Communication method and communication apparatus

Abstract

A communication method and a communication apparatus. The method comprises: in a network architecture comprising a plurality of agents, a first network element can assign, on the basis of a request of a first system agent, an identifier to a first group comprising the first system agent and at least one first service agent, and agents (for example, the first system agent and the at least one first service agent) comprised in the first group are used for processing a first task, such that the agents in the first group can subsequently be managed at the granularity of the first group, thereby achieving unified management of the plurality of agents.

Description

Communication methods and communication devices

[0001] This application claims priority to Chinese Patent Application No. 202510181176.X, filed on February 19, 2025, entitled "Communication Method and Communication Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and more specifically, to a communication method and a communication device. Background Technology

[0003] With the continuous development of artificial intelligence (AI) technology, AI models are being applied to mobile communication networks. For example, agents in mobile communication networks can use AI models to process tasks and realize the intentions of terminal devices. When the intentions of terminal devices are complex, multiple agents can collaborate to process tasks.

[0004] Currently, technologies for multiple intelligent agents to collaborate on task processing are maturing, and various network architectures involving multiple agents exist. However, for scenarios with multiple intelligent agents in the network architecture, there is a lack of solutions for unified management of these agents. Therefore, how to uniformly manage multiple agents has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a communication method and a communication device for unified management of multiple intelligent agents.

[0006] Firstly, a communication method is provided. This method can be executed by a first network element. Unless otherwise specified, the "first network element" in this application can refer to the first network element itself, or a component within the first network element (e.g., a processor, chip, or chip system, such as a circuit or chip in the first network element responsible for communication functions (e.g., a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core or a system-in-package (SIP) chip), or it can be a logic module or software that can implement all or part of the functions of the first network element.

[0007] The communication method includes: receiving first request information from a first system agent, the first request information being used to request the allocation of an identifier for a first group, the first group including the first system agent and at least one first service agent, the first group being used to process a first task, the first task being used to implement a first intent of a first terminal device; and sending first response information to the first system agent, the first response information including the identifier of the first group.

[0008] Based on the above technical solution, the first network element can assign an identifier to a first group including the first system intelligent agent and at least one first service intelligent agent based on the request of the first system intelligent agent. The intelligent agents included in the first group (e.g., the first system intelligent agent and at least one first service intelligent agent) are used to process the first task, so that the intelligent agents in the first group can be managed at the granularity of the first group, thereby realizing the unified management of multiple intelligent agents.

[0009] For example, agents in a first group can be managed uniformly at the granularity of the first group, including but not limited to the following possible methods:

[0010] For example, after the first task is completed, the first system agent sends an update request to the first network element to update the information of the first group and save the tracking or memory within the group.

[0011] For example, during the execution of the first task, the first system agent can periodically (e.g., when some sub-tasks in the first task are completed) send update requests to the first network element to update the information of the first group and save the tracking or memory within the group.

[0012] For example, during the execution of the first task, if the service agents in the first group change due to the update of a subtask of the first task, the unavailability of a certain first service agent in the first group (such as going offline), or the version update of a certain first service agent, the first system agent can send an update request to the first network element to update the information of the members (e.g., service agents) of the first group.

[0013] For example, if other tasks (such as the second task) can be processed in combination with the first task, the first system agent can send an update request to the first network element to update the task information of the first group, etc.

[0014] It should be understood that the above-listed methods for unified management of agents in the first group are merely examples and do not constitute any limitation on the scope of protection of this application. Information about the first group can also be updated in other possible situations. For example, in other cases where updates are needed, the first system agent can send an update request to the first network element to update the information of the first group. These will not be elaborated upon further here.

[0015] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: receiving second request information from the first system agent, the second request information being used to request updates to the information of the first group, the information of the first group including at least one of the following: the identifier of the first group, the information of the first task, the information of the first terminal device, the information of the first system agent, the information of the at least one first service agent, the status information of the first group, or the memory information corresponding to the first group.

[0016] Based on the above technical solution, the information of the first group can be updated through group status update information (e.g., second request information). This ensures that the information of the first group is updated promptly when updates are required, thereby improving the performance of group management.

[0017] Furthermore, group information includes various types of information (such as information about the agents included in the group, the state information of the group itself, or the memory information corresponding to the group), which can improve the accuracy of describing different groups.

[0018] In conjunction with the first aspect, in some implementations of the first aspect, when the first task and the second task are processed together, the updated information of the first group further includes: information of the second task and information of at least one second service agent, the second service agent being used to execute a sub-task in the second task, and the second task being used to implement the second intent of the first terminal device.

[0019] Based on the above technical solution, one method for updating group information is as follows: when the first task and the second task are processed together, the updated information of the first group also includes information related to the second task, such as information about the second task and information about at least one second service agent executing the second task. Therefore, when the first task and the second task are processed together, it is not necessary to create a separate group for the second task, which simplifies the process to some extent and reduces the complexity of task processing.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, if one of the at least one first service agent does not support executing the first subtask in the first task, and the third service agent supports executing the first subtask; or, if the third service agent has better performance or a newer version than the first service agent, the updated information of the first group further includes: information of the third service agent, wherein the information of the third service agent includes at least one of the identifier, version information, or type information of the third service agent.

[0021] Based on the above technical solution, one method for updating group information is as follows: If a service agent in the first group becomes unavailable (e.g., offline, faulty, updated version, etc.), other available service agents can be provided to execute the corresponding sub-tasks, avoiding the impact of task execution on the unavailability of a certain service agent. Alternatively, if an updated version or a better service agent is available, the better service agent can be used to execute the task, improving the performance of task execution.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, after the identifier of the first group is successfully assigned, the state of the first group is "pending formation"; when the first group is successfully formed, the state of the first group is "formed successfully"; when the first system agent and the at least one first service agent in the first group communicate, the state of the first group is "under discussion"; when the first group is disbanded, the state of the first group is "disbanded".

[0023] Based on the above technical solutions, the group has multiple possible states, which can more accurately locate different states and achieve more accurate group information management.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: receiving third request information, the third request information being used to request information about the first group.

[0025] Based on the above technical solution, other system agents (such as the second system agent) can obtain the information of the first group from the first network element through the third request information, so that when the second system agent receives the information of the second task of the first terminal device, it can obtain the group information that can execute the second task from the first network element, instead of directly creating a group for the second task, which simplifies the process to a certain extent and reduces the complexity of task processing.

[0026] Secondly, a communication method is provided. This method can be executed by a first system intelligent agent. Unless otherwise specified, the "first system intelligent agent" in this application can refer to the first system intelligent agent itself, or a component in the first system intelligent agent (e.g., a processor, chip, or chip system, such as a circuit or chip in the first system intelligent agent responsible for communication functions (e.g., a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), or a logic module or software that can implement all or part of the functions of the first system intelligent agent.

[0027] The communication method includes: receiving information about a first task from a first terminal device, the first task being used to implement a first intention of the first terminal device; sending first request information to a first network element, the first request information being used to request the allocation of an identifier for a first group, the first group including a first system agent and at least one first service agent, the first group being used to process the first task.

[0028] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending a second request message to the first network element, the second request message being used to request an update of the information of the first group, the information of the first group including at least one of the following: the identifier of the first group, the information of the first task, the information of the first terminal device, the information of the first system agent, the information of the at least one first service agent, the status information of the first group, and the memory information corresponding to the first group.

[0029] In conjunction with the second aspect, in some implementations of the second aspect, when the first task and the second task are processed together, the updated information of the first group further includes: information of the second task and information of at least one second service agent, the second service agent being used to execute a sub-task in the second task, and the second task being used to implement the second intent of the first terminal device. In conjunction with the second aspect, in some implementations of the second aspect, before sending the second request information to the first network element, the method further includes: receiving fourth request information from a second system agent, the fourth request information being used to request the merging of the first task and the second task; or, generating the second task, the second task being at least one sub-task of the first task.

[0030] In conjunction with the second aspect, in some implementations of the second aspect, the method further includes: sending a third request message to the first network element, the third request message being used to request that the information of one of the first sub-service intelligent agents in the at least one first service intelligent agent be updated to the information of a third service intelligent agent, the information of the third service intelligent agent including at least one of the identifier, version information, or type information of the third service intelligent agent, wherein the first service intelligent agent does not support executing the first sub-task in the first task, the third service intelligent agent supports executing the first sub-task, or the third service intelligent agent has better performance or a newer version than the first service intelligent agent.

[0031] The beneficial effects of the second aspect and some implementations thereof can be referred to the relevant descriptions in the first aspect, and will not be repeated here.

[0032] Thirdly, a communication method is provided. This method can be executed by a second system intelligent agent. Unless otherwise specified, the "second system intelligent agent" in this application can refer to the second intelligent agent itself, or a component in the second system intelligent agent (e.g., a processor, chip, or chip system, such as a circuit or chip in the second system intelligent agent responsible for communication functions (e.g., a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core), or a logic module or software that can implement all or part of the functions of the second system intelligent agent.

[0033] The communication method includes: receiving information about a second task from a first terminal device, the second task being used to implement a second intent of the first terminal device; sending a third request message to a first network element, the third request message being used to request information about a first group, the first group including a first system agent and at least one first service agent, the first group being used to process a first task, the first task being used to implement a first intent of the first terminal device; the information about the first group including at least one of the following: the identifier of the first group, information about the first task, information about the first terminal device, information about the first system agent, information about the at least one first service agent, the state of the first group, and the memory of the first group.

[0034] In conjunction with the third aspect, in some implementations of the third aspect, the method further includes: sending a fourth request message to the first system agent, the fourth request message being used to request the merging of the first task and the second task.

[0035] The beneficial effects of the third aspect and some implementations thereof can be referred to the relevant descriptions in the first aspect, and will not be repeated here.

[0036] Fourthly, a communication device is provided. This communication device is used to execute the methods described in the first aspect and any implementation thereof. For example, the communication device includes modules, units, or means corresponding to the operations involved in the first aspect. These modules, units, or means can be implemented in software, hardware, or a combination of software and hardware.

[0037] In one possible design, the communication device includes: a communication unit configured to receive first request information from a first system agent, the first request information being used to request the allocation of an identifier for a first group, the first group including the first system agent and at least one first service agent, the first group being used to process a first task, the first task being used to implement a first intent of a first terminal device. The communication unit is further configured to send first response information to the first system agent, the first response information including the identifier of the first group.

[0038] The communication unit can perform the receiving and transmitting processes described in the first aspect above, and the processing unit can perform other processes described in the first aspect above besides receiving and transmitting.

[0039] The aforementioned communication device may be a first network element, or a communication module in the first network element, or a chip in the first network element responsible for communication functions, such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a logical node, logical module, or software that can realize all or part of the functions of the first network element.

[0040] Fifthly, a communication device is provided. This communication device is used to execute the methods described in the second aspect and any implementation thereof. For example, the communication device includes modules, units, or means corresponding to the operations involved in the second aspect. These modules, units, or means can be implemented in software, hardware, or a combination of software and hardware.

[0041] In one possible design, the communication device includes: a communication unit for receiving information about a first task from a first terminal device, the first task being used to implement a first intention of the first terminal device; the communication unit is further configured to send first request information from a first network element, the first request information being used to request the allocation of an identifier for a first group, the first group including a first system agent and at least one first service agent, the first group being used to process the first task.

[0042] The communication unit can perform the receiving and transmitting processes described in the second aspect above, and the processing unit can perform other processes described in the second aspect above besides receiving and transmitting.

[0043] The aforementioned communication device may be a first system intelligent agent, or a communication module in the first system intelligent agent, or a chip in the first system intelligent agent responsible for communication functions, such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a logical node, logical module or software that can realize all or part of the functions of the first system intelligent agent.

[0044] Sixthly, a communication device is provided. This communication device is used to execute the methods described in the third aspect and any implementation thereof. For example, the communication device includes modules, units, or means corresponding to the operations involved in the third aspect. These modules, units, or means can be implemented in software, hardware, or a combination of software and hardware.

[0045] In one possible design, the communication device includes: a communication unit for receiving information about a second task from a first terminal device, the second task being used to implement a second intent of the first terminal device; the communication unit is further configured to send a third request message to a first network element, the third request message being used to request information about a first group, the first group including a first system agent and at least one first service agent, the first group being used to process a first task, the first task being used to implement a first intent of the first terminal device; the information of the first group includes at least one of the following: an identifier of the first group, information about the first task, information about the first terminal device, information about the first system agent, information about the at least one first service agent, the state of the first group, and the memory of the first group.

[0046] The communication unit can perform the receiving and transmitting processes described in the third aspect above, and the processing unit can perform other processes described in the third aspect above besides receiving and transmitting.

[0047] The aforementioned communication device may be a second system intelligent agent, or a communication module in the second system intelligent agent, or a chip in the second system intelligent agent responsible for communication functions, such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a logical node, logical module or software that can realize all or part of the functions of the second system intelligent agent.

[0048] A seventh aspect provides a communication device. The communication device includes at least one processor. The at least one processor is capable of executing a computer program or instructions, which, when executed, cause the communication device to implement the methods of any one of the first to third aspects and any implementation thereof.

[0049] In one possible design, the communication device may further include at least one interface circuit. This interface circuit is used to implement communication functions within the communication device and / or communication functions between the communication device and other devices or components.

[0050] In one possible design, the communication device may further include at least one interface circuit and / or at least one memory. The at least one processor is coupled to the at least one memory. The at least one memory is used to store part or all of the necessary computer programs or instructions for implementing the functions involved in any of the first to third aspects and any implementation thereof. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0051] In one possible design, the at least one processor is used to communicate with other devices or components via at least one interface circuit.

[0052] The aforementioned communication device may be a first network element, or a communication module in the first network element, or a chip in the first network element responsible for communication functions, or a logic node, logic module, or software that can realize all or part of the functions of the first network element.

[0053] The aforementioned communication device may be a first system intelligent agent, or a communication module in the first system intelligent agent, or a chip in the first system intelligent agent responsible for communication functions, or a logic node, logic module, or software that can realize all or part of the functions of the first system intelligent agent.

[0054] The aforementioned communication device may be a second system intelligent agent, or a communication module in the second system intelligent agent, or a chip in the second system intelligent agent responsible for communication functions, or a logic node, logic module, or software that can realize all or part of the functions of the second system intelligent agent.

[0055] Eighthly, a communication system is provided. This communication system includes at least one of the communication devices described in the fourth to sixth aspects.

[0056] A ninth aspect provides a chip or chip system. The chip or chip system includes at least one processing circuitry for executing a computer program or instructions, causing the chip or chip system to perform the methods described in the first to third aspects and any possible implementation thereof.

[0057] The chip or chip system may include output circuits or interfaces for transmitting information or data, and input circuits or interfaces for receiving information or data.

[0058] A tenth aspect provides a computer-readable storage medium. This computer-readable storage medium stores computer program code or instructions, which, when executed by a processor, implement the methods of the first to third aspects and any possible implementation thereof.

[0059] Eleventhly, a computer program product is provided. The computer program product includes: computer program code or instructions, wherein when a processor executes the computer program code or instructions, the method in any of the possible implementations of the first to third aspects is implemented.

[0060] In a twelfth aspect, a computer program is provided. When the computer program is run, it causes the methods of the first to third aspects and any possible implementation thereof to be implemented.

[0061] It should be understood that the beneficial effects of the fourth to twelfth aspects mentioned above can be referred to the first to third aspects mentioned above and any possible implementation methods, which will not be elaborated here. Attached Figure Description

[0062] Figures 1 and 2 are schematic diagrams of a communication system applicable to embodiments of this application.

[0063] Figure 3 is a schematic diagram of a communication system applicable to an embodiment of this application.

[0064] Figure 4 is a schematic diagram of another communication system applicable to embodiments of this application.

[0065] Figures 5 to 9 are schematic flowcharts of the communication method provided in the embodiments of this application.

[0066] Figure 10 is a schematic block diagram of a communication device provided in an embodiment of this application.

[0067] Figure 11 is a schematic diagram of another communication device provided in an embodiment of this application.

[0068] Figure 12 is a schematic diagram of a chip system provided in an embodiment of this application. Detailed Implementation

[0069] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0070] Before introducing the scheme of this application, the following points should be noted.

[0071] First, in this application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0072] Second, in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can mean: a, or, b, or, c, or, a and b, or, a and c, or, b and c, or, a, b, and c. Here, a, b, and c can each be single or multiple.

[0073] Third, in this application, the terms "first," "second," "#1," and "#2," as well as various numerical designations, are used for ease of description and are not intended to limit the scope of the embodiments of this application. For example, they are used to distinguish different messages, rather than to describe a specific order or sequence. It should be understood that such descriptions can be interchanged where appropriate to describe solutions other than those in the embodiments of this application.

[0074] Fourth, in this application, "instruction" or "for instruction" can include both direct and indirect instruction. When describing instruction information as being used to instruct A, it can include whether the instruction information directly or indirectly instructs A, but does not necessarily mean that the instruction information carries A.

[0075] The indication methods involved in the embodiments of this application should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated. The information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately. Moreover, the sending period and / or sending time of these sub-information can be the same or different. This application does not limit the sending method, for example.

[0076] The "instruction information" in the embodiments of this application can be an explicit instruction, that is, a direct instruction through signaling, or an instruction obtained by combining other rules or parameters with the parameters indicated by the signaling, or by deduction. It can also be an implicit instruction, that is, an instruction obtained based on rules or relationships, or based on other parameters, or by deduction. This application does not specifically limit it in this regard.

[0077] Fifth, in this application, "protocol" can refer to a standard protocol in the field of communications, such as fifth-generation (5G) protocols. thThis application does not limit the scope of network protocols such as generation (5G), New Radio (NR) protocols, and related protocols applied in future communication systems. "Predefined" may include predefined terms, such as protocol definitions. "Preconfiguration" can be achieved by pre-storing corresponding codes, tables, or other means of indicating relevant information in the device; this application does not limit the implementation method.

[0078] Sixth, in this application, terms such as "message," "information," "signal," or "information element (IE, which may be abbreviated as information element)" can be used interchangeably. There is no limitation on the name of the message or information, as long as it can achieve the corresponding function.

[0079] "Sending information to XX (device)" can be understood as the destination of the information being that device. This can include sending information to that device directly or indirectly. "Receiving information from XX (device), or receiving information from XX (device)" can be understood as the source of the information being that device. This can include receiving information from that device directly or indirectly. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly, and will not be elaborated further here.

[0080] "Communication" can also be described as data transmission, information transmission, data processing, etc. "Transmission" includes sending and / or receiving. "Transmission" can be described as output. "Sending" can also be understood as the output of a chip interface, and "receiving" can be understood as the input of a chip interface. In other words, "sending" or "receiving" can occur between devices, for example, device 1 and device 2 sending or receiving data via an air interface. "Sending" or "receiving" can also occur within a device, for example, sending or receiving data between components, modules, chips, software modules, or hardware modules within the device via a bus, wiring, or interface.

[0081] For example, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logic module within a device sending information to another logic module. For instance, "device 1 sending information" can be understood as device 1 sending information to device 2, or it can be understood as logic module 1 within device 1 sending information to logic module 2 within device 1. Similarly, "receiving information" can be understood as device 1 receiving information from device 2, or it can also be understood as logic module 1 within device 1 receiving information from logic module 2. For instance, "device 1 receiving information" can be understood as device 1 receiving information from device 2, or it can be understood as logic module 1 within device 1 receiving information from logic module 2 within device 1.

[0082] Seventh, in this application, the words "exemplarily," "for example," etc., are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as an "example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the word "example" is intended to present concepts in a concrete manner. In the embodiments of this application, "of," "corresponding, relevant," "corresponding," and "associate" may sometimes be used interchangeably, and it should be noted that their intended meanings are consistent unless their distinctions are emphasized.

[0083] The following describes the communication system to which this application applies.

[0084] The technical solutions of this application can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, 5G systems, New Radio (NR) systems, and future communication systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems.

[0085] In a communication system, a device can send signals to or receive signals from another device. These signals may include reference signals, information, signaling, or data. In this application, "device" can be replaced by an entity, network entity, communication equipment, communication module, node, or communication node.

[0086] Figure 1 is a schematic diagram of a communication system applicable to an embodiment of this application. As shown in Figure 1, the communication system 100 includes at least one terminal (120a-120j in Figure 1, collectively referred to as 120), a radio access network (RAN), and a core network (CN) 200. The RAN includes at least one RAN node (110a and 110b in Figure 1, collectively referred to as 110). The RAN may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1). The terminal 120 is wirelessly connected to the RAN node 110. The RAN node 110 is wirelessly or wiredly connected to the core network 200. The core network devices in the core network 200 and the RAN node 110 in the RAN can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0087] RAN can be used for the third-generation partner program (3 rd Cellular systems related to the Generation Partnership Project (3GPP), such as fourth-generation (4G) cellular systems. th RAN can be a generation (4G) mobile communication system, a 5G mobile communication system, or a future-oriented evolution system. RAN can also be an open radio access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN can also be a communication system that integrates two or more of the above systems.

[0088] RAN node 110, sometimes also referred to as network equipment, access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in communication system 100 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative. For example, network element 120i in Figure 1 can be a helicopter or drone, which can be configured as a mobile base station. For terminals 120j accessing the RAN through network element 120i, network element 120i is a base station; but for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes both referred to as communication devices. For example, network elements 110a and 110b in Figure 1 can be understood as communication devices with base station functions, and network elements 120a-120j can be understood as communication devices with terminal functions.

[0089] In one possible scenario, a RAN node can be a base station (BS), an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a base station in a future mobile communication system, or an access node in a WiFi system. A RAN node can be a macro base station (as shown in Figure 1, 110a), a micro base station or indoor station (as shown in Figure 1, 110b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU).

[0090] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control planes (CU-CPs), CU-user planes (CU-UPs), radio units (RUs), or CU-radio units (CU-RUs), etc. CUs and DUs can be configured separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio equipment or radio units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0091] In different systems, CU (including open CU-CP (O-CU-CP) and open CU-UP (O-CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called an open central unit (O-CU), DU can also be called an open distributed unit (O-DU), CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0092] Terminal 120 can be a device or module that accesses the aforementioned communication system and has corresponding communication functions. A terminal can also be referred to as user equipment (UE), user device, access terminal, user unit, user station, mobile station, mobile station (MS), remote station, remote terminal, mobile device, user terminal, terminal unit, terminal station, terminal device, wireless communication equipment, user agent, or user equipment. A terminal typically contains a communication module, circuit, or chip that performs the corresponding communication functions. The terminal may also be configured with program instructions for performing these communication functions.

[0093] For example, the terminal in this application embodiment can be a mobile phone, a personal digital assistant (PDA) computer, a laptop computer, a tablet computer, a drone, a computer with wireless transceiver capabilities, a machine type communication (MTC) terminal, a virtual reality (VR) terminal, an augmented reality (AR) terminal, an Internet of Things (IoT) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home (e.g., game consoles, smart TVs, smart speakers, smart refrigerators, and fitness equipment), a transport vehicle with wireless communication capabilities, a communication module, or a roadside unit (RSU) with terminal capabilities.

[0094] The RAN and terminal 120 can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenario in which the RAN and terminal 120 are located.

[0095] Communication between access network devices and terminal devices follows a specific protocol layer structure. This protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: radio resource control (RRC) layer, packet data convergence protocol (PDCP) layer, radio link control (RLC) layer, media access control (MAC) layer, or physical (PHY) layer, etc. The user plane protocol layer may include at least one of the following: service data adaptation protocol (SDAP) layer, PDCP layer, RLC layer, MAC layer, or physical layer, etc.

[0096] The correspondence between network elements and their achievable protocol layer functions in the ORAN system can be found in Table 1 below.

[0097] Table 1

[0098] CN 200 can be a 5G core network or an evolved 5G core network. Taking a 5G core network as an example, CN 200 includes access and mobility management (AMF) network elements responsible for mobility management and access management services; session management (SMF) network elements responsible for session management; user plane (UPF) network elements responsible for user plane packet routing and forwarding and quality of service (QoS) control; and policy control (PCF) network elements. These core network elements can operate independently or be combined to implement certain control functions; for example, AMF, SMF, and PCF can be combined into a single core network device.

[0099] The communication system 100 provided in this application may further include AI network elements for implementing some or all AI-related operations. AI network elements may also be referred to as AI nodes, AI devices, AI entities, AI modules, AI models, or AI units, etc. The AI ​​network elements may be built into the network elements of the communication system. For example, an AI network element may be an AI module built into: access network equipment, core network equipment, cloud server, or operation, administration, and maintenance (OAM) to implement AI-related functions. The OAM may act as the network management system for the core network equipment and / or the access network equipment. Alternatively, the AI ​​network element may also be an independently configured network element in the communication system. Optionally, the terminal or its built-in chip may also include an AI entity for implementing AI-related functions.

[0100] Figure 2 is a schematic diagram of a communication system applicable to an embodiment of this application. As shown in Figure 2, network elements in the communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in OAM, are equipped with one or more AI modules (only one is shown in Figure 2 for clarity). The access network node can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be equipped with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are provided in CU-CP and / or CU-UP.

[0101] The AI ​​module is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0102] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0103] It should be understood that the above naming is defined solely for the purpose of distinguishing different functions and should not be construed as limiting this application. This application does not preclude the possibility of using other naming conventions in 5G networks and other future networks. For example, in future networks, some or all of the above-mentioned network elements may use the terminology from 5G, or they may use other names, etc.

[0104] It is understood that Figure 1 or Figure 2 is merely an example and does not constitute a limitation on the scope of protection of this application. The communication method provided in the embodiments of this application may also involve network elements not shown in Figure 1 or Figure 2, and of course, the communication method provided in the embodiments of this application may also include only some of the network elements shown in Figure 1 or Figure 2.

[0105] To facilitate understanding of the embodiments of this application, the basic concepts involved in this application will be explained first.

[0106] 1. Artificial Intelligence (AI): AI enables machines to possess human-like intelligence, such as allowing machines to use computer hardware and software to simulate certain intelligent human behaviors. To achieve AI, machine learning methods can be employed. In machine learning, machines learn (or train) models using training data. This model represents the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result).

[0107] 2. Intelligent Agent: This is a concept in the field of artificial intelligence. Any entity capable of independent thought and interaction with its environment can be abstracted as an intelligent agent. In essence, an intelligent agent is a type of AI module. The basic characteristics of an intelligent agent are: it can react to changes in its environment and automatically adjust its behavior and state; different intelligent agents can also interact with other intelligent agents according to their own intentions.

[0108] For example, an intelligent agent can use a large language model (LLM) as its core, which includes a memory module, a tool module, a planning module, and an action module. The memory module implements long-term and / or short-term memory functions; the tool module contains multiple callable external tools; the planning module contains various planning algorithms; for example, the agent can plan external input tasks based on its memory; and the action module supports the agent in performing actions based on the planning results, such as calling up tools.

[0109] In this application, an intelligent agent can generally be considered as a proxy that can autonomously complete a set goal through action. "Intelligent agent" and "intelligence" are inseparable; it possesses some human-like intelligent abilities and behaviors, such as learning, reasoning, decision-making, and execution capabilities. Optionally, the intelligent agent can be replaced with other terms, such as artificial general intelligence (AGI), artificial intelligence, AI controller, intelligent unit, intelligent entity, or intelligent agent, etc. This application does not limit the name of the intelligent agent, as long as it can achieve the corresponding function.

[0110] In this application, the intelligent agent can be integrated into the existing hardware / software of the communication device, or the intelligent agent can be independent of the existing hardware / software of the communication device. The existing hardware / software may include at least one of the following: a chip, a baseband chip, a modem chip, a SoC chip containing a modem core, a SIP chip, a communication module, a chip system, a processor, a logic module, or software, etc.

[0111] The above description of the terminology is for ease of understanding only and does not limit the scope of protection of the embodiments of this application.

[0112] Currently, due to the continuous advancement of AI technology, the reasoning ability of AI models has been significantly improved, promoting the rapid development of intelligent agents based on large models. When the intent of a terminal device is complex, multiple intelligent agents can collaborate to process tasks.

[0113] Understandably, using multiple intelligent agents to solve the problem of complex intents in terminal devices offers several advantages, including but not limited to the following:

[0114] (1) Each intelligent agent can possess knowledge and skills in a certain service domain and can independently complete the business functions of the corresponding service domain, thereby improving the reasoning accuracy of the intelligent agent.

[0115] (2) When multiple intelligent agents cooperate with each other, complex tasks can be decomposed into multiple simple sub-tasks, reducing the processing complexity of a single sub-task.

[0116] (3) Each agent can use different AI models, and each AI model can handle its own strengths, thereby improving the accuracy and efficiency of the entire system's reasoning.

[0117] 3. System agent (sys-agent): Supports the application of large models to understand the intentions of terminal devices, decompose the intentions into tasks (e.g., the first task) of one or more service domains (e.g., perception service domain, computing power service domain, or conversation service domain), and then calls the agent of each service domain in the one or more service domains to orchestrate the tasks of the service domain.

[0118] Optionally, the system agent can decompose the intent of the terminal device into network function requirements of one or more service domains, and then determine the task for each service domain based on its network function requirements. Optionally, the system agent can also schedule network services based on task orchestration results (e.g., the orchestration result of a first task) to complete task execution. For example, the system agent can generate orchestration instructions that network elements in the network can recognize based on the task orchestration results, and send these instructions to the network elements to trigger task execution.

[0119] It should be understood that the system agent in this application may also be called the first agent, or agent A, etc., as long as it can perform the corresponding functions. No limitation is made on the name of the system agent.

[0120] 4. Service Agent (SRV-Agent): This can include agents from different service domains, such as connection agents, computation agents, or perception agents. Service agents receive task orchestration requests from system agents, support calling large local or remote models for task orchestration, and output the orchestration results. For example, service agents may include computation agents, connection agents, or perception agents.

[0121] It should be understood that the service agent in this application may also be called a second agent, or agent B, etc., as long as it can perform the corresponding functions. No limitation is made on the name of the service agent.

[0122] 5. Agent repository network element: Supports functions such as agent registration, agent discovery, and agent information storage.

[0123] It should be understood that the intelligent agent storage network element in this application can also be called an intelligent agent storage node or an intelligent agent information storage network element, as long as it can perform the corresponding functions. No limitation is made on the name of the intelligent agent storage network element.

[0124] 6. Prompt: In large AI models, the primary role of a prompt is to provide the model with contextual information about the input and the model's parameters. When training supervised or unsupervised learning models, a prompt helps the model better understand the intent of the input and respond accordingly. Furthermore, a prompt can improve the model's interpretability and accessibility.

[0125] In layman's terms, a prompt is to provide an AI model with a "hint" or "guidance" to help it better understand and complete tasks.

[0126] For example, a prompt is not just a question or query entered by the user; it also includes instructions, external information (context), output prompts, and more. The user output or query is typically (but not always) a query entered into the system by the user (i.e., the prompter); the instructions tell the model what to do, how to use external information (if provided), how to process the query, and how to construct the output; the external information (context) acts as an additional source of knowledge for the model. This can be manually inserted into the prompt, obtained through retrieval from a vector database (retrieval enhancement), or introduced through other means (API, computation, etc.); the output indicator marks the beginning of the text to be generated.

[0127] It should be noted that modern communication networks are characterized by diversity, heterogeneity, and massive scale. The devices within these networks involve various terminals, such as IoT devices, augmented reality (AR) terminals, and virtual reality (VR) terminals, resulting in a dramatic increase in the number of devices. Due to the constant changes in user behavior, business needs, and network load, the dynamic nature of networks has increased, requiring real-time adjustments to resource allocation and optimization strategies. Future networks can leverage AI to address issues such as flexibility and dynamic change.

[0128] Furthermore, as multi-agent technology matures, agents can observe the environment, analyze and think, and flexibly utilize a range of tools. Future network architectures may introduce AI agents to drive network service processes, thereby improving network management efficiency, supporting the flexible development of new services, and promoting the evolution of network autonomy and intelligence.

[0129] Currently, while agents can accomplish tasks through agent architecture, they haven't considered multicast or discussion modes within groups. This leads to problems such as competition among multiple agents of the same type and the need for multiple rounds of iterative discussions, resulting in a lack of unified group management capabilities. For example, assigning group identities (IDs) through system agents may cause ID conflicts, failing to guarantee the uniqueness of IDs within the domain. Furthermore, different discussion groups for different tasks on the same terminal may experience task orchestration conflicts if they cannot share business chat logs. Additionally, the lack of saving or backing up group history information prevents the synchronization of historical information when system agents re-enter the network, and also hinders the system agents' ability to reflect, learn, and optimize orchestration capabilities.

[0130] In view of this, this application provides a communication method and apparatus that enables unified management of multiple intelligent agents.

[0131] Below, we will first illustrate the network architecture provided in the embodiments of this application with reference to Figure 3.

[0132] Figure 3 is a schematic diagram of a communication system applicable to an embodiment of this application. As shown in Figure 3(a), an AI mobile network architecture for multi-agent collaboration is proposed. This architecture may include a first network element (e.g., a group repository), agents, a second network element (e.g., an agent repository network element), and a third network element (e.g., a task-centric function (TCF)). The agents in this application include system agents and service agents.

[0133] Optionally, the architecture may also include at least one of the following: a message bus (e.g., an agent message bus), a fourth network element in the network (e.g., the fourth network element supports network services), or a terminal device, etc.

[0134] As an example, the functional modules included in the system's intelligent agent are shown in Figure 3(b). The network task management module organizes sys-agents and service agents into a task intelligent orchestration working group, and enables intelligent orchestration collaboration among the group's intelligent agents to obtain instructions that drive third-party network elements to schedule and execute network services. The agent topology management module manages the topology of local agents, providing functions such as agent selection, agent discovery, agent registration, and deregistration. The task orchestration codec module encodes the output of the network task management module, generating instructions that the third-party network element can understand and recognize, and calls the third-party network element interface to issue instructions to the third-party network element to schedule network services for task execution. The agent connection management module implements the underlying transmission connection management and state maintenance for information interaction and communication among multiple agents. The underlying transmission protocol can be Transmission Control Protocol (TCP), Hypertext Transfer Protocol (HTTP), or other protocols, without limitation.

[0135] As an example, the functional modules included in a service agent are shown in Figure 3(c). The task orchestration module receives task orchestration requests from system agents and utilizes the AI ​​model and knowledge base of the service domain for reasoning and task orchestration to obtain the orchestration results. The agent topology management module manages the topology of the local agents, providing functions such as agent selection, agent discovery, agent registration, and deregistration. The agent connection management module manages the underlying transmission connection and state maintenance for information interaction and communication among multiple agents.

[0136] The first network element can manage information about various task groups. The first network element can also be called a group repository network element.

[0137] It should be noted that the architecture shown in Figure 3(a) is merely an example and does not constitute any limitation on the scope of protection of this application. The first network element can be deployed independently (e.g., the independent deployment method shown in Figure 3(a)), or the first network element can be co-located with other network elements (e.g., agent repository network elements). For example, the function of the first network element can be implemented by the agent repository network element, which can be understood as enhancing the agent repository network element in the current network architecture so that the agent repository network element has the functions of the current agent repository network element and the functions of the first network element in this application.

[0138] It should be understood that this application does not impose any restrictions on the name and deployment method of the first network element, as long as it can achieve the corresponding function.

[0139] For example, the group information managed by the first network element can be described by a group profile, which may include, but is not limited to, at least one of the following:

[0140] 1) Group Identifier (ID): Used to uniquely identify a group. For example, the group identifier may include the public land mobile network (PLMN), the identifier of the terminal equipment, and the identifier of the mission. For example, the group ID is PLMN + UE ID + prompt ID.

[0141] 2) Task prompt: The instruction or request issued by the UE to the AI, such as the task ID, intent description, etc.

[0142] 3) Terminal device information (info): Information about the terminal device that initiated the task request, such as UE ID, type, etc.

[0143] 4) Information about system agents: Information about system agents in the group, such as the system agent's ID, type, status, load, or version.

[0144] 5) Service Agent List: Information about at least one service agent in the group. For example, the information of a service agent includes a list of information such as the service agent's ID, type, status, load, or version.

[0145] 6) Group status information: Indicates whether the group has not been created, the group has been successfully created, the group is in discussion, or the group has been disbanded.

[0146] 7) Group memory information: Indicates the tracking of group dialogue history, shared memory, etc., such as the process of agents in the group acquiring, storing, retaining and subsequently retrieving information.

[0147] Group memory is divided into short-term memory and long-term memory, including task results, reasons for results, contextual information of discussions, and chat history for each round (such as task ID, result, reason, etc.).

[0148] In addition, group memory can also be called group track, group dialogue history tracking, co-memory, etc., and this application does not limit it to these terms.

[0149] The second network element supports automatic online registration, capability registration, and inter-agent discovery functions for intelligent agents within the network. As an example, the functional modules included in the second network element are shown in Figure 3(d). The intelligent agent registration management provides intelligent agent registration and / or deregistration interfaces. When an intelligent agent goes online, it can call the registration interface to report its information to the second network element, such as at least one of the following: intelligent agent identifier, capabilities, roles, open interfaces, supported protocols, or location information. When an intelligent agent goes offline, it can call the deregistration interface to request the deletion of its information from the second network element. The intelligent agent discovery management provides a discovery interface. Intelligent agents (e.g., sys-agents) can call the discovery interface to discover service agents in a specific service domain. The input information for the discovery interface can be at least one of the intelligent agent's capabilities, roles, or location information.

[0150] The agent repository network element is used to store agent information and provides interfaces for adding, deleting, and modifying information for agent registration and discovery. This agent repository network element can also be called an agent repository or agent information database, etc. This application does not impose any restrictions on the name of the network element, as long as it can perform the corresponding functions.

[0151] A message bus can be viewed as a distributed message bus for collaboration and dialogue among multiple intelligent agents. In one implementation, the message bus can be coupled to the intelligent agents (e.g., system agents or service agents), or embedded within the agents as an internal functional module. In this implementation, the system agent can directly send a first request message to the service agent, thus achieving rapid point-to-point communication among multiple agents. In another implementation, the message bus can be decoupled from the intelligent agents (e.g., system agents or service agents), or acting as an independent routing node. In this implementation, the system agent can forward the first request message to the service agent through the agent message bus. For example, after receiving a second request message from the system agent, the message bus can perform rapid message routing and forwarding based on the service agent's identifier and / or address, thereby improving efficient collaboration among multiple agents and ultimately realizing the intent of the terminal device. In schemes where messages between multiple agents are forwarded through a server, the server needs to manage the multiple agents, such as managing their information (e.g., agent identifiers), making the process complex. In contrast, the message bus eliminates the need for multi-agent management, enabling rapid message routing and forwarding based on service agent information, thus improving collaboration efficiency among agents. As an example, the functional modules included in the message bus are shown in Figure 3(e). The agent routing module stores the relationship between agent identifiers and agent addresses, and routes and forwards messages based on the agent identifiers. The agent reachability management module stores the reachability status of agent addresses; if the agent address is reachable, the message can be routed; otherwise, message routing fails and an error code is returned. Agent reachability can be checked periodically. The agent connection management module manages the underlying transmission connections and maintains the state of information interaction and communication among multiple agents.

[0152] Optionally, the agent connection management module in the above-mentioned system agent and / or service agent can be connected to the agent message bus to realize functions such as routing management, status reporting, and message reception and forwarding.

[0153] The third network element supports receiving task instructions from the system's intelligent agent, scheduling network services to execute tasks, and realizing network service functions. The network services involved in this application can be network atomic services or other services, as long as they provide a service interface for the third network element to schedule. For example, network services may include at least one of the following: access services, session services, computing power services, sensing services, or other services.

[0154] A terminal device acts as a mobile terminal requesting network services. In one implementation, the terminal device can send its intent, such as requesting computing resources, to a system agent or a third-party network element.

[0155] As one implementation approach, the system agent, service agent, first network element, second network element, and third network element in the above network architecture can be deployed as independent network elements. The message bus can also be an independent network element, such as an agent message router deployed independently, or it can be deployed as a functional module within the system agent and / or service agent. There are no limitations on this.

[0156] Figure 4 is a schematic diagram of another network architecture applicable to embodiments of this application.

[0157] As shown in Figure 4, this system architecture includes multiple system agents (e.g., system agents 1 to N) and multiple service agents (e.g., connection service agents 1 to 3, computing power service agents 1 and 2, and sensory agent 1) within an area 1. Furthermore, the system architecture 300 also includes a first network element (e.g., a group storage repository) and a second network element (e.g., an agent storage repository network element). System agents can request a group ID from the first network element and form a service agent group. After the task is completed, the system agents can also send updated group information to the first network element and save tracking or memories within the group. Additionally, during task execution, if an update subtask is triggered, or if a service agent becomes unavailable (e.g., suddenly goes offline), or if a version update causes changes to the service agent, the system agents can also update the latest group member information to the first network element.

[0158] It should be understood that the naming of network elements in the above network architecture is defined only for the convenience of distinguishing different functions and does not constitute a limitation on this application. This application does not exclude the possibility of using other names for various network elements in mobile network architecture and other future networks. For example, the above-mentioned agent storage network element can also be called agent storage node or agent information storage network element, etc., and there is no limitation in this regard.

[0159] It should also be understood that the network architectures shown in Figures 3 and 4 are examples given to understand the technical solutions and do not constitute a limitation on the scope of protection of this application.

[0160] The following examples, in conjunction with Figures 5 to 9, illustrate the communication method provided in the embodiments of this application, which can be applied to the aforementioned network architecture. The embodiments of this application use a first network element (e.g., a group repository), a system agent (e.g., a system agent), a service agent (e.g., a service agent), and a second network element (e.g., an agent repository network element) as the execution subjects for illustrative purposes. The execution subjects, such as the first network element, system agent, service agent, and second network element, can be the first network element, system agent, service agent, or second network element itself, or components within the first network element, system agent, service agent, or second network element (e.g., processors, chips, or chip systems, such as circuits or chips in the system agent responsible for communication functions (e.g., modem chips, also known as baseband chips, or SoC chips or SIP chips containing modem cores), or logic modules or software capable of implementing all or part of the functions).

[0161] Figure 5 is a schematic flowchart of a communication method provided in an embodiment of this application. As shown in Figure 5, the method includes the following steps. For details not covered herein, please refer to the relevant descriptions in existing solutions. For the sake of brevity, these details will not be elaborated here.

[0162] S510, the first system intelligent agent sends a first request message to the first network element, and correspondingly, the first network element receives the first request message from the first system intelligent agent.

[0163] For example, the description of the first system intelligent agent can be found in Figure 3 above, and will not be repeated here. Similarly, the description of the first network element can be found in Figure 3 above, and will not be repeated here.

[0164] The first request information is used to request the allocation of an identifier for a first group, which includes the first system agent and at least one first service agent. The first group is used to process a first task, which is used to implement a first intent of the first terminal device.

[0165] It should be noted that the first system agent included in the aforementioned first group can also participate in other groups besides the first group. For example, the first group includes the first system agent and at least one first service agent, and group #A includes the first system agent and at least one service agent #A. That is, the first system agent can participate in the first group and also in group #A. Similarly, the same service agent can participate in multiple groups. For example, the first group includes the first system agent and service agent #B, and group #B includes system agent #B and service agent #B. That is, service agent #B can participate in the first group and also in group #B.

[0166] For example, the first request information includes at least one of the following parameters: the identifier of the first terminal device, the information of the first task, or the information of the first system agent. The identifier of the first terminal device is used to identify the first terminal device and may be information capable of identifying the first terminal device, such as a subscription permanent identifier (SUPI), a temporary identifier, or a permanent device identifier. The information of the first task may be information capable of identifying the first task, such as a description or ID. The information of the first system agent may be information capable of identifying the first system agent, such as its ID or version information.

[0167] In this application, the first system agent can communicate directly with the first network element. For example, the first system agent can sense the first network element through pre-configuration or other means; alternatively, the first system agent can establish communication with the first network element through other methods. This application does not limit the communication methods between the first system agent and the first network element. For example, the first network element and the agent storage network element can be co-located. The communication methods between the first system agent and the first network element can be found in the description of the communication methods between the first system agent and the agent storage network element, and will not be illustrated here.

[0168] For example, the first system agent can trigger the above step S510 after receiving a task prompt from the first terminal device and determining, based on the type of the first task requested by the task prompt and the identifier of the first terminal device, that there is no group corresponding to the first task.

[0169] Furthermore, after receiving the aforementioned first request information, the first network element can assign identification information to the first group and notify the first system agent through the first response information. Therefore, the method flow shown in Figure 5 further includes:

[0170] S520, the first system intelligent agent receives the first response information from the first network element, and correspondingly, the first network element sends the first response information to the first system intelligent agent.

[0171] The first response information includes an identifier for the first group. For example, the first response information carries a Group ID that is unique within the domain and assigned to the first network element, such as PLMN+UEID+promptID.

[0172] As described above, the first network element can manage the information of the first group, which may include the identifier of the first group, and at least one of the following:

[0173] Information about the first task, information about the first terminal device, information about the first system agent, information about at least one first service agent, status information of the first group, or memory information corresponding to the first group.

[0174] The information of the first task may include information about at least one subtask contained in the first task, such as the description information of the at least one subtask.

[0175] The information of the first terminal device can be the identifier of the first terminal device. The identifier of the first terminal device is used to identify the first terminal device and can be information that can identify the first terminal device, such as the SUPI, temporary identity identifier, or permanent device identifier.

[0176] The information of the first system agent can be related to the first system agent, such as the first system agent's ID, type, state, load, or version.

[0177] The information of at least one first service agent indicates at least one first service agent included in the first group, and the information of each first service agent may be information such as the service agent's ID, type, status, load, or version.

[0178] The status information of the first group is used to indicate the status of the first group, such as not formed, successfully formed, under discussion, disbanded, etc. Optionally, after the identifier of the first group is successfully assigned, the status of the first group is pending formation; when the first group is successfully formed, the status of the first group is successfully formed; when the first system agent and at least one first service agent in the first group are communicating, the status of the first group is under discussion; when the first group is disbanded, the status of the first group is disbanded.

[0179] The memory information corresponding to the first group indicates the tracking of the dialogue history and shared memory of the first group, such as the process by which agents within the group acquire, store, retain, and subsequently retrieve information. The memory corresponding to the first group is divided into short-term memory and long-term memory, including the result of the first task, the reason for the result, the context information of the discussion, and the chat history of each round (such as task ID, result, reason, etc.). Furthermore, the memory information corresponding to the first group can also be referred to as the group track, the dialogue history tracking of the first group, or the shared memory of the first group; this application does not limit this terminology.

[0180] Optionally, the first system agent can request updates to the information of the first group through the second request information. In this case, the method flow shown in Figure 5 further includes:

[0181] S530, the first system intelligent agent sends a second request message to the first network element, and correspondingly, the first network element receives the second request message from the first system intelligent agent.

[0182] The second request information is used to request updates to the information in the first group.

[0183] As one possible implementation, the second request information used to request updates to the information in the first group could be:

[0184] After the first task is completed, the first system agent requests an update to the state of the first group to be disbanded via a second request message; or,

[0185] During the execution of the first task, the first system agent can periodically (e.g., when some sub-tasks in the first task are completed) send second request information to the first network element, update the information of the first group, etc.

[0186] For example, the working status of one or more first service agents within the first group may change. For instance, the first group includes first service agents #1, #2, and #3. After completing the sub-task assigned to a certain task, first service agents #1, #2, and #3 can reuse agent update information and report their own status update to idle.

[0187] It should be noted that the above-mentioned service agent updating its status to idle after completing a subtask assigned to a task is merely an illustrative description of the service agent's working state changes and does not constitute any limitation on the scope of protection of this application. After completing a subtask assigned to a task, the service agent may not necessarily become idle and may continue to complete other tasks, which will not be elaborated here.

[0188] To facilitate understanding, the process of forming and disbanding the first group under this implementation method will be described in detail below with reference to Figure 6. Detailed explanations will not be provided here.

[0189] As another possible implementation, the second request information used to request updates to the first group could be:

[0190] Update the information of the service agents included in the first group.

[0191] For example, if one of the at least one first service agents does not support executing the first subtask in the first task, and the third service agent supports executing the first subtask; or if the third service agent has better performance or a newer version than the first service agent, the updated information of the first group further includes: information of the third service agent, wherein the information of the third service agent includes at least one of the identifier, version information, or type information of the third service agent.

[0192] For example, during the execution of the first task, if at least one of the first service agents, namely the first service agent #1, suddenly becomes offline and unavailable or times out and becomes unresponsive, it will be unable to support the execution of the first sub-task in the first task. The first system agent can discover a new service agent to execute the first sub-task in the first task. For example, the first system agent can discover a third service agent through an agent discovery message, which carries filtering information (e.g., filtering information such as not selecting the first service agent #1).

[0193] For example, during the first task, the first system agent discovers that the periodically received service agent information has an updated version or a better service agent (e.g., a third service agent).

[0194] For ease of understanding, the process of agents in the first group updating the information of the first group during the discussion will be described in detail below with reference to Figure 7. Detailed explanation will not be provided here.

[0195] As another possible implementation, the second request information used to request updates to the information in the first group could be:

[0196] In the case where the first task and the second task are processed together, the updated information of the first group also includes: information of the second task and information of at least one second service agent, the second service agent being used to execute a sub-task in the second task, and the second task being used to realize the second intent of the first terminal device.

[0197] For example, in this implementation, the first system agent may request updates to the information of the first group through the second request information in the following ways, including but not limited to:

[0198] Possibility 1: The first system agent receives a fourth request from the second system agent, the fourth request being used to request the merging of the first task and the second task.

[0199] In this implementation, the second system agent receives information about a second task from the first terminal device, whereby the second task is used to implement the second intent of the first terminal device. The second system agent sends a third request message to the first network element, which requests information about the first group. If the first group of the first terminal device is currently executing the first task, the second system agent sends a task update request (e.g., the fourth request message mentioned above) to the first system agent, sending the information about the second task of the first terminal device to the first system agent for merging processing. The fourth request message includes the identifier of the first terminal device and the information about the second task.

[0200] For ease of understanding, the process of updating information in the first group under the possible scenario shown in Figure 8 will be described in detail below, but will not be explained in detail here.

[0201] Possibility Two: The first system agent determines that the first task requires an additional subtask, and the current service agents within the group cannot handle it. In the scenario shown, the aforementioned second task can also be understood as at least one subtask of the first task.

[0202] For ease of understanding, the process of updating information in the first group under the possible scenario shown in Figure 9 will be described in detail below, without going into further detail here.

[0203] Additionally, it should be noted that after the second system agent receives the information of the second task from the first terminal device, the first and second tasks may not be processed together. That is, the second system agent can create a second group based on the second task. The second group includes the second system agent and at least one fourth service agent. In other words, the method flow shown in Figure 5 also includes:

[0204] S501, the second system intelligent agent sends a first request message #2 to the first network element, and correspondingly, the first network element receives the first request message #2 from the second system intelligent agent.

[0205] S502, the second system intelligent agent receives the first response information #2 from the first network element, and accordingly, the first network element sends the first response information #2 to the second system intelligent agent.

[0206] S503, the second system intelligent agent sends a second request message #2 to the first network element, and correspondingly, the first network element receives the second request message #2 from the second system intelligent agent.

[0207] It should be understood that the creation process, update process and related descriptions of the second group can refer to the description of the first group above. That is, steps S501 to S503 can refer to the description of steps S510 to S530 above, and will not be repeated here.

[0208] For example, the first network element can provide group information to system agents in the network architecture. For instance, the first network element can receive a third request from a system agent (e.g., the first system agent, the second system agent, or other system agents), the third request being used to request information about the groups managed by the first network element (e.g., information about the first group mentioned above or information about other groups managed by the first network element).

[0209] Additionally, it should be noted that the first system agent can also provide group information to other system agents in the network architecture. For example, the first system agent receives a third request from other system agents (such as the second system agent). The third request is used to request information about the groups in which the first system agent participates (such as the information of the first group mentioned above or the information of other groups in which the first system agent participates).

[0210] In this application, a system agent can act as the receiver of a third request message, providing group information to other system agents; or, a system agent can act as the sender of a third request message, requesting group information from other system agents or the first network element.

[0211] In the communication method shown in Figure 5, the first network element can assign an identifier to a first group including the first system intelligent agent and at least one first service intelligent agent based on the request of the first system intelligent agent. The intelligent agents included in the first group (e.g., the first system intelligent agent and at least one first service intelligent agent) are used to process the first task, so that the intelligent agents in the first group can be managed at the granularity of the first group, thereby realizing the unified management of multiple intelligent agents.

[0212] For ease of understanding, the following uses the first network element as the group storage network element, and at least one service agent in the first group including computing power service agents, connection service agents, etc. as an example, and uses Figures 6 to 9 to illustrate how the communication method provided in this application can uniformly manage multiple agents.

[0213] Figure 6 is a schematic flowchart of another communication method provided in an embodiment of this application. This communication method is applicable to scenarios involving the formation of a group comprising multiple agents and the updating of group information upon disbanding the group. The communication method includes the following steps:

[0214] S610, System Intelligent Agent #1 Sensing Group Storage Network Element.

[0215] For example, when System Agent #1 (Sys Agent #1) goes online, it can perceive the group repository network element through pre-configuration or other means, and System Agent #1 can directly communicate with the group repository network element.

[0216] S620, System agent #1 determines whether a corresponding first group exists.

[0217] Specifically, system agent #1 receives a task request (prompt) from the first terminal device and determines whether there is a first group corresponding to the first task based on the type of the first task requested in the received task request and the identifier of the first terminal device.

[0218] When system agent #1 determines that there is no first group corresponding to the first task, the method flow shown in Figure 6 further includes:

[0219] S630, System Agent #1 sends Request Message #1 to the Group Storage Network Element.

[0220] The request information #1 is used to request the allocation of a group ID for the first group. The request information #1 includes at least one of the following parameters: the identifier of the first terminal device, information about the first task, or information about the first system agent.

[0221] Optionally, request information #1 can be understood as the first request information in the communication method shown in Figure 5 above.

[0222] It should be noted that this request information #1 can also be called group apply request information, group ID allocation request information, etc. This application does not limit the name of this request information #1.

[0223] S640, the group storage network element sends response information #1 to system agent #1.

[0224] Specifically, in response to request information #1, the group repository network element sends response information #1 to system agent #1. Response information #1 includes group ID1, which is a unique group ID assigned by the group repository network element to system agent #1 for the first group within the domain, such as PLMN+UEID+promptID. This group ID1 corresponds to the first task, or in other words, group ID1 corresponds to system agent #1.

[0225] Optionally, response information #1 can be understood as the first response information in the communication method shown in Figure 5 above.

[0226] S650, system agent #1 performs task allocation and at least one service agent executes and discusses the first task.

[0227] S660 and system agent #1 integrate the sub-tasks of the first task and determine whether the first task has been completed.

[0228] If the first task is completed, proceed with the following steps:

[0229] S670, System Agent #1 terminates the first task and disbands the first group. The execution result of the first task is output to the first terminal device.

[0230] As can be seen from the above, after the group is formed through steps S630 and S640, the agents within the group can perform information interaction as in steps S640 to S670, and execute processes such as task allocation, discussion, execution, integration, and disbandment.

[0231] For example, the first group status update specifically includes the following steps:

[0232] S601, Information update of the computing power service agent.

[0233] For example, the computing power service agent interacts with the agent repository network element to exchange computing power service agent update request information and response information to achieve information updates for the computing power service agent. The computing power service agent update request information can be a reused update request from the computing power service agent; the computing power service agent update response information can also be a reused update response from the computing power service agent.

[0234] For example, the computing power service agent sends update request information #2 to the agent repository network element. Update request information #2 is used to report information about the computing power service agent, such as updating the status of the computing power service agent to idle. Correspondingly, the agent repository network element receives update request information #2 from the computing power service agent and, in response to update request information #2, sends update response information #2 to the computing power service agent. This update response information #2 includes the update result, such as whether updating the status of the computing power service agent to idle was successful or failed.

[0235] S602, Information update of the connection service agent.

[0236] For example, the connection service agent interacts with the agent repository network element to exchange connection service agent update request information and response information to achieve information updates for the connection service agent. The connection service agent update request information can be a reused connection service agent update request; the connection service agent update response information can also be a reused connection service agent update response information.

[0237] For example, the connection service agent sends update request information #3 to the agent repository network element. Update request information #3 is used to report information about the connection service agent, such as updating the connection service agent's status to idle. Correspondingly, the agent repository network element receives update request information #3 from the connection service agent and, in response to update request information #3, sends update response information #3 to the connection service agent. This update response information #3 includes the update result, such as whether updating the connection service agent's status to idle was successful or failed.

[0238] S603, Information update of system agent #1.

[0239] For example, system agent #1 interacts with the agent repository network element to update system agent #1's information by exchanging update request and response information. The system agent #1's update request information can be a reused update request from system agent #1; the system agent #1's update response information can also be a reused update response from system agent #1.

[0240] For example, system agent #1 sends update request information #4 to the agent repository network element. Update request information #4 is used to report information about system agent #1, such as updating the status of system agent #1 to idle. Correspondingly, the agent repository network element receives update request information #4 from system agent #1 and, in response to update request information #4, sends update response information #4 to system agent #1. Update response information #4 includes the update result, such as whether updating the status of system agent #1 to idle was successful or failed.

[0241] S604, System agent #1 sends a group status update request to the group storage network element.

[0242] The group status update request information is used to request an update to the group file. The group status update request information includes group ID1 and information for updating the group file. It can be understood that the information for updating the group file is used to update the content of the group file.

[0243] Optionally, the group status update request information can be understood as the second request information in the communication method shown in Figure 5 above.

[0244] For example, the information used to update the group file includes a group status of "successfully created," etc. The group status update request information may also include information such as the ID, type, status, load, version, and group chat history of the service agents that need to be created to form the group.

[0245] Specifically, the group repository network element updates the group file based on the group status update request information. It can use the group ID1 and the information used to update the group file to update the content of the corresponding group file. For details of the content, please refer to the description of the group file in Figure 3, which will not be repeated here.

[0246] Specifically, after the group is successfully formed (i.e., after system agent #1 sends a group formation request to the service agent that needs to form the group and receives a response), a group status update request is sent.

[0247] For example, the group repository network element updates the group ID in the group file to group ID1 and updates the group status in the group file to "successfully established".

[0248] For example, system agent #1 obtains the group ID as group ID1 through steps S630 and S640. The service agents that need to establish the group include the connection service agent and the computing power service agent. Then the group status update request information includes the ID of the connection service agent, the ID of the computing power service agent, group ID1, and the group chat history.

[0249] S605, the group storage network element sends group status update response information to system agent #1.

[0250] The group status update response information is in response to the group status update request information, and the group status update response information may include the result of the update, such as update success / failure.

[0251] It should be understood that the above steps S604 and S605 are merely examples of a first group information update process and do not constitute any limitation on the scope of protection of this application. The information update of the first group may also have other possible forms. For example, during the execution of the first task, the system agent #1 may periodically (e.g., when some sub-tasks in the first task end) send update requests to the group storage network element to update the information of the first group and save the tracking or memory within the group. The update process can be referred to the description of the above steps S604 and S605, and will not be repeated here.

[0252] Figure 7 is a schematic flowchart of another communication method provided in an embodiment of this application. This communication method is applicable to scenarios where, after a system agent receives responses from all required service agents and successfully forms a team, during the subsequent task allocation discussion phase, it discovers that a certain service agent is unavailable or a newer version is available, and updates the group member information to the group repository. The communication method includes the following steps:

[0253] S710, system agent #1 sends information #1 to agent storage network element.

[0254] Information #1 is used to subscribe to agent information. Optionally, in the communication method shown in Figure 7, system agent #1 subscribes to agent information from the agent repository network element to obtain information about service agents in the network. This agent information is used for subsequent task decomposition and orchestration.

[0255] For example, the service agents in the network include connection service agents and computing service agents #1.

[0256] S720, the agent storage network element sends agent information to system agent #1.

[0257] Agent information includes information such as the type of service agent and the corresponding capability description.

[0258] For example, system agent #1 can unsubscribe from information about service agents in the network. The agent repository network element can periodically send information about agents in the network to system agent #1.

[0259] Optionally, the agent information sent by the agent storage network element to the system agent #1 includes the identifier and capability description of the connection service agent, the identifier and capability description of the computing power service agent #1, and other information.

[0260] S730, the first group was formed.

[0261] For example, a first group with group ID 1 can be created.

[0262] S740, System Agent #1 sends a group creation request to the group storage network element.

[0263] After the first group is successfully formed (i.e., after system agent #1 sends a group formation request to at least one required service agent and receives a response), system agent #1 sends a group establishment request to the group storage network element to update the status of the first group to the group storage network element. The group establishment request information includes the identifier of the first group, the status of the first group as "successfully established", and other group file information.

[0264] Optionally, the group creation request information can reuse the group status update request information. For a description of the group status update request information, please refer to the description of step S604 in Figure 6, which will not be repeated here.

[0265] S750, the group storage network element sends group establishment response information to system agent #1.

[0266] The group creation response information responds to the group creation request information.

[0267] Optionally, the group creation response information is a reused group status update response information. For a description of the group status update response information, please refer to the description of step S605 in Figure 6, which will not be repeated here.

[0268] S760, System Agent #1 assigns tasks, and the service agents in the first group execute and discuss them.

[0269] For example, the service agent performs and discusses multiple rounds. That is, the system agent #1 can exchange multiple rounds of request and response information with the service agent.

[0270] As an example, and not a limitation, the following situations may occur during the task assignment discussion phase:

[0271] Scenario 1: During the task, one or more service agents in the first group become unavailable or unresponsive. For ease of description, we will use the example of a single service agent becoming unavailable or unresponsive. The description of multiple service agents becoming unavailable or unresponsive can be referred to the description of a single service agent becoming unavailable or unresponsive, and will not be repeated here.

[0272] For example, during the task, the connection service agent #1 suddenly becomes offline and unavailable or times out and becomes unresponsive.

[0273] Scenario 2: During the task, system agent #1 discovers that there is an updated version of the service agent in the network or that there is a better service agent.

[0274] For example, during the task, system agent #1 periodically receives agent information from agent repository network elements and discovers that there are updated or better service agents in the network. For example, the computing power service agent #1 in the current network has an updated or better computing power service agent #2.

[0275] In the case shown in Case 1 or Case 2, the method flow shown in Figure 7 may also include the following step S701.

[0276] S701, System Agent #1 discovers and connects to Service Agent #2.

[0277] Specifically, system agent #1 interacts with agent repository network elements to exchange service agent discovery request information and service agent discovery response information in order to discover and connect to service agent #2.

[0278] For example, in the above scenario one: System agent #1 discovers that connection service agent #1 is unavailable or has timed out without response, and sends a connection service agent discovery request to the agent repository network element; or,

[0279] For scenario two above: If system agent #1 discovers that there is an updated version or a better service agent among the agent information it receives periodically, then system agent #1 can send a service agent discovery request to the agent repository network element.

[0280] The aforementioned connection service agent discovery request information is used to request the discovery of other connection service agents, excluding connection service agent #1. This connection service agent discovery request information carries filtering information, which indicates that connection service agent #1 should not be selected; or, in other words, the filtering information indicates that other connection service agents should be selected. The agent repository network element sends a connection service agent discovery response information to system agent #1, which is used to provide feedback on the discovered connection service agents.

[0281] As an example, the connection service agent discovery response message includes information about connection service agent #2.

[0282] As another example, the connection service agent discovery response message includes information from multiple connection service agents (i.e., multiple agents, including service agent #2).

[0283] For example, the information of the connection service agent #2 includes at least one of the following: the identifier of the connection service agent #2 (e.g., the ID of the connection service agent #2), or the open interface supported by the connection service agent #2 (e.g., an interface such as a URL or API).

[0284] Optionally, the information of the connection service agent #2 may also include at least one of the following: the deployment location of the connection service agent #2, the service domain of the connection service agent #2, the protocols supported by the connection service agent #2, the capabilities of the connection service agent #2, the role of the connection service agent #2, the models supported by the connection service agent #2, or the service domain of the connection service agent #2, etc.

[0285] Furthermore, after system agent #1 discovers connection service agent #2, it notifies connection service agent #2 to join the first group and continues to execute the first task. The method flow shown in Figure 7 can also include the following steps:

[0286] S770, System Agent #1 reassigns tasks, and the service agents in the first group execute and discuss them.

[0287] System agent #1 performs new task allocation in the first group of group ID1, and at least one service agent discusses and executes the task. It is understood that the at least one service agent does not include computing power service agent #1, but includes connection service agent #1 and computing power service agent #2.

[0288] S780, System Agent #1 sends a group status update request to the group storage network element.

[0289] S790, the group storage network element sends group status update response information to system agent #1.

[0290] It should be understood that when the information of the service agents in the first group changes, system agent #1 sends a group update request to the group repository network element to update the information of the first group.

[0291] For example, the information in the group update request information used to update the group file includes information such as the ID, type, status, load, or version of computing power service agent #2. The group update request information is used to update the list of service agents in the group file. For instance, the group repository updates computing power service agent #1 to computing power service agent #2, that is, it updates the ID, type, status, load, or version of computing power service agent #1 to the same information as computing power service agent #2. Alternatively, the group repository adds the ID, type, status, load, or version of computing power service agent #2 to the list of service agents; optionally, the group repository deletes the ID, type, status, load, or version of computing power service agent #1.

[0292] It should be noted that each round of information changes for the service agent requires executing steps S770 to S790 as described above, until the first task ends and the first group is disbanded.

[0293] Optionally, after the first group is disbanded, system agent #1 sends a group status update request to the group repository network element. This group status update request includes information for updating the group file, including group ID1 and the group status being "disbanded". Upon receiving the group status update request, the group repository network element updates the first group status of group ID1 in the group file to the disbanded state.

[0294] Figure 8 is a schematic flowchart of another communication method provided in an embodiment of this application. This communication method is applicable when a first terminal device (e.g., UE#1) is performing a first task, and if UE#1 requests another new task (e.g., a second task), it can obtain historical group information by subscribing to a group repository, and can choose to merge the processing or prioritize the same system agent for task decomposition processing. The communication method includes the following steps:

[0295] S810, System Agent #1 receives the request for the first task.

[0296] S820, System agent #1 discovers at least one service agent, performs first task decomposition and allocation, and at least one service agent performs subtask arrangement of the first task.

[0297] For example, system agent #1 receives a task request (e.g., prompt1) from UE #1 for a first task, and decomposes and assigns the first task, with each service agent (e.g., connection service agent and computing power service agent) performing subtask orchestration.

[0298] For example, based on the information in prompt1, system agent #1 identifies and analyzes the first task, which involves the computing power service domain and the session service domain. Then, system agent #1 discovers and invokes the computing power service agent and the connection service agent to orchestrate tasks for system agent #1. System agent #1 decomposes and assigns tasks to the computing power service agent and the connection service agent, which then orchestrate the subtasks assigned to system agent #1.

[0299] S830, System Agent #2 receives the request for the second task.

[0300] S840, System Agent #2 sends a group request message to the group storage network element.

[0301] The group request information is used to request the group information corresponding to UE#1. Specifically, the group request information is used to request the group information corresponding to the ID of UE#1. This group information is the group file for the group corresponding to UE#1.

[0302] Optionally, the group request information can be understood as the third request information in the communication method shown in Figure 5 above.

[0303] S850, the group storage network element sends group response information to system agent #2.

[0304] The group response information includes the group information corresponding to UE#1 (i.e., the group file of the group corresponding to the ID of UE#1). For example, the group corresponding to the ID of UE#1 is the first group of group ID1.

[0305] As an example, and not a limitation, after system agent #2 obtains the group information corresponding to UE #1, the following may occur:

[0306] Scenario 3: The first task of the first group corresponding to UE#1 is in progress.

[0307] In the case shown in Case 3, the method flow shown in Figure 8 may also include the following steps S801 to S804.

[0308] S801, System Agent #2 sends a task update request to System Agent #1.

[0309] The task update request information includes the prompt2 message sent by UE#1. System agent #1 attempts to merge the first and second tasks. The task update request information includes the ID of UE#1 and the information of the second task.

[0310] Optionally, the task update request information can be understood as the fourth request information in the communication method shown in Figure 5 above.

[0311] S802, System Agent #1 sends task update response information to System Agent #2.

[0312] The task update response information is used to provide feedback on the merge processing status, i.e. whether the merge processing of the first and second tasks is accepted.

[0313] S803, System Agent #1 analyzes the second task, discovers the service agent corresponding to the second task (e.g., the synesthesia service agent), and assigns the second task. Each service agent performs sub-task arrangement for the second task until the task is completed, and the group is disbanded.

[0314] For example, system agent #1, based on information about the second task, identifies and analyzes the second task, which involves the perception service domain, and then discovers and invokes a synesthetic service agent to orchestrate the second task. System agent #1 decomposes and assigns the second task to the synesthetic service agent, which then orchestrates the subtasks of the assigned second task.

[0315] S804, Group Status Update.

[0316] For example, system agent #1 interacts with the group repository network element to exchange group status update request and response information. The group status update request information is used to request an update to the task request (i.e., prompt) information, which can be found in the prompt in the aforementioned group file. As can be seen from the above, the group status update request information includes information for updating the group file, which includes information from prompt2, such as the ID of the second task and the intent description of the second task.

[0317] For example, the group repository network element updates the prompt in the group file to the information prompt2 based on the group status update request information. In response to the group status update request information, the group repository network element sends a group status update response information to system agent #1.

[0318] Scenario 4: The first task of the first group corresponding to the current UE#1 is completed, the first group is disbanded, or the system agent #1 does not merge the processing of the first and second tasks, etc.

[0319] In the case shown in Case 4, the system agent #2 can create a corresponding second group for the second task, and the method flow shown in Figure 8 can also include the following steps S811 and S812.

[0320] S811, System agent #2 discovers at least one service agent, performs second task decomposition and allocation, and at least one service agent performs subtask arrangement of the second task.

[0321] For example, system agent #2 analyzes historical chat logs and, based on the information in prompt2, identifies and analyzes a second task. This second task involves the perception service domain. System agent #2 then discovers and invokes a synesthetic service agent to orchestrate the second task. System agent #2 decomposes and assigns the second task to the synesthetic service agent, which then orchestrates the subtasks of the assigned second task.

[0322] S812, Group Status Update.

[0323] For example, system agent #2 interacts with the group repository network element to exchange group status update request and response information. The specific group status update process can be referenced from the interaction process between system agent #1 and the group repository network element during the creation of the corresponding first group for the first task, and will not be elaborated here.

[0324] Figure 9 is a schematic flowchart of another communication method provided in an embodiment of this application. This communication method is applicable to scenarios where a new subtask generated by a system agent needs a new service agent to join the group while a task (such as the first task) is in progress. The communication method includes the following steps:

[0325] S910, System Agent #1 receives the request for the first task.

[0326] S920, System agent #1 discovers at least one service agent, performs first task decomposition and allocation, and at least one service agent performs subtask arrangement of the first task.

[0327] Steps S910 and S920 can be referred to the description of steps S810 and S820 in Figure 8 above, and will not be repeated here.

[0328] S930, System Agent #1 determines that a new subtask #1 needs to be added, and confirms that the service agents in the current group cannot handle it.

[0329] For example, this subtask #1 involves the perception service domain, and system agent #1 determines that it is necessary to discover and invoke the synesthetic service agent to orchestrate the subtask #1. System agent #1 determines that the first group of the current group ID1 does not include the synesthetic service agent.

[0330] S940, System Agent #1 discovers the Sensory Service Agent.

[0331] For example, system agent #1 and agent repository network element exchange service agent discovery request and response information. For instance, system agent #1 sends a sensory service agent discovery request to the agent repository network element for subtask #1, whereby the sensory service agent is used to discover other sensory service agents. Based on the sensory service agent discovery request, the agent repository network element discovers the sensory service agent and obtains its information.

[0332] For example, the information of the synesthetic service agent includes at least one of the following: the identifier of the synesthetic service agent (e.g., the ID of the synesthetic service agent), or the open interface supported by the synesthetic service agent (e.g., a URL or API).

[0333] Optionally, the information of the synesthetic service agent may also include at least one of the following: the deployment location of the synesthetic service agent, the service domain of the synesthetic service agent, the protocols supported by the synesthetic service agent, the capabilities of the synesthetic service agent, the role of the synesthetic service agent, the models supported by the synesthetic service agent, or the service domain of the synesthetic service agent.

[0334] For example, in response to the synesthetic service agent discovery request information, the agent storage network element sends synesthetic service agent discovery response information to system agent #1, which includes information about the discovered synesthetic service agent.

[0335] S950, System Agent #1 reassigns tasks, and the service agents in the first group execute and discuss them.

[0336] For example, system agent #1 adds the synesthetic service agent that orchestrates subtask #1 to the first group of group ID1, which includes the synesthetic service agent. System agent #1 decomposes and assigns the first task and subtask #1, and each service agent orchestrates the subtask.

[0337] For example, system agent #1 decomposes and assigns the first task to computing power service agent and connection service agent, and assigns subtask #1 to synesthesia service agent. The computing power service agent and connection service agent respectively arrange the subtasks of the assigned first task, and the synesthesia service agent arranges subtask #1.

[0338] S960, Group Status Update.

[0339] For example, system agent #1 interacts with the group repository network element to exchange group status update request and response information. The group status update request information is used to request updates to information in the group file, which includes information such as the ID, type, status, load, or version of the synesthetic service agent. Based on the information used to request updates to the group file, the group repository updates the list of service agents in the group file. For example, the group repository adds information such as the ID, type, status, load, or version of the synesthetic service agent to the list of service agents.

[0340] For example, in response to a group status update request, the group repository network element sends a group status update response to system agent #1.

[0341] It should be noted that each time the system agent #1 determines that a new subtask needs to be added and the current service agent in the group cannot handle it, it needs to execute the above steps S940 to S960 until the first task is completed and the first group is disbanded.

[0342] Optionally, after the first group is disbanded, system agent #1 sends a group status update request to the group repository network element. This group status update request includes information for updating the group file, including group ID1 and the group status being "disbanded". Upon receiving the group status update request, the group repository network element updates the first group status of group ID1 in the group file to the disbanded state.

[0343] The methods for unified management of agents in the first group listed in Figures 6 to 9 above are merely examples and do not constitute any limitation on the scope of protection of this application. The information of the first group can also be updated in other possible situations. For example, in other cases where there is an update requirement, system agent #1 can also send an update request to the group storage network element to update the information of the first group. These will not be illustrated further here.

[0344] It should be understood that 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.

[0345] It should also be understood that, in the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0346] It should also be understood that in some of the above embodiments, the examples are mainly based on devices in existing network architectures, and it should be understood that the specific form of the devices is not limited in the embodiments of this application. For example, any device that can achieve the same function in the future is applicable to the embodiments of this application.

[0347] It is understood that, in the above-described method embodiments, the methods and operations implemented by devices (such as the first network element, the first system intelligent agent, and the second system intelligent agent) can also be implemented by components (such as chips or circuits) that can be used in the devices.

[0348] It is also understood that some optional features in the various embodiments of this application may not depend on other features in some scenarios, or may be combined with other features in some scenarios, without limitation.

[0349] The communication method provided in the embodiments of this application has been described in detail above with reference to Figures 5 to 9. The above communication method is mainly introduced from the perspective of the interaction between the first network element, the first system intelligent agent, and the second system intelligent agent. It can be understood that, in order to realize the above functions, the first network element, the first system intelligent agent, and the second system intelligent agent include hardware structures and / or software modules corresponding to the execution of each function.

[0350] Those skilled in the art will recognize that, based on the units and algorithm steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is implemented in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0351] The communication device provided in the embodiments of this application will be described in detail below with reference to Figures 10 to 12. It should be understood that the description of the device embodiments corresponds to the description of the method embodiments. Therefore, for content not described in detail, please refer to the method embodiments above. For the sake of brevity, some content will not be repeated.

[0352] This application embodiment can divide the first network element, the first system intelligent agent, and the second system intelligent agent into functional modules according to the above method example. 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. The following description uses the division of each functional module according to each function as an example.

[0353] Figure 10 is a schematic block diagram of a communication device 10 provided in an embodiment of this application. The device 10 includes a transceiver module 11 and a processing module 12. The transceiver module 11 can implement corresponding communication functions, and the processing module 12 is used for data processing. In other words, the transceiver module 11 is used to perform receiving and sending related operations, and the processing module 12 is used to perform other operations besides receiving and sending. The transceiver module 11 can also be referred to as a communication interface or a communication unit. The transceiver module 11 may include a receiving module and / or a sending module, whereby the receiving module performs receiving-related operations and the sending module performs sending-related operations.

[0354] Optionally, the device 10 may further include a storage module 13, which can be used to store instructions and / or data. The processing module 12 can read the instructions and / or data in the storage module so that the device can perform the operation of the device in the aforementioned method embodiments. The above modules may also be referred to as units, such as transceiver unit, processing unit, storage unit, etc.

[0355] In one design, the device 10 may correspond to the first network element in the above method embodiment, or a component of the first network element (such as a chip).

[0356] The device 10 can implement the steps or processes corresponding to the first network element in the above method embodiment. The transceiver module 11 can be used to perform the transceiver-related operations of the first network element in the above method embodiment, and the processing module 12 can be used to perform the processing-related operations of the first network element in the above method embodiment.

[0357] In one possible implementation, transceiver module 11 is configured to receive first request information from a first system agent, the first request information being used to request the allocation of an identifier for a first group, the first group including the first system agent and at least one first service agent, the first group being used to process a first task, the first task being used to implement a first intent of a first terminal device. Transceiver module 11 is also configured to send first response information to the first system agent, the first response information including the identifier of the first group.

[0358] When the device 10 is used to execute the method in FIG5, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S510, S520, S530, S501, S502 and S503; the processing module 12 can be used to execute the processing steps in the method.

[0359] When the device 10 is used to execute the method in FIG6, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S630, S640, S604 and S605; the processing module 12 can be used to execute the processing steps in the method.

[0360] When the device 10 is used to execute the method in FIG7, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S740, S750, S780 and S790; the processing module 12 can be used to execute the processing steps in the method.

[0361] When the device 10 is used to execute the method in FIG8, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S840, S850, S805 and S812; the processing module 12 can be used to execute the processing steps in the method.

[0362] When the device 10 is used to execute the method in FIG9, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as step S960; the processing module 12 can be used to execute the processing steps in the method.

[0363] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0364] In another design, the device 10 may correspond to the first system agent in the above method embodiment, or a component of the first system agent (such as a chip).

[0365] The device 10 can implement the steps or processes corresponding to those executed by the first system agent in the above method embodiment. The transceiver module 11 can be used to perform transceiver-related operations of the first system agent in the above method embodiment, and the processing module 12 can be used to perform processing-related operations of the first system agent in the above method embodiment.

[0366] In one possible implementation, transceiver module 11 is used to receive information about a first task from a first terminal device, the first task being used to implement a first intent of the first terminal device; transceiver module 11 is used to send first request information to a first network element, the first request information being used to request the allocation of an identifier for a first group, the first group including the first system agent and at least one first service agent, the first group being used to process the first task.

[0367] When the device 10 is used to execute the method in FIG5, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S510, S520 and S530; the processing module 12 can be used to execute the processing steps in the method.

[0368] When the device 10 is used to execute the method in FIG6, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S630, S640, S603, S604 and S605; the processing module 12 can be used to execute the processing steps in the method, such as steps S610, S60, S650, S660 and S670.

[0369] When the device 10 is used to execute the method in FIG7, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S710, S720, S740, S750, S701, S780 and S790; the processing module 12 can be used to execute the processing steps in the method, such as steps S730, S760 and S770.

[0370] When the device 10 is used to execute the method in FIG8, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S810, S801, S802 and S804; the processing module 12 can be used to execute the processing steps in the method, such as steps S820 and S803.

[0371] When the device 10 is used to execute the method in FIG9, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S910, S940 and S960; the processing module 12 can be used to execute the processing steps in the method, such as steps S920, S930 and S950.

[0372] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0373] In another design, the device 10 may correspond to the second system agent in the above method embodiments, or to a component of the second system agent (such as a chip).

[0374] The device 10 can implement the steps or processes corresponding to those executed by the second system agent in the above method embodiments. The transceiver module 11 can be used to perform transceiver-related operations of the second system agent in the above method embodiments, and the processing module 12 can be used to perform processing-related operations of the second system agent in the above method embodiments.

[0375] In one possible implementation, transceiver module 11 is configured to receive information about a second task from a first terminal device, the second task being used to implement a second intent of the first terminal device; transceiver module 11 is configured to send third request information to a first network element, the third request information being used to request information about a first group, the first group including a first system agent and at least one first service agent, the first group being used to process a first task, the first task being used to implement a first intent of the first terminal device; the information of the first group includes at least one of the following: the identifier of the first group, information about the first task, information about the first terminal device, information about the first system agent, information about the at least one first service agent, the state of the first group, and the memory of the first group.

[0376] When the device 10 is used to execute the method in FIG5, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S501, S502 and S503; the processing module 12 can be used to execute the processing steps in the method.

[0377] When the device 10 is used to execute the method in FIG8, the transceiver module 11 can be used to execute the steps of sending and receiving information in the method, such as steps S801, S802, S840, S850 and S812; the processing module 12 can be used to execute the processing steps in the method, such as step S811.

[0378] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0379] It should also be understood that the device 10 here is embodied in the form of a functional module. The term "module" here can refer to application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors, etc.) and memories for executing one or more software or firmware programs, integrated logic circuits, and / or other suitable components supporting the described functions. In an alternative example, those skilled in the art will understand that device 10 may specifically be a mobility management network element in the above embodiments, and may be used to execute the various processes and / or steps corresponding to the mobility management network element in the above method embodiments; or, device 10 may specifically be a terminal device in the above embodiments, and may be used to execute the various processes and / or steps corresponding to the terminal device in the above method embodiments. To avoid repetition, further details are omitted here.

[0380] The apparatus 10 of each of the above-described schemes has the function of implementing the corresponding steps performed by the devices (such as the first network element, the first system agent, and the second system agent) in the above-described methods. This function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described functions; for example, the transceiver module can be replaced by a transceiver (for example, the transmitting unit in the transceiver module can be replaced by a transmitter, and the receiving unit in the transceiver module can be replaced by a receiver), and other units, such as processing modules, can be replaced by processors, which respectively execute the transceiver operations and related processing operations in each method embodiment.

[0381] In addition, the transceiver module 11 can also be a transceiver circuit (for example, it may include a receiving circuit and a transmitting circuit), and the processing module can be a processing circuit.

[0382] Figure 11 is a schematic diagram of another communication device 20 provided in an embodiment of this application. The device 20 includes a processor 21, which is used to execute computer programs or instructions stored in a memory 22, or to read data / signaling stored in the memory 22, to perform the methods in the above-described method embodiments. Optionally, there may be one or more processors 21.

[0383] Optionally, as shown in FIG11, the device 20 further includes a memory 22 for storing computer programs or instructions and / or data. The memory 22 may be integrated with the processor 21 or may be disposed separately. Optionally, there may be one or more memories 22.

[0384] Optionally, as shown in FIG11, the device 20 further includes a transceiver 23, which is used for receiving and / or transmitting signals. For example, the processor 21 is used to control the transceiver 23 to receive and / or transmit signals. The transceiver 23 may include a receiver and / or a transmitter, the receiver being used for receiving signals and the transmitter for transmitting signals; if the communication device 20 is a chip, then the transceiver 23 is the chip's input / output interface, where the output corresponds to transmitting and the input corresponds to receiving.

[0385] As one approach, the device 20 is used to implement the operations performed by the first network element, the first system agent, or the second system agent in the various method embodiments described above.

[0386] It should be understood that the processor mentioned in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0387] It should also be understood that the memory mentioned in the embodiments of this application can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0388] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0389] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0390] Figure 12 is a schematic diagram of a chip system 30 provided in an embodiment of this application. The chip system 30 (or may also be called a processing system) includes logic circuitry 31 and an input / output interface 32.

[0391] The logic circuit 31 can be a processing circuit in the chip system 30. The logic circuit 31 can be coupled to a memory unit, calling instructions from the memory unit, enabling the chip system 30 to implement the methods and functions of the embodiments of this application. The input / output interface 32 can be an input / output circuit in the chip system 30, outputting processed information from the chip system 30, or inputting data or signaling information to be processed into the chip system 30 for processing.

[0392] As one approach, the chip system 30 is used to implement the operations performed by the first network element, the first system agent, or the second system agent in the various method embodiments described above.

[0393] For example, logic circuit 31 is used to implement processing-related operations performed by the first network element, the first system agent, or the second system agent in the above method embodiments; input / output interface 32 is used to implement sending and / or receiving-related operations performed by the first network element, the first system agent, or the second system agent in the above method embodiments.

[0394] This application also provides a computer-readable storage medium storing computer instructions for implementing the methods executed by the device in the above-described method embodiments.

[0395] For example, when the computer program is executed by a computer, it enables the computer to implement the methods executed by the first network element, the first system agent, or the second system agent in the various embodiments of the above methods.

[0396] This application also provides a computer program product comprising instructions which, when executed by a computer, implement the methods performed by a first network element, a first system agent, or a second system agent in the above-described method embodiments.

[0397] This application also provides a communication system, including the aforementioned first network element, first system agent, or second system agent.

[0398] The explanations and beneficial effects of the relevant contents in any of the devices provided above can be found in the corresponding method embodiments provided above, and will not be repeated here.

[0399] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of apparatus or units may be electrical, mechanical, or other forms.

[0400] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The 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. For example, the computer can be a personal computer, a server, or a network device, etc. 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 website, computer, server, or data center 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 that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs). For example, the aforementioned available media include, but are not limited to, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, and other media capable of storing program code.

[0401] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method characterized by comprising: Applied to the first network element, including: The system receives a first request from a first system agent. The first request is used to request the allocation of an identifier for a first group. The first group includes the first system agent and at least one first service agent. The first group is used to process a first task, which is used to implement a first intent of a first terminal device. Send a first response message to the first system agent, the first response message including the identifier of the first group.

2. The method of claim 1, wherein, The method further includes: Receive a second request message from the first system agent, the second request message being used to request updates to the information of the first group, the information of the first group including at least one of the following: The identifier of the first group, the information of the first task, the information of the first terminal device, the information of the first system agent, the information of the at least one first service agent, the status information of the first group, or the memory information corresponding to the first group.

3. The method of claim 2, wherein, In the case of merging the first and second tasks, the updated information for the first group also includes: The information of the second task and the information of at least one second service agent, the second service agent being used to execute sub-tasks in the second task, the second task being used to realize the second intent of the first terminal device.

4. The method according to claim 2 or 3, characterized in that, In the at least one first service agent, one of the first service agents does not support executing the first subtask in the first task, while the third service agent supports executing the first subtask; or, If the third service agent has better performance or a newer version than the first service agent, the updated information of the first group also includes: The information of the third service agent. The information of the third service agent includes at least one of the following: the identifier, version information, or type information of the third service agent.

5. The method according to any one of claims 2 to 4, characterized in that, After the identifier of the first group is successfully assigned, the status of the first group is "pending formation". When the first group is successfully formed, the status of the first group is "successfully formed"; When the first system agent and the at least one first service agent in the first group are communicating, the state of the first group is "under discussion"; When the first group is disbanded, the state of the first group is disbanded.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Receive a third request message, which is used to request information about the first group.

7. A communication method characterized by comprising: Applied to the first system intelligent agent, including: Receive information from a first task from a first terminal device, wherein the first task is used to implement a first intent of the first terminal device; A first request message is sent to a first network element. The first request message is used to request the allocation of an identifier for a first group. The first group includes the first system agent and at least one first service agent. The first group is used to process the first task.

8. The method of claim 7, wherein, The method further includes: Send a second request message to the first network element. The second request message is used to request updates to the information of the first group. The information of the first group includes at least one of the following: The identifier of the first group, the information of the first task, the information of the first terminal device, the information of the first system agent, the information of the at least one first service agent, the status information of the first group, and the memory information corresponding to the first group.

9. The method of claim 8, wherein, In the case of merging the first and second tasks, the updated information for the first group also includes: The information of the second task and the information of at least one second service agent, the second service agent being used to execute sub-tasks in the second task, the second task being used to realize the second intent of the first terminal device.

10. The method of claim 9, wherein, Before sending the second request information to the first network element, the method further includes: Receive a fourth request from the second system agent, the fourth request being used to request the merging of the first task and the second task; or... Generate the second task, which is at least one subtask of the first task.

11. The method according to any one of claims 8 to 10, characterized in that, The method further includes: A third request message is sent to the first network element. The third request message is used to request that the information of one of the first sub-service intelligent agents in the at least one first service intelligent agent be updated to the information of the third service intelligent agent. The information of the third service intelligent agent includes at least one of the following: the identifier, version information, or type information of the third service intelligent agent. Wherein, the first service agent does not support executing the first subtask in the first task, and the third service agent supports executing the first subtask, or... The third service agent is either more powerful or has a newer version than the first service agent.

12. A communication method characterized by comprising: Applied to the second system intelligent agent, including: Receive information from a second task from a first terminal device, the second task being used to implement a second intent of the first terminal device; Send a third request message to the first network element. The third request message is used to request information of the first group. The first group includes the first system intelligent agent and at least one first service intelligent agent. The first group is used to process the first task. The first task is used to realize the first intent of the first terminal device. The information of the first group includes at least one of the following: The identifier of the first group, the information of the first task, the information of the first terminal device, the information of the first system agent, the information of the at least one first service agent, the state of the first group, and the memory of the first group.

13. The method according to claim 12, characterized in that, A fourth request message is sent to the first system agent, the fourth request message being used to request the merging of the first task and the second task.

14. A communication method, characterized in that, The first system agent receives information about a first task from a first terminal device, the first task being used to implement a first intent of the first terminal device; The first system agent sends a first request message to the first network element. The first request message is used to request the allocation of an identifier for a first group. The first group includes the first system agent and at least one first service agent. The first group is used to process the first task. The first network element receives the first request information from the first system agent and sends the first response information to the first system agent. The first response information includes the identifier of the first group.

15. A communications device, characterized by It includes modules or units for performing the method as described in any one of claims 1 to 6, or modules or units for performing the method as described in any one of claims 7 to 11, or modules or units for performing the method as described in claim 12 or 13.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program or instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 13.

17. A computer program product, characterised in that, It includes a computer program or instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 13.

18. A communication system, characterized by It includes the first network element and the first system intelligent agent, wherein: The first network element is used to perform the method as described in any one of claims 1 to 6; The first system agent is used to perform the method as described in any one of claims 7 to 11.

19. The system of claim 18, wherein, The system further includes a second system agent, which performs the method as described in claim 12 or 13.

Images