 and OAM platforms configure standard workflow tables for ACP nodes.

[0149] The standard workflow table includes information on at least one standard workflow, such as the standard workflow identifier (SOP ID), the order in which multiple agents process business within the standard workflow, and the identification information of the multiple agents. For example, the standard workflow table can be as shown in Table 1 above.

[0150] Understandably, step S500 is optional. That is, step S500 can be omitted. If step S500 is not executed, a standard workflow table can be built into the ACP node.

[0151] S501: The Planning Agent sends the first message to the ACP node. Correspondingly, the ACP node receives the first message from the Planning Agent.

[0152] The first message includes an instruction message and an identifier for the first standard workflow. The instruction message indicates that the Planning Agent operates in a standard workflow mode, and the multiple agents in the first standard workflow include the Planning Agent. Please refer to the above explanations regarding the instruction message and the first standard workflow; they will not be repeated here.

[0153] Furthermore, the first message may also include the Planning Agent's identifier, task description, task identifier, or expected output results. The encapsulation format of the first message can be found in the relevant instructions in Method 1 above, and will not be repeated here.

[0154] S502, the ACP node determines that the first message is sent in the first sending mode, and looks up the standard workflow table to determine the receiving agent.

[0155] Based on the example shown in Table 1 above, if the first standard workflow is standard workflow 1, then the ACP node will find workflow entry 1 in the standard workflow table. Since the first agent is the Planning Agent, the next-hop agent of the Planning Agent is determined to be the Assemble Agent according to standard workflow 1, that is, the receiving agent is the Assemble Agent. The ID or IP address of the Assemble Agent is obtained from the standard workflow table. Please refer to the relevant description in the first possible implementation of the above case 1, which will not be repeated here.

[0156] S503, the ACP node forwards the first message to the Assemble Agent. Correspondingly, the Assemble Agent receives the first message.

[0157] As one possible implementation, if the ID of the Assemble Agent is obtained in step S502, the ACP node determines the IP address of the Assemble Agent based on the ID, and then forwards the first message based on the IP address of the Assemble Agent. If the IP address of the Assemble Agent is obtained in step S502, the message is forwarded directly based on the IP address.

[0158] Figure 6 illustrates another exemplary description of the communication method described above. In this example, the first agent is taken as the Connection Agent, and communication between agents is achieved through forwarding by the ACP node. The first agent adopts a standard workflow, and the ACP node forwards information based on the identifier of the receiving agent. Referring to Figure 6, the communication method includes the following steps:

[0159] S601, the ACF node sends task allocation information to the Connection Agent. Correspondingly, the ACF node receives task allocation information from the ACF node.

[0160] Specifically, the task allocation information configures the Connection Agent to use the standard workflow and configures the receiving agent, including its identification information. In this embodiment, the receiving agent is Execution Agent. Furthermore, the task allocation information also assigns tasks to the Connection Agent.

[0161] S602, the Connection Agent sends the first message to the ACP node. Correspondingly, the ACP node receives the first message from the Connection Agent.

[0162] As one possible implementation, the Connection Agent can generate the first message after executing a task based on the task allocation information of the ACF node.

[0163] The first message includes instruction information and identification information of the receiving agent (such as the Execution Agent). Furthermore, the first message may also include the identification of the Connection Agent, task description, task identifier, or expected output result. The encapsulation format of the first message can be found in the relevant description in Method 1 above, and will not be repeated here.

[0164] S603, the ACP node determines that the first message is sent in the first sending mode, and determines the receiving agent based on the identification information of the receiving agent.

[0165] In this embodiment, the receiving agent is Execution Agent as an example. The detailed implementation of step S603 can be found in the description of the second possible implementation of Case 1 above, and will not be repeated here.

[0166] S604, the ACP node forwards the first message to the Execution Agent. Correspondingly, the Execution Agent receives the first message. Refer to the relevant description in the second possible implementation of scenario one above; it will not be repeated here.

[0167] Figure 7 illustrates another exemplary embodiment of the communication method described above. In this example, the first agent is taken as the Connection Agent, and communication between agents occurs through forwarding via an ACP node. The ACP node determines the working mode and sending method based on whether the message carries the identifier information of the receiving agent. Referring to Figure 7, the communication method includes the following steps:

[0168] S701, the ACF node sends task allocation information to the Connection Agent. Correspondingly, the ACF node receives task allocation information from the ACF node.

[0169] The task allocation information configures the receiving agent to the Connection Agent, including its identification information. In this embodiment, the receiving agent is Execution Agent. Furthermore, the task allocation information also assigns tasks to the Connection Agent.

[0170] S702, the Connection Agent sends the first message to the ACP node. Correspondingly, the ACP node receives the first message from the Connection Agent.

[0171] In this embodiment, when the Connection Agent operates in a standard workflow mode, the first message includes the identification information of the receiving agent; when the Connection Agent operates in a dynamic workflow mode, the first message does not include the identification information of the receiving agent. This embodiment uses the standard workflow mode of the Connection Agent, where the first message includes the identification information of the receiving agent, as an example for explanation.

[0172] Furthermore, the first message may also include the identifier of the Connection Agent, task description, task identifier, or expected output results, as described in the relevant description in step S602 above.

[0173] S703. If the first message includes the identification information of the receiving agent, the ACP node determines that the sending method of the first message is the first sending method, and determines the receiving agent based on the identification information of the receiving agent.

[0174] In this embodiment, the receiving agent is Execution Agent as an example. The detailed implementation of step S703 can be found in the description of the second possible implementation of Case 1 above, and will not be repeated here.

[0175] S704, the ACP node forwards the first message to the Execution Agent. Correspondingly, the Execution Agent receives the first message. Refer to the relevant description in the second possible implementation of scenario one above; it will not be repeated here.

[0176] As one possible implementation, if the first message does not include the identification information of the receiving agent, in step S703 above, the ACP node determines that the sending method of the first message is the second sending method, and determines the receiving agent based on the semantics of the task description. For details, please refer to the relevant description in the third possible implementation of the above situation one, which will not be repeated here.

[0177] Figure 8 illustrates another exemplary description of the communication method described above. In this example, the first agent is the Planning Agent, and communication between agents occurs through forwarding by an ACP node. The ACP node determines the receiving agent for forwarding based on the semantics of the task description. Referring to Figure 8, the communication method includes the following steps:

[0178] S801, the Planning Agent receives user requests.

[0179] For example, the user request is used to request the execution of a task, such as requesting to plan a weekend camping trip for the user.

[0180] S802, the Planning Agent sends the first message to the ACP node.

[0181] As one possible implementation, the Planning Agent can decompose tasks based on user requests, determine the connection that needs to be established between the user's smart terminal and the network smart assistant, and thus generate the first message based on this.

[0182] The first message includes an instruction and a task description. The instruction indicates that the Planning Agent operates in a dynamic workflow mode. For example, the Planning Agent's operating mode can be determined by the Planning Agent itself or configured by the ACF node; there are no restrictions.

[0183] Optionally, the first message may also include the identifier of the Planning Agent, the task identifier, the expected output, etc. The message format of the first message can be referred to the aforementioned relevant instructions, and will not be repeated here.

[0184] S803 and ACP nodes determine that the first message is sent using the second sending method, and determine the receiving agent based on the semantics of the task description.

[0185] For example, ACP can invoke local models or external network models (such as NetGPT) to parse the semantics of the task description and reason about the receiving agent based on that semantics. In this embodiment, the receiving agent for ACP node reasoning is a Connection Agent as an example.

[0186] S804, the ACP node forwards the first message to the Connection Agent. Correspondingly, the Connection Agent receives the first message. Refer to the description in the third possible implementation of scenario one above; it will not be repeated here.

[0187] It should be noted that in the above embodiments of this application, the message names between the ACP node, the first intelligent agent, and the second intelligent agent, the names of each parameter, or the names of each piece of information are just examples. In other embodiments, they may be other names, and the method provided in this application does not specifically limit them.

[0188] It is understood that in the embodiments of this application, the ACP node, the first intelligent agent, and the second intelligent agent can execute some or all of the steps in the embodiments of this application. These steps or operations are merely examples, and the embodiments of this application can also execute other operations or variations thereof. Furthermore, the various steps can be executed in different orders as presented in the embodiments of this application, and it is not necessarily necessary to execute all the operations in the embodiments of this application.

[0189] It is understood that, in the above embodiments, the methods and / or steps implemented by the ACP node can also be implemented by components (e.g., processors, chips, chip systems, circuits, logic modules, or software) that can be used with the ACP node, or by logic nodes, logic modules, or software that can implement all or part of the functions of the ACP node; similarly, the methods and / or steps implemented by the first intelligent agent can also be implemented by components (e.g., processors, chips, chip systems, circuits, logic modules, or software) that can be used with the first intelligent agent, or by logic nodes, logic modules, or software that can implement all or part of the functions of the first intelligent agent.

[0190] It is understood that, in order to achieve the aforementioned functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0191] This application embodiment can divide the communication device into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0192] Figure 9 shows a schematic diagram of a communication device 90. The communication device 90 includes a processing module 901 and a transceiver module 902. This communication device 90 can be used to implement the functions of the aforementioned ACP node or first intelligent agent.

[0193] In some embodiments, the communication device 90 may further include a storage module (not shown in FIG9) for storing program instructions and data.

[0194] In some embodiments, the transceiver module 902, also referred to as a transceiver unit, is used to implement sending and / or receiving functions. The transceiver module 902 may consist of a transceiver circuit, a transceiver, a transceiver unit, or a communication interface.

[0195] In some embodiments, the transceiver module 902 may include a receiving module and a sending module, respectively used to execute the receiving and sending steps performed by the ACP node or the first intelligent agent in the above method embodiments, and / or other processes used to support the technology described herein; the processing module 901 may be used to execute the processing steps (e.g., determination) performed by the ACP node or the first intelligent agent in the above method embodiments, and / or other processes used to support the technology described herein.

[0196] As one possible implementation, when the communication device 90 is used to implement the functions of the aforementioned ACP node or first intelligent agent:

[0197] Processing module 901 is used to acquire the first message of the first intelligent agent; processing module 901 is also used to determine the sending method of the first message, which is either a first sending method or a second sending method. In the first sending method, the message is sent based on the identification information of the intelligent agent, and in the second sending method, the message is sent based on the semantics of the task description; sending and receiving module 902 is used to send the first message according to the sending method of the first message.

[0198] Optionally, the first message includes instruction information indicating the operating mode of the first intelligent agent. If the operating mode of the first intelligent agent is a standard workflow, the first message is sent in a first sending method; or, if the operating mode of the first intelligent agent is a dynamic workflow, the first message is sent in a second sending method.

[0199] Optionally, in a standard workflow, the order in which multiple agents process tasks is predefined; in a dynamic workflow, the order in which multiple agents process tasks is variable.

[0200] Optionally, the first message is sent using a first sending method; the first message also includes an identifier of a first standard workflow. If the first standard workflow includes multiple agents, the transceiver module 902 is used to send the first message according to the first message sending method, including: the transceiver module 902 is used to determine a second agent through the processing module 901 based on the identifier of the first standard workflow, the second agent being the next-hop agent of the first agent in the first standard workflow; the transceiver module 902 is used to send the first message to the second agent.

[0201] Optionally, the processing module 901 is further configured to acquire information about at least one standard workflow, the at least one standard workflow including a first standard workflow, the information of the standard workflow including the identifier of the standard workflow and the order in which multiple agents in the standard workflow process business.

[0202] Optionally, the first message is sent in a first sending method; the first message also includes the identification information of the second intelligent agent. If the second intelligent agent is the receiving intelligent agent of the first message, the transceiver module 902 is used to send the first message according to the sending method of the first message, including: the transceiver module 902 is used to send the first message to the second intelligent agent according to the identification information of the second intelligent agent.

[0203] Optionally, if the first message includes the identification information of the second intelligent agent, the first message is sent in a first sending method; or, if the first message does not include the identification information of the second intelligent agent, the first message is sent in a second sending method; wherein, the second intelligent agent is the receiving intelligent agent of the first message.

[0204] Optionally, when the first message is sent in a first sending mode, the transceiver module 902 is used to send the first message according to the first message sending mode, including: the transceiver module 902 is used to send the first message to the second intelligent agent according to the information of the second intelligent agent.

[0205] Optionally, the message is sent in the second sending method; if the first message also includes a task description, the transceiver module 902 is used to send the first message according to the sending method of the first message, including: the transceiver module 902 is used to determine the semantics of the task description through the processing module 901; the transceiver module 902 is also used to determine the second intelligent agent as the receiving intelligent agent of the first message through the processing module 901 according to the semantics of the task description; the transceiver module 902 is also used to send the first message to the second intelligent agent.

[0206] As one possible implementation, when the communication device 90 is used to implement the functions of the first intelligent agent described above:

[0207] Processing module 901 is used to generate a first message, which includes indication information or identification information of a second intelligent agent; transceiver module 902 is used to send the first message. The indication information indicates whether the first intelligent agent's working mode is a standard workflow or a dynamic workflow; the second intelligent agent is the receiving intelligent agent of the first message.

[0208] Optionally, the processing module 901 is further configured to acquire information about at least one standard workflow, the at least one standard workflow including a first standard workflow, the information of the standard workflow including the identifier of the standard workflow and the order in which multiple agents in the standard workflow process business.

[0209] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0210] In this application, the communication device 90 can be presented in an integrated manner by dividing it into various functional modules. Here, "module" can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, integrated logic circuits, and / or other devices that can provide the above functions.

[0211] Alternatively, the modules in the communication device 90 can be implemented in software, hardware, or a combination of both. When any of the above modules are implemented in software, the software exists as computer program instructions and is stored in memory. The processor can be used to execute the program instructions and implement the above method flow. The processor can be built into a system-on-chip (SoC) or ASIC, or it can be a separate semiconductor chip. In addition to the core that executes the software instructions for computation or processing, the processor may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), or logic circuits that implement dedicated logic operations.

[0212] When the above modules or units are implemented in hardware, the hardware can be any one or any combination of a general-purpose central processing unit (CPU), microprocessor, digital signal processing (DSP) chip, microcontroller unit (MCU), artificial intelligence processor, ASIC, SoC, FPGA, PLD, application-specific digital circuit, hardware accelerator, or non-integrated discrete device, which can run the necessary software or perform the above method flow independently of software.

[0213] In some embodiments, when the communication device 90 in FIG9 is a chip or chip system, the function / implementation process of the transceiver module 902 can be implemented through the input / output interface (or communication interface) of the chip or chip system, and the function / implementation process of the processing module 901 can be implemented through the processor (or processing circuit) of the chip or chip system.

[0214] Since the communication device 90 provided in this embodiment can execute the above method, the technical effects it can achieve can be referred to the above method embodiment, and will not be repeated here.

[0215] As a possible product form, the ACP node or first intelligent agent described in the embodiments of this application can also be implemented using one or more FPGAs, PLDs, controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits capable of performing the various functions described throughout this application.

[0216] As another possible product form, the ACP node or the first intelligent agent in this application can adopt the composition structure shown in FIG10, or include the components shown in FIG10. FIG10 is a schematic diagram of the composition of a communication device 1000 provided in this application. The communication device 1000 can be an ACP node or a module, chip or system-on-a-chip in the ACP node; or the communication device 1000 can be a first intelligent agent or a module, chip or system-on-a-chip in the first intelligent agent.

[0217] As shown in Figure 10, the communication device 1000 includes at least one processor 1001 and at least one communication interface (Figure 10 is merely an example illustrating the inclusion of a communication interface 1004 and a processor 1001). Optionally, the communication device 1000 may also include a communication bus 1002 and a memory 1003.

[0218] The processor 1001 can be a CPU, a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a PLD, or any combination thereof. The processor 1001 can also be other devices with processing capabilities, such as circuits, devices, one or more integrated circuits or software modules for controlling the execution of the program according to this application, without limitation.

[0219] The communication bus 1002 is used to connect different components in the communication device 1000, enabling communication between them. The communication bus 1002 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used in Figure 10, but this does not indicate that there is only one bus or one type of bus.

[0220] Communication interface 1004 is used for communicating with other devices or communication networks. For example, communication interface 1004 can be a module, circuit, transceiver, or any device capable of communication, such as an Ethernet interface, RAN interface, WLAN interface, transceiver, pin, bus, interface circuit, or transceiver circuit. Optionally, communication interface 1004 can also be an input / output interface located within processor 1001, used to implement signal input and signal output for the processor.

[0221] The memory 1003 may be a device with storage function, used to store instructions and / or data. The instructions may be computer programs.

[0222] For example, memory 1003 may be read-only memory (ROM) or other types of static storage devices capable of storing static information and / or instructions; it may also be random access memory (RAM) or other types of dynamic storage devices capable of storing information and / or instructions; it may also be electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices; or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0223] It should be noted that the memory 1003 can exist independently of the processor 1001, or it can be integrated with the processor 1001. The memory 1003 can be located inside or outside the communication device 1000, without limitation.

[0224] The memory stores the computer execution instructions involved in the implementation of the solution provided in this solution, and the processor controls the execution of these instructions. The processor executes the computer execution instructions stored in the memory to implement the method provided in this solution. Alternatively, in this solution, the processor may execute the processing-related functions of the method provided below, and the communication interface is responsible for communicating with other devices or communication networks; this solution does not specifically limit this aspect.

[0225] Optionally, the computer execution instructions in this solution can also be referred to as application code, and this solution does not specifically limit this.

[0226] As an optional implementation, the communication device 1000 may further include an output device 1005 and an input device 1006. The output device 1005 communicates with the processor 1001 and can display information in various ways. For example, the output device 1005 may be a liquid crystal display (LCD), a light-emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 1006 communicates with the processor 1001 and can receive user input in various ways. For example, the input device 1006 may be a mouse, keyboard, touchscreen device, or sensing device, etc.

[0227] In some embodiments, those skilled in the art will recognize that the communication device 90 shown in FIG9 can take the form of the communication device 1000 shown in FIG10 in terms of hardware implementation.

[0228] As an example, the functions / implementation of the processing module 901 and transceiver module 902 in Figure 9 can be implemented by the processor 1001 in the communication device 1000 shown in Figure 10 calling computer execution instructions stored in the memory 1003. Alternatively, the functions / implementation of the processing module 901 in Figure 9 can be implemented by the processor 1001 in the communication device 1000 shown in Figure 10 calling computer execution instructions stored in the memory 1003, and the functions / implementation of the transceiver module 902 in Figure 9 can be implemented by the communication interface 1004 in the communication device 1000 shown in Figure 10.

[0229] It should be noted that the structure shown in Figure 10 does not constitute a specific limitation on the ACP node or the first intelligent agent. For example, in other embodiments of this application, the ACP node or the first intelligent agent may include more or fewer components than shown in the figure, or combine some components, or split some components, or have different component arrangements. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0230] In some embodiments, this application also provides a communication device, which includes a processor for implementing the methods in any of the above method embodiments.

[0231] As one possible implementation, the communication device also includes a memory. This memory stores necessary computer programs and data. The computer program may include instructions, which a processor can invoke to instruct the communication device to execute the methods described in any of the above method embodiments. Alternatively, the memory may not be present in the communication device.

[0232] As one possible implementation, the communication device also includes an interface circuit, which is a code / data read / write interface circuit, used to receive computer execution instructions (which are stored in memory and may be read directly from memory or may be transmitted through other devices) and transmit them to the processor.

[0233] As one possible implementation, the communication device further includes a communication interface for communicating with modules outside the communication device. For example, the processor can be coupled to memory via the communication interface, causing the methods in any of the above method embodiments to be executed when the processor executes a computer program or instructions in the memory.

[0234] It is understood that the communication device can be a chip or a chip system. When the communication device is a chip system, it can be composed of chips or may include chips and other discrete devices. This application does not specifically limit this.

[0235] This application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a computer, implements the functions of any of the above-described method embodiments.

[0236] This application also provides a computer program product that, when executed by a computer, implements the functions of any of the above method embodiments.

[0237] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0238] It is understood that the systems, apparatuses, and methods described in this application can also be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0239] The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. The components shown as units may or may not be physical units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0240] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0241] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive (SSD)). In this embodiment, the computer may include the aforementioned apparatus.

[0242] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0243] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A communication method, characterized in that, The method includes: Obtain the first message from the first intelligent agent; The sending method of the first message is determined. The sending method of the first message is either a first sending method or a second sending method. In the first sending method, the message is sent based on the identification information of the intelligent agent. In the second sending method, the message is sent based on the semantics of the task description. The first message is sent according to the sending method of the first message.

2. The method according to claim 1, characterized in that, The first message includes instruction information, which indicates the working mode of the first intelligent agent; When the first intelligent agent operates in a standard workflow mode, the first message is sent using the first sending method; or, When the first intelligent agent operates in a dynamic workflow mode, the first message is sent using the second sending method.

3. The method according to claim 2, characterized in that, In the standard workflow, the order in which multiple intelligent agents process business is a predefined order; In the dynamic workflow, the order in which multiple intelligent agents process business is variable.

4. The method according to claim 2 or 3, characterized in that, The first message is sent using the first sending method; the first message also includes an identifier of a first standard workflow, and the multiple agents in the first standard workflow include the first agent; Sending the first message according to the sending method of the first message includes: Based on the identifier of the first standard workflow, a second intelligent agent is determined, and the second intelligent agent is the next-hop intelligent agent of the first intelligent agent in the first standard workflow; Send the first message to the second intelligent agent.

5. The method according to claim 4, characterized in that, The method further includes: Obtain information about at least one standard workflow, the at least one standard workflow including the first standard workflow, the information of the standard workflow including the identifier of the standard workflow and the order in which multiple agents process business in the standard workflow.

6. The method according to claim 2 or 3, characterized in that, The first message is sent in the first sending method; the first message also includes the identification information of the second intelligent agent, the second intelligent agent being the receiving intelligent agent of the first message; Sending the first message according to the sending method of the first message includes: The first message is sent to the second intelligent agent based on the identification information of the second intelligent agent.

7. The method according to claim 1, characterized in that, If the first message includes the identification information of the second intelligent agent, the first message is sent in the first sending method; or, If the first message does not include the identification information of the second agent, the first message is sent in the second sending method. The second intelligent agent is the intelligent agent that receives the first message.

8. The method according to claim 7, characterized in that, The first message is sent using the first sending method; sending the first message according to the first message sending method includes: Based on the information from the second intelligent agent, the first message is sent to the second intelligent agent.

9. The method according to any one of claims 2-3 or 7, characterized in that, The first message is sent using the second sending method; the first message also includes a task description; Sending the first message according to the sending method of the first message includes: Determine the semantics of the task description; Based on the semantics of the task description, the second agent is determined to be the receiving agent of the first message; Send the first message to the second intelligent agent.

10. The method according to any one of claims 1-9, characterized in that, The identification information of the intelligent agent includes the intelligent agent's identifier and / or Internet Protocol (IP) address.

11. A communication method, characterized in that, The method includes: Generate a first message, which may include instruction information or identification information of a second intelligent agent; Send the first message; The instruction information indicates that the working mode of the first intelligent agent is a standard workflow or a dynamic workflow; the second intelligent agent is the receiving intelligent agent of the first message.

12. The method according to claim 11, characterized in that, In the standard workflow, the order in which multiple intelligent agents process business is a predefined order; In the dynamic workflow, the order in which multiple intelligent agents process business is variable.

13. The method according to claim 11 or 12, characterized in that, When the instruction information indicates that the working mode of the first intelligent agent is a standard workflow, the first message also includes the identifier of the first standard workflow or the identifier information of the second intelligent agent. The first intelligent agent in the first standard workflow includes the first intelligent agent and the second intelligent agent is the receiving intelligent agent of the first message.

14. The method according to claim 13, characterized in that, The method further includes: Obtain information about at least one standard workflow, the at least one standard workflow including the first standard workflow, the information of the standard workflow including the identifier of the standard workflow and the order in which multiple agents process business in the standard workflow.

15. The method according to any one of claims 11-14, characterized in that, The identification information of the second intelligent agent includes the identifier of the second intelligent agent and / or Internet Protocol (IP) address.

16. A communication device, characterized in that, The communication device includes a processor; the processor is configured to run a computer program or instructions to cause the communication device to perform the method as described in any one of claims 1-10, or to cause the communication device to perform the method as described in any one of claims 11-15.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions or programs that, when executed on a computer, cause the method described in any one of claims 1-10 to be performed, or cause the method described in any one of claims 11-15 to be performed.

18. A computer program product, characterized in that, The computer program product includes computer instructions; when some or all of the computer instructions are run on a computer, they cause the method as described in any one of claims 1-10 to be performed, or cause the method as described in any one of claims 11-15 to be performed.

Images