Communication method, apparatus, storage medium, and program product

Abstract

This application provides a communication method, apparatus, storage medium, and program product. The method includes: an ACP receiving first information, the first information including first parameters; the ACP parsing the first parameters to obtain a first task; the ACP obtaining a target network element based on the first task; and then the ACP sending second information, the second information including second parameters, which are generated based on the first parameters, or the second parameters including the first parameters. The second information is used to instruct the target network element to perform the first task based on the second parameters. In this example, the ACP can understand the first parameters, obtain the target task, determine the target network element to perform the task, and generate input information for the target network element, thus achieving the purpose of semantically routing messages between agents.

Description

Technical Field

[0001] This application relates to the field of communications, and more particularly to a communication method, apparatus, storage medium, and program product. Background Technology

[0002] Future communication systems need to support new business scenarios such as the integration of artificial intelligence (AI) with communication and the fusion of sensing and communication, including smart cities, digital healthcare, and smart factories. Different business scenarios have different performance requirements; therefore, communication systems need strong customization capabilities to integrate end-to-end network functions, application functions, and communication, computing, and data resources to build end-to-end application networks for service targets (tenants / users / applications, etc.). An application network is a logical network composed of a series of network functions, application functions, and communication, computing, and data resources. The future number of application networks will be large, and each application network involves the flexible assembly of multiple functions and multi-dimensional resources, with complex parameter configurations. This presents significant challenges to the design and management of application networks. Traditional predefined processes based on human expert experience are insufficient to address this problem.

[0003] AI-based agents, with their powerful intent understanding, reasoning abilities, and capacity for interaction and self-evolution, are considered an effective way to solve the aforementioned problems. Since it's typically difficult for a single agent to complete all tasks, future core networks will likely contain multiple agents and shared common components. How to intelligently determine the next agent to handle tasks when multiple agents collaborate is a problem that needs to be solved. Summary of the Invention

[0004] This application discloses a communication method, device, storage medium, and program product that can intelligently determine the next intelligent agent.

[0005] Firstly, embodiments of this application provide a communication method. This method can be applied to an agent communication proxy (ACP). In this method, the ACP receives first information, which includes first parameters. The ACP parses the first parameters to obtain a first task. The ACP obtains a target network element based on the first task. Then, the ACP sends second information, which includes second parameters generated based on the first parameters, or the second parameters include the first parameters. The second information is used to instruct the target network element to perform the first task based on the second parameters.

[0006] In this embodiment, the ACP parses a first parameter from a first network element to obtain a first task. Then, the ACP obtains a target network element based on the first task. Next, the ACP sends second information to instruct the target network element to execute the first task based on the second parameter. In this example, the ACP can understand the first parameter, obtain the target task, determine the target network element to execute the task, and generate the input information for that target network element, thus achieving the goal of semantically routing messages between agents.

[0007] Understandably, the first parameter indicates the target task (i.e., the first task).

[0008] The second parameter can be understood as the input parameter used when the target network element performs the first task.

[0009] In one possible implementation, ACP parses the first parameter, which could be semantic parsing, image parsing, or symbol parsing, etc.

[0010] In one possible implementation, ACP determines the target network element from multiple network elements based on the first task and the capability and / or location information of multiple network elements.

[0011] In one possible implementation, the first information further includes a third parameter, which includes at least one of the following:

[0012] The identifier of the first network element, the task execution information of the first network element, the input parameters corresponding to the first task, and the identifier of the service. The service is related to the first task, and the first network element is the network element that sends the first information.

[0013] The identifier of the first network element identifies which network element the first information originates from. The task execution information of the first network element can be understood as the input information of the first network element when executing its corresponding task. This input information includes, for example, task information and related parameters. The input parameters corresponding to the first task can be understood as the input parameters of the network element executing the first task. Optionally, the input parameters corresponding to the first task can be the output information of the first network element when executing its corresponding task. The above service can be understood as a user-requested service. This service is related to the first task. Or, in other words, this service includes the first task. The service identifier is used to identify this service.

[0014] In one possible implementation, the third parameter is the input parameter corresponding to the first task. The ACP parses the third parameter to obtain a fourth parameter, which indicates the input parameter corresponding to the first task. Then, based on the first task, the fourth parameter, and the capability information and / or location information of multiple network elements, the ACP determines the target network element from multiple network elements.

[0015] In other words, in this example, ACP determines the target network element from multiple network elements by comprehensively considering the first task and the input parameters corresponding to the network element executing the first task.

[0016] In one possible implementation, the third parameter includes the task execution information of the first network element, and the second parameter is generated based on the first parameter and the task execution information of the first network element.

[0017] In another possible implementation, the ACP sends a third message including a first task, which instructs a second network element to determine a network element for performing the first task. The ACP also receives a fourth message indicating a target network element.

[0018] In this example, other network elements determine the target network element and then send the determined target network element to the ACP.

[0019] In one possible implementation, the ACP receives a fifth message, which includes the result of the target network element performing the first task.

[0020] In this example, after the target network element completes the first task, it sends the execution result to the ACP so that the ACP can return it to the first network element, or the ACP can send the execution result to the network element that is executing the next task.

[0021] In one possible implementation, the ACP sends a sixth message, which includes the identifier of the service, the first task, and the result of the target network element performing the first task, wherein the service is related to the first task.

[0022] In this example, ACP sends the execution result to the first network element.

[0023] Secondly, embodiments of this application provide a communication method. This method can be applied to a first network element, and includes: the first network element sending first information, the first information including first parameters, the first information being used to indicate a network element to perform a first task, the first task being associated with the first parameters.

[0024] In one possible implementation, the first network element receives sixth information, which includes the identifier of the service, the first task, and the result of the target network element performing the first task, wherein the service is related to the first task.

[0025] In one possible implementation, the first information also includes a third parameter, which includes at least one of the following:

[0026] The identifier of the first network element, the task execution information of the first network element, the input parameters corresponding to the first task, and the identifier of the service.

[0027] Thirdly, embodiments of this application provide a communication method. This method can be applied to a target network element. The method includes: the target network element receiving second information, the second information including a second parameter generated based on a first parameter, or the second parameter including the first parameter; the second information being used to instruct the target network element to perform a first task based on the second parameter, the first task being related to the first parameter. The target network element also sends fifth information, the fifth information including the result of the target network element performing the first task.

[0028] In one possible implementation, the second parameter is generated based on the first parameter and the task execution information of the first network element, which is the network element that sends the first information, and the first information includes the first parameter and the task execution information of the first network element.

[0029] Fourthly, this application provides a communication device that has the functions of the first aspect described above. For example, the communication device includes modules, units, or means that perform the operations involved in the first aspect. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0030] In one implementation, the communication device includes: a communication module for receiving first information, the first information including first parameters;

[0031] The processing module is used to parse the first parameter to obtain the first task;

[0032] This processing module is also used to obtain the target network element based on the first task;

[0033] The communication module is also used to send second information, which includes a second parameter generated based on the first parameter, or the second parameter includes the first parameter. The second information is used to instruct the target network element to perform the first task based on the second parameter.

[0034] In one possible implementation, the processing module is also used for:

[0035] Based on the first task and the capability and / or location information of multiple network elements, the target network element is determined from these multiple network elements.

[0036] In one possible implementation, the first information further includes a third parameter, which includes at least one of the following:

[0037] The identifier of the first network element, the task execution information of the first network element, the input parameters corresponding to the first task, the identifier of the service, the service being related to the first task, and the first network element being the network element that sends the first information.

[0038] In one possible implementation, the third parameter is the input parameter corresponding to the first task, and the processing module is further configured to:

[0039] The third parameter is parsed to obtain the fourth parameter, which indicates the input parameter corresponding to the first task;

[0040] Based on the first task, the fourth parameter, and the capability information and / or location information of multiple network elements, the target network element is determined from the multiple network elements.

[0041] In one possible implementation, the third parameter includes the task execution information of the first network element, and the second parameter is generated based on the first parameter and the task execution information of the first network element.

[0042] In one possible implementation, the communication module is also used for:

[0043] Send a third message, the third message including the first task, the third message being used to instruct the second network element to determine the network element for performing the first task;

[0044] Receive the fourth information, which indicates the target network element.

[0045] In one possible implementation, the communication module is also used for:

[0046] Receive the fifth information, which includes the result of the target network element performing the first task.

[0047] In one possible implementation, the communication module is also used for:

[0048] Send a sixth message, which includes the identifier of the service, the first task, and the result of the target network element performing the first task, and the service is related to the first task.

[0049] Fifthly, this application also provides a communication device that has the functions of the second aspect above. For example, the communication device includes modules, units, or means that perform the operations involved in the second aspect above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0050] In one implementation, the communication device includes: a communication module for transmitting first information, the first information including a first parameter, the first information being used to indicate the determination of a network element for performing a first task, the first task being associated with the first parameter.

[0051] In one possible implementation, the communication module is also used for:

[0052] The sixth information is received, which includes the identifier of the service, the first task, and the result of the target network element performing the first task, and the service is related to the first task.

[0053] In one possible implementation, the first information further includes a third parameter, which includes at least one of the following:

[0054] The identifier of the first network element, the task execution information of the first network element, the input parameters corresponding to the first task, the identifier of the service, the service being related to the first task, and the first network element being the network element that sends the first information.

[0055] Sixthly, this application provides a communication device that has the functions of the third aspect above. For example, the communication device includes modules, units, or means that perform the operations involved in the third aspect above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0056] In one implementation, the communication device includes: a communication module for receiving second information, the second information including a second parameter, the second parameter being generated based on a first parameter, or the second parameter including the first parameter, the second information being used to instruct a target network element to perform a first task based on the second parameter, the first task being related to the first parameter;

[0057] The communication module is also used to send a fifth message, which includes the result of the target network element performing the first task.

[0058] In one possible implementation, the second parameter is generated based on the first parameter and the task execution information of the first network element, where the first network element is the network element that sends the first information, and the first information includes the first parameter and the task execution information of the first network element.

[0059] In a seventh aspect, this application provides a communication device including a processor, the processor being configured to execute a computer program or computer-executable instructions stored in a memory, and / or to cause the device to perform a method as provided in any of the possible embodiments of the first to third aspects via logic circuitry.

[0060] One possible implementation also includes memory. Alternatively, the memory and processor can be integrated together.

[0061] One possible implementation also includes an interface circuit.

[0062] In one possible implementation, the device is a chip or chip system.

[0063] Eighthly, this application provides a communication system including the communication device as described in the fourth aspect, the communication device as described in the fifth aspect, and the communication device as described in the sixth aspect.

[0064] Ninthly, this application provides a computer-readable storage medium storing a computer program that is executed by a processor to implement the method provided in any possible implementation of the first aspect, or the method provided in any possible implementation of the second aspect, or the method provided in any possible implementation of the third aspect.

[0065] In a tenth aspect, this application provides a computer program product that, when run on a computer, causes the computer to perform a method as provided in any possible implementation of the first aspect, or a method as provided in any possible implementation of the second aspect, or a method as provided in any possible implementation of the third aspect.

[0066] It is understood that the apparatus described in the fourth aspect, the apparatus described in the fifth aspect, the apparatus described in the sixth aspect, the apparatus described in the seventh aspect, the system described in the eighth aspect, the computer-readable storage medium described in the ninth aspect, or the computer program product described in the tenth aspect are all used to perform the methods provided in any of the first to third aspects. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here. Attached Figure Description

[0067] The accompanying drawings used in the embodiments of this application are described below.

[0068] Figure 1 This is a schematic diagram of a communication system provided in an embodiment of this application;

[0069] Figure 2 This is a schematic diagram of a core network architecture provided in an embodiment of this application;

[0070] Figure 3 This is a flowchart illustrating a communication method provided in an embodiment of this application;

[0071] Figures 4-6 This is a schematic diagram of another communication method provided in an embodiment of this application;

[0072] Figures 7-8 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0073] Figure 9 This is a schematic diagram of another communication device provided in an embodiment of this application. Detailed Implementation

[0074] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0075] Figure 1 A possible, non-limiting system schematic diagram is shown. For example... Figure 1 As shown, the communication system 1000 includes a radio access network (RAN) 100 and a core network (CN) 200. Optionally, it also includes an Internet 300. The RAN 100 includes at least one RAN node (e.g., Figure 1 110a and 110b, collectively referred to as 110) and at least one terminal (such as Figure 1 RAN100, denoted as RAN100, comprises RAN nodes 120a-120j, collectively referred to as RAN120. RAN100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 1 (Not shown in the image). Terminal 120 is connected to RAN node 110 wirelessly. RAN node 110 is connected to core network 200 wirelessly or via wired connection. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0076] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or evolutionary systems beyond 5G (e.g., 6th generation, 6G mobile communication systems). RAN 100 can also be an open radio access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless-fidelity (Wi-Fi) system based on the IEEE 802.11 standard. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0077] RAN node 110, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and assists terminals in achieving wireless access. Multiple RAN nodes 110 in the communication system 1000 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative, for example... Figure 1 Network element 120i can be a helicopter or a drone, and it can be configured as a mobile base station. For terminals 120j that access RAN 100 through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes referred to as communication devices, for example... Figure 1 Network elements 110a and 110b can be understood as communication devices with base station functions, while network elements 120a-120j can be understood as communication devices with terminal functions.

[0078] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a next-generation base station in a 6G mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc. A RAN node can also be a macro base station (such as...) Figure 1 110a), micro base stations or indoor stations (such as Figure 1 In CRAN scenarios, RAN nodes can be 110b), relay nodes or donor nodes, or wireless controllers. Optionally, RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, in vehicle-to-everything (V2X) technology, the access network equipment can be a roadside unit (RSU).

[0079] In another possible scenario, multiple RAN nodes assist the terminal in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0080] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. 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.

[0081] A terminal can also be called a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality (VR) devices, augmented reality (AR) devices, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, smart home devices, light UEs, reduced-capability UEs (REDCAP UEs), point-of-sale (POS) machines, customer-premises equipment (CPE), etc. The terminal can also be a vehicle device, such as a complete vehicle device, an in-vehicle module, an in-vehicle chip, an on-board unit (OBU), or a telematics box (T-BOX). The embodiments of this application do not limit the device form of the terminal.

[0082] 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.

[0083] For the network elements in the ORAN system and their corresponding protocol layer functions, please refer to Table 1:

[0084] Table 1

[0085] ORAN network elements 3GPP protocol layer functions O-CU-CP RRC+PDCP-C O-CU-UP SDAP+PDCP-U O-DU RLC+MAC+PHY-high O-RU PHY-low

[0086] Base stations and terminals can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can be deployed on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of the base stations and terminals.

[0087] The roles of base stations and terminals can be relative, for example, Figure 1 The helicopter or drone 120i can be configured as a mobile base station. For terminals 120j accessing the wireless access network 100 via 120i, terminal 120i is a base station; however, for base station 110a, 120i is a terminal, meaning that 110a and 120i communicate via a wireless air interface protocol. Of course, 110a and 120i can also communicate via a base station-to-base station interface protocol; in this case, 120i is also a base station relative to 110a. Therefore, both base stations and terminals can be collectively referred to as communication devices. Figure 1 The 110a and 110b in the text can be referred to as communication devices with base station functions. Figure 1 The 120a-120j in the text can be referred to as communication devices with terminal functions.

[0088] In this embodiment, the base station is also referred to as an access network device. The apparatus used to implement the functions of the access network device can be the access network device itself; it can also be any apparatus capable of supporting the access network device in implementing these functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the access network device or used in conjunction with the access network device. In this embodiment, the example of an access network device being used to implement the functions of the access network device is used only and does not constitute a limitation on the solutions of this embodiment.

[0089] It is understood that this application can be applied between access network equipment and terminals.

[0090] It should be understood that Figure 1 The number and type of devices in the communication system shown are for illustrative purposes only. This application is not limited to this. In actual applications, the communication system may include more terminals, more access network devices, and other network elements, such as core network devices and / or network elements used to implement artificial intelligence functions.

[0091] It is understandable that all or part of the functions implemented by one or more of the terminals, access network equipment, core network equipment, or network elements used to implement artificial intelligence functions can be virtualized, that is, implemented through one or more of dedicated or general-purpose processors and corresponding software modules. Among these, the transmit and receive functions of the terminals and access network equipment, which involve air interface transmission, can be implemented in hardware. Core network equipment, such as operation administration and maintenance (OAM) network elements, can also be virtualized. Optionally, one or more of the functions of the virtualized terminals, access network equipment, core network equipment, or network elements used to implement artificial intelligence functions can be implemented by cloud devices, such as cloud devices in over-the-top (OTT) systems.

[0092] Reference Figure 2 The diagram shown is a schematic representation of a core network architecture provided in an embodiment of this application. Figure 2 As shown, the core network contains multiple agents and multiple common components, and the functions of each agent and component are described below:

[0093] Planning agent: Understands the complex task requirements of the input and breaks down the complex task into a series of simple and easy-to-execute subtasks.

[0094] Assemble agent: Responsible for intelligently selecting the execution function based on the input task or subtask description.

[0095] Connection agent: Responsible for intelligent connection management, including configuring terminal and base station functions, and establishing and updating end-to-end network topology and connections according to business needs.

[0096] Execution agent: Responsible for computing resource management, including the deployment, updating, and deletion of functional instances, and the dynamic scheduling of computing resources.

[0097] Network generative pre-trained transformer (NetGPT): Infers the expected result based on input prompts, etc.

[0098] Public memory: Used to collect and store network data, knowledge, etc., for intelligent agents to query.

[0099] Toolbox: Stores a large amount of network and application function information, which can be flexibly arranged and assembled by intelligent agents to generate personalized application networks, etc.

[0100] Sandbox: Used to verify the reasoning results of agents, simulating the operation and performance of the application network before deployment.

[0101] Agent communication proxy (ACP): It understands the semantic meaning of the task objective in agent messages, intelligently selects the agent to handle the task, and generates the input messages required by that agent. Understandably, the representation of the task objective is not limited to natural language; it can also be in other ways, such as symbols or images.

[0102] It should be noted that, Figure 2 The intelligent agents (and their names) and common components (and their names) shown are merely examples. The future core network is not limited to the aforementioned intelligent agents (and their names) and common components (and their names), and may also include other functions, etc.

[0103] The architecture of the embodiments of this application has been described above. The methods of the embodiments of this application will be described in detail below.

[0104] Reference Figure 3 The diagram shown is a flowchart illustrating a communication method provided in an embodiment of this application. Optionally, this method can be applied to the aforementioned communication system, for example... Figure 2 The example illustrates a communication system. This example uses ACP as a case study, but other network elements or names can also be used; this solution does not impose any restrictions. Figure 3The communication method shown may include steps 301-304. Steps 301-304 are as follows:

[0105] 301. The first network element sends first information to the ACP, the first information including first parameters. Accordingly, the ACP receives the first information.

[0106] For example, the first network element can be any intelligent agent or common component. For instance, the first network element can be a planning intelligent agent, a connecting intelligent agent, or an executing intelligent agent.

[0107] The first parameter can be understood as a task parameter, which is used to indicate the target task (i.e., the first task below).

[0108] In one possible implementation, the aforementioned first information further includes a third parameter, which includes at least one of the following:

[0109] The identifier of the first network element, the task execution information of the first network element, the input parameters corresponding to the first task, and the identifier of the service.

[0110] The third parameter will be described below.

[0111] The identifier (ID) of the first network element is used to identify which network element the first information originates from, so as to facilitate message response and message tracing after the task is completed. For example, the identifier of the first network element could be PA001, where PA stands for planningagent.

[0112] The task execution information of the first network element can be understood as the input information of the first network element when executing its corresponding task. This input information includes, for example, task information and related parameters.

[0113] The input parameters corresponding to the first task can be understood as the input parameters of the network element executing the first task. Optionally, the input parameters corresponding to the first task can be the output information of the first network element when executing its corresponding task.

[0114] The aforementioned service can be understood as a service requested by a user (such as a terminal or application). This service is related to the first task. In other words, the service includes the first task. A service identifier is used to identify the service. For example, the service identifier could be, for instance, 201.

[0115] 302. ACP parses the first parameter to obtain the first task.

[0116] For example, this parsing could be semantic parsing. For instance, based on existing natural language processing (NLP) methods, a neural network could be trained using machine learning, inputting a task description carried in natural language into the neural network, and outputting a task description that the machine / network element can understand.

[0117] For example, this parsing can also be image parsing. For instance, it can be based on image description, where the first parameter is carried by an image, and then parsed using an image recognition model.

[0118] Of course, this parsing can also be symbolic parsing, that is, understanding the task to be represented by recognizing some predefined key symbols. This scheme does not impose any restrictions on this.

[0119] 303. ACP obtains the target network element based on this first task.

[0120] In one possible implementation, ACP determines the target network element from multiple network elements based on the first task and the capability and / or location information of multiple network elements.

[0121] For example, ACP obtains capability and / or location information of multiple network elements (agents and / or common components) from other network elements, such as the first network element or the agent repository function (ARF) network element. Then, based on the first task and the obtained information, ACP determines the appropriate network element.

[0122] In another possible implementation, the aforementioned third parameter is the input parameter corresponding to the first task. The ACP further parses the third parameter to obtain a fourth parameter, which indicates the input parameter corresponding to the first task. Then, based on the first task, the fourth parameter, and the capability and / or location information of multiple network elements, the ACP determines the target network element from among the multiple network elements.

[0123] In other words, in this example, ACP determines the target network element from multiple network elements by comprehensively considering the first task and the input parameters corresponding to the network element executing the first task.

[0124] Understandably, this example uses the third parameter as the input parameter corresponding to the first task. Of course, ACP can also determine the target network element based on other third parameters (such as the task execution information of the first network element, the service identifier, etc.), and this solution does not restrict this.

[0125] In the example above, ACP determines the target network element itself.

[0126] In another possible implementation, the ACP sends a third message to the second network element, which includes a first task and instructs the second network element to determine the network element to perform the first task. Then, the ACP receives a fourth message from the second network element, which indicates the target network element.

[0127] In this example, other network elements determine the target network element and then send the determined target network element to the ACP.

[0128] Optionally, the second network element can determine the target network element based on the first task and the capability information and / or location information of multiple network elements. Alternatively, the aforementioned third information may also include a third parameter, which is an input parameter corresponding to the first task. Furthermore, the second network element can determine the target network element based on the first task, the third parameter, and the capability information and / or location information of multiple network elements. This solution does not impose any limitations on this.

[0129] 304. The ACP sends second information to the target network element, the second information including a second parameter, which is generated based on the first parameter, or the second parameter including the first parameter, the second information being used to instruct the target network element to perform the aforementioned first task based on the second parameter. Accordingly, the target network element receives the second information.

[0130] The second parameter can be understood as the input parameter used when the target network element performs the first task.

[0131] In one possible implementation, the second parameter is generated based on the first parameter. That is, ACP obtains the second parameter by processing the first parameter. This processing could be, for example, parsing. Optionally, the first information also includes a third parameter, which includes the task execution information of the first network element. ACP generates the second parameter based on the first parameter and the task execution information of the first network element.

[0132] In another possible implementation, the second parameter includes the first parameter. Optionally, the first information also includes a third parameter, which includes task execution information of the first network element. The second parameter includes both the first parameter and the third parameter.

[0133] ACP sends a second parameter to the target network element, which then performs the first task described above based on the second parameter.

[0134] In one possible implementation, ACP processes the first parameter to obtain the second parameter. Then, ACP generates second information. ACP sends the second information to the target network element. Alternatively, ACP generates a second parameter that includes the aforementioned first parameter. Then, ACP generates second information. ACP sends the second information to the target network element.

[0135] Optionally, ACP generates different message formats based on the type of the target network element, so that the target network element can understand the message and further process the message according to the second parameter carried in the message.

[0136] In one possible implementation, the ACP receives fifth information from the target network element, which includes the result of the target network element performing the first task.

[0137] In this example, after the target network element completes the first task, it sends the execution result to the ACP so that the ACP can return it to the first network element, or the ACP can send the execution result to the network element that is executing the next task.

[0138] In one possible implementation, the ACP sends a sixth message to the first network element, which includes the service identifier, the first task, and the result of the target network element performing the first task.

[0139] In this example, ACP sends the execution result to the first network element.

[0140] In this embodiment, the ACP parses a first parameter from a first network element to obtain a first task. Then, the ACP obtains a target network element based on the first task. Next, the ACP sends second information to instruct the target network element to execute the first task based on the second parameter. In this example, the ACP can understand the first parameter, obtain the target task, determine the target network element to execute the task, and generate the input information for that target network element, thus achieving the goal of semantically routing messages between agents.

[0141] The communication method provided in this application will be described below with reference to Examples 1-3.

[0142] Example 1

[0143] Combination Figure 4 As shown, this example illustrates a scenario where the Planning agent receives a user's business request, decomposes the business logic, and then other agents are needed to perform subsequent function matching. For example... Figure 4 As shown, the communication method includes steps 401-406, as detailed below:

[0144] 401. The planning agent receives user messages.

[0145] For example, the planning agent receives a message from a terminal or app, which contains the following information:

[0146] (1) Task ID: Used to index the task. (2) Task description: Describes the task that the agent needs to perform. (3) Input parameters: Inputs key parameter information required for the agent to perform the task, such as location and time.

[0147] For example, the user carries a service identifier of "none", that is, the task ID value is empty; the service description information is "create a smart city traffic monitoring application network instance, which can automatically count and output the number of vehicles and update the results once a day", and the input parameter is "monitoring location: entrance of Jing'an Park".

[0148] 402. The planning agent understands the task description in the user message above, decomposes the task into a series of sub-tasks, and infers the next steps to complete the task.

[0149] 403. The Planning agent sends the first message to the ACP.

[0150] For example, each agent is locally configured with the ACP's Internet Protocol (IP) address, so each agent can send messages based on that address.

[0151] Optionally, the first information output by the agent includes the following third parameter and first parameter:

[0152] The third parameter includes: (1) Agent ID: used to record which agent the message comes from, such as PA001, where PA represents the planning agent. (2) Service ID: service index, such as none (meaning no) or 201. (3) Task execution information of the planning agent: such as the input information of the planning agent, such as the service request and input parameters (create a smart city traffic monitoring application network instance, which can automatically count and output the number of vehicles, update the results once a day, and monitor the location at the entrance of Jing'an Park). (4) Input parameters corresponding to the target task: such as the output information of the planning agent, which can be used as the input of the next agent, such as the decomposed sub-task list (sub-task 1: collect the perception data of the monitoring location; sub-task 2: identify the vehicles in the data; sub-task 3: count the number of vehicles; sub-task 4: output the results).

[0153] The first parameter (i.e., the target task): is used by ACP to determine which agent to select for inference, such as selecting the execution function for each subtask.

[0154] Optionally, the aforementioned first information may also include other information, such as subtask indexes. This solution does not impose any restrictions on this.

[0155] Optionally, it may also include step 404, whereby ACP obtains capability information and / or location information of each agent and component in the current network from ARF.

[0156] 405. ACP understands the description of the first parameter and, in conjunction with the acquired capability information and / or location information of each agent and component, infers the appropriate agent to handle the target task.

[0157] For example, ACP understands the first parameter to obtain the target task. Then, ACP selects an assembly agent based on the target task and the capability and / or location information of each agent and component. Of course, ACP can also use other methods, as described in [reference needed]. Figure 3 The description of step 303 in the illustrated embodiment will not be repeated here.

[0158] 406. ACP sends the second message to the Assemble agent.

[0159] For example, ACP generates appropriate second information and sends it to the selected Assemble agent. "Appropriate" can be understood as the message format, etc., conforming to the requirements or needs of the Assemble agent.

[0160] Optionally, the second information includes the following parameters: (1) Business identifier: none. (2) Target task (which can also be understood as the first parameter above): Select the execution function for each subtask. (3) Input parameters corresponding to the target task: i.e., the description of the subtask list decomposed by the Planning agent above.

[0161] In this way, the Assemble agent executes the target task based on the parameters in the received second information and obtains the result of executing the target task.

[0162] For example, after the target task of the above-mentioned function matching is completed, function configuration and linking are required. Therefore, the Assemble agent will send the result of executing the target task (i.e., the function matching result) and the next steps (function configuration and linking) to the ACP. The ACP selects the next agent for the next role based on the next steps (such as repeating the execution). Figure 3In the illustrated embodiment (steps 301-303), the ACP considers the service complete (i.e., all four sub-tasks have been completed) until it receives a message from a network element (such as an agent) containing "none" as the next action. Then, the ACP returns the final execution result to the Planning agent.

[0163] This completes the user's business request.

[0164] In this example, ACP obtains the target task by understanding the first information, selects a suitable agent to handle the task based on the target task, generates the input message required by the agent, and sends it to the agent.

[0165] Example 2

[0166] Combination Figure 5 As shown, this example illustrates a scenario where a Connection agent needs to query base station information. Figure 5 As shown, the communication method includes steps 501-505, as detailed below:

[0167] 501. The Connection agent sends the first message to the ACP, which includes the following third parameter and first parameter:

[0168] The third parameter includes: (1) Agent ID: CA121, where CA represents Connectionagent. (2) Service ID: 301. (3) Connection agent's task execution information: Configure sensing task, sensing location coordinates are (10, 54). (4) Input parameters corresponding to the target task: No sensing base station information.

[0169] The first parameter (i.e. the target task): Obtain base station information near coordinates (10,54).

[0170] 502. ACP determines the public memory to be queried based on the first parameter in the first information.

[0171] In one possible implementation, ACP generates a base station query request (i.e., the second information) based on the first parameter and the task execution information of Connectionagent in the third parameter.

[0172] 503. ACP sends the second message to the selected public memory.

[0173] For example, the second information includes a second parameter, which includes query parameters such as location (around coordinates (10,54)) and capability requirements (such as having perception capabilities).

[0174] 504. Public memory returns the queried base station information (fifth information) to ACP.

[0175] For example, the fifth piece of information includes the results of performing the above query task, such as information such as base station ID, location, and capabilities.

[0176] 505. ACP sends the sixth message to the Connection agent.

[0177] For example, the sixth piece of information includes the following parameters:

[0178] (1) Service identifier: 301. (2) Service description information: Configure sensing task, sensing location coordinates are (10, 54). It can be understood that the service description information can be the task execution information of the Connection agent. (3) Result of executing the above query task: Queryed base station information, including base station ID, location, and capabilities.

[0179] This completes the task of querying base station information.

[0180] In this example, ACP obtains the target task by understanding the first information, selects the appropriate component to process the task based on the target task, generates the input message required by the component, and encapsulates the information content output by the component into a message and returns it to the corresponding agent.

[0181] Example 3

[0182] Combination Figure 6 As shown, this example illustrates a scenario where an agent requests NetGPT for collaborative inference. The execution agent is responsible for deploying functional instances to execute tasks. Because the execution agent's local model inference accuracy is limited, it initiates auxiliary inference requests to improve the accuracy of the deployment scheme. For example... Figure 6 As shown, the communication method includes steps 601-606, as detailed below:

[0183] 601. The execution agent sends the first message to the ACP, which includes the following third parameter and first parameter:

[0184] The third parameter includes: (1) Agent identifier: EA214, where EA stands for execution agent. (2) Service identifier: 301. (3) Connection agent's task execution information: deployment task function, task description, and function description. (4) Input parameters corresponding to the target task: local model output results.

[0185] The first parameter (i.e. the target task): the deployment plan for the auxiliary reasoning function and the required resources.

[0186] 602. ACP obtains cloud platform resource information from public memory.

[0187] 603. ACP determines that NetGPT will perform auxiliary reasoning based on the first parameter, and generates the prompt required by NetGPT by combining the existing information.

[0188] For example, the existing information includes the inference task to be performed (obtained by parsing the first parameter), the current inference result (obtained by parsing the input parameters corresponding to the target task in the third parameter), and cloud platform resource information obtained from public memory, etc.

[0189] 604. ACP sends the generated prompt (i.e., the second message) to NetGPT.

[0190] For example, the prompt includes information such as task description (i.e., the target task mentioned above), input parameters (i.e., the input parameters corresponding to the target task mentioned above), cloud platform resources, and output format requirements.

[0191] 605. NetGPT returns the expected inference result (i.e., the fifth piece of information).

[0192] For example, the expected inference result includes a feature deployment scheme.

[0193] 606. ACP sends the sixth message to the execution agent.

[0194] For example, the sixth piece of information includes: (1) the identifier of the service: 301. (2) the description information of the service: deployment task function, task and function description. (3) the result of performing the above task: deployment plan (function, deployment location, resources), etc.

[0195] This completes the task of NetGPT for collaborative reasoning.

[0196] In this example, ACP obtains the target task by understanding the first information, selects an appropriate component to process the task based on the target task, generates the input messages required by the component, and encapsulates the information content output by the component into a message and returns it to the corresponding agent.

[0197] It should be noted that, in the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between the various 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.

[0198] The methods of the embodiments of this application have been described in detail above, and the apparatus of the embodiments of this application is provided below. It is understood that the division of multiple units or modules in the various apparatus embodiments of this application is only a logical division based on function and is not intended to limit the specific structure of the apparatus. In specific implementations, some functional modules may be subdivided into more smaller functional modules, and some functional modules may be combined into a single functional module. However, regardless of whether these functional modules are subdivided or combined, the general flow executed by the apparatus is the same. For example, some apparatuses include a receiving unit and a transmitting unit. In some designs, the transmitting unit and the receiving unit can also be integrated into a communication unit, which can implement the functions implemented by the receiving unit and the transmitting unit. Typically, each unit corresponds to its own program code (or program instructions). When the program code corresponding to each unit runs on the processor, it causes the unit to be controlled by the processing unit to execute the corresponding flow and thus achieve the corresponding function.

[0199] This application also provides an apparatus for implementing any of the above methods. For example, a communication apparatus is provided that includes a module (or means) for implementing the steps performed by ACP in any of the above methods.

[0200] For example, refer to Figure 7 The diagram shown is a structural schematic of a communication device provided in an embodiment of this application. This communication device is used to implement the aforementioned communication method, for example... Figures 3 to 6 The communication method shown.

[0201] like Figure 7 As shown, the device may include a communication module 701 and a processing module 702, as detailed below:

[0202] Communication module 701 is used to receive first information, the first information including first parameters;

[0203] Processing module 702 is used to parse the first parameter to obtain the first task;

[0204] The processing module 702 is also used to obtain the target network element based on the first task;

[0205] The communication module 701 is also used to send second information, the second information including a second parameter, the second parameter being generated based on the first parameter, or the second parameter including the first parameter, the second information being used to instruct the target network element to perform the first task based on the second parameter.

[0206] In one possible implementation, the processing module 702 is further configured to:

[0207] Based on the first task and the capability and / or location information of multiple network elements, the target network element is determined from these multiple network elements.

[0208] In one possible implementation, the first information further includes a third parameter, which includes at least one of the following:

[0209] The identifier of the first network element, the task execution information of the first network element, the input parameters corresponding to the first task, the identifier of the service, the service being related to the first task, and the first network element being the network element that sends the first information.

[0210] In one possible implementation, the third parameter is the input parameter corresponding to the first task, and the processing module 702 is further configured to:

[0211] The third parameter is parsed to obtain the fourth parameter, which indicates the input parameter corresponding to the first task;

[0212] Based on the first task, the fourth parameter, and the capability information and / or location information of multiple network elements, the target network element is determined from the multiple network elements.

[0213] In one possible implementation, the third parameter includes the task execution information of the first network element, and the second parameter is generated based on the first parameter and the task execution information of the first network element.

[0214] In one possible implementation, the communication module 701 is further used for:

[0215] Send a third message, the third message including the first task, the third message being used to instruct the second network element to determine the network element for performing the first task;

[0216] Receive the fourth information, which indicates the target network element.

[0217] In one possible implementation, the communication module 701 is further used for:

[0218] Receive the fifth information, which includes the result of the target network element performing the first task.

[0219] In one possible implementation, the communication module 701 is further used for:

[0220] Send a sixth message, which includes the identifier of the service, the first task, and the result of the target network element performing the first task, and the service is related to the first task.

[0221] For a description of each of the above modules, please refer to the description in the foregoing embodiments, which will not be repeated here.

[0222] For example, embodiments of this application also provide an apparatus for implementing any of the above methods. For instance, a communication apparatus is provided that includes a module (or means) for implementing the steps performed by the first network element in any of the above methods.

[0223] For example, refer to Figure 8 The diagram shown is a structural schematic of a communication device provided in an embodiment of this application. This communication device is used to implement the aforementioned communication method, for example... Figures 3 to 6 The communication method shown.

[0224] like Figure 8 As shown, the device may include a communication module 801, as detailed below:

[0225] The communication module 801 is used to send first information, the first information including a first parameter, the first information being used to indicate the network element to be used to perform a first task, the first task being associated with the first parameter.

[0226] In one possible implementation, the communication module 801 is further used for:

[0227] The sixth information is received, which includes the identifier of the service, the first task, and the result of the target network element performing the first task, and the service is related to the first task.

[0228] In one possible implementation, the first information further includes a third parameter, which includes at least one of the following:

[0229] The identifier of the first network element, the task execution information of the first network element, the input parameters corresponding to the first task, the identifier of the service, the service being related to the first task, and the first network element being the network element that sends the first information.

[0230] For a description of each of the above modules, please refer to the description in the foregoing embodiments, which will not be repeated here.

[0231] This application also provides an apparatus for implementing any of the above methods. For example, a communication apparatus is provided that includes a module (or means) for implementing the steps performed by the target network element in any of the above methods.

[0232] For example, refer to Figure 8The diagram shown is a structural schematic of a communication device provided in an embodiment of this application. This communication device is used to implement the aforementioned communication method, for example... Figures 3 to 6 The communication method shown.

[0233] like Figure 8 As shown, the device may include a communication module 801, as detailed below:

[0234] The communication module 801 is used to receive second information, the second information including a second parameter, the second parameter being generated based on a first parameter, or the second parameter including the first parameter, the second information being used to instruct a target network element to perform a first task based on the second parameter, the first task being related to the first parameter;

[0235] The communication module 801 is also used to send fifth information, which includes the result of the target network element performing the first task.

[0236] In one possible implementation, the second parameter is generated based on the first parameter and the task execution information of the first network element, where the first network element is the network element that sends the first information, and the first information includes the first parameter and the task execution information of the first network element.

[0237] For a description of each of the above modules, please refer to the description in the foregoing embodiments, which will not be repeated here.

[0238] It should be understood that the division of modules in the above devices is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, modules in a communication device can be implemented by a processor calling software; for example, a communication device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of each module in the device. The processor can be, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the modules in the device can be implemented as hardware circuits. The functionality of some or all units can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC), and the functionality of some or all of the above units is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD), such as a field-programmable gate array (FPGA), which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the above units. All modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0239] Reference Figure 9 The diagram shown is a hardware structure schematic of another communication device provided in an embodiment of this application. Figure 9 The communication device 900 shown includes one or more processors 901 (one processor is shown in the figure).

[0240] Processor 901 is a circuit with signal processing capabilities. In one implementation, processor 901 can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, processor 901 can achieve certain functions through the logical relationships of hardware circuits. These logical relationships of hardware circuits are fixed or reconfigurable. For example, processor 901 can be a hardware circuit implemented as an ASIC or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the processor loading instructions to achieve the functions of some or all of the above modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as a type of ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), or deep learning processing unit (DPU). The processor 901 is used to execute related programs to implement the functions required by the units in the communication device of the present application embodiment, or to execute the communication method of the method embodiment of the present application.

[0241] Optionally, the communication device 900 may also include a memory (e.g., memory 903, memory 904, memory 905) (shown as dashed lines in the figure). This memory is used to store instructions executed by the processor 901, or to store input data required for the processor 901 to execute instructions, or to store data generated after the processor 901 executes instructions.

[0242] Optionally, the memory may be located within the one or more processors (e.g., memory 903), or outside the one or more processors (e.g., memory 904, memory 905), or may include a storage portion located within the one or more processors and a storage portion located outside the one or more processors.

[0243] In this embodiment, the memory (e.g., memory 903, memory 904, memory 905) may include, but is not limited to, cache, read-only memory (ROM), random access memory (RAM), synchronous dynamic random access memory (SDRAM), hard disk drive (HDD) or solid-state drive (SSD), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), etc. Memory is any other medium capable of carrying or storing desired program code having an instruction or data structure form and accessible by a computer, but is not limited thereto. The memory in this embodiment may also be a circuit or any other device capable of implementing storage functions for storing computer programs or instructions, and / or data.

[0244] Optionally, the communication device 900 may also include a communication interface 902 (shown as a dashed line in the figure). The processor 901 and the communication interface 902 are coupled together. The communication interface 902 can be a transceiver or interface circuit, a bus, a module, or other type of communication interface.

[0245] The memory can store programs. When the program stored in the memory is executed by the processor 901, the processor 901 and the communication interface 902 are used to execute the various steps of the communication method of the embodiments of this application.

[0246] As can be seen, each module in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms or a portion of the processing circuits in these processors.

[0247] Furthermore, the modules in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these modules are integrated together as a system-on-a-chip (SOC). The SOC may include at least one processor for implementing any of the above methods or for implementing the functions of the modules of the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.

[0248] It should be noted that, although Figure 9 The illustrated device 900 only shows the memory, processor, and communication interface. However, those skilled in the art should understand that in specific implementations, device 900 may also include other devices necessary for normal operation. Furthermore, depending on specific needs, those skilled in the art should understand that device 900 may also include hardware devices for implementing other additional functions. Moreover, those skilled in the art should understand that device 900 may only include the devices necessary for implementing the embodiments of this application, and may not necessarily include... Figure 9 All the devices shown.

[0249] This application also provides a computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform one or more steps of any of the above methods.

[0250] This application also provides a computer program product containing instructions. When the computer program product is run on a computer or processor, it causes the computer or processor to perform one or more steps of any of the methods described above.

[0251] It is understood that in this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information to indicate A, it can be understood that the instruction information carries A, directly indicates A, or indirectly indicates A. In this application, the information indicated by the instruction information is called the information to be instructed. In specific implementation, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index, or indirectly indicating the information to be instructed by indicating other information, wherein there is an association between the other information and the information to be instructed. It is also possible to indicate only a part of the information to be instructed, while the other parts of the information to be instructed are known or agreed upon in advance. For example, the instruction of specific information can also be achieved by using the arrangement order of various information in advance (e.g., as specified by a protocol), thereby reducing the instruction overhead to a certain extent. The information to be instructed can be sent as a whole or divided into multiple sub-information to be sent separately, and the sending period and / or sending time of these sub-information can be the same or different. This application does not limit the specific sending method. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the transmitting device by sending configuration information to the receiving device.

[0252] It should be understood that in the description of this application, unless otherwise stated, " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B can represent A or B; where A and B can be singular or plural. Furthermore, in the description of this application, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" do not necessarily imply difference. In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0253] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the division of units is merely a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. The coupling, direct coupling, or communication connection shown or discussed between each other may be indirect coupling or communication connection through some interfaces, apparatuses, or units, and may be electrical, mechanical, or other forms.

[0254] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0255] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. 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 accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be read-only memory (ROM), random access memory (RAM), or magnetic media, such as floppy disks, hard disks, magnetic tapes, magnetic disks, or optical media, such as digital versatile discs (DVDs), or semiconductor media, such as solid state disks (SSDs).

[0256] The above description is merely a specific implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the embodiments of this application should be covered within the protection scope of the embodiments of this application. Therefore, the protection scope of the embodiments of this application should be determined by the protection scope of the claims.

Claims

1. A communication method, characterized in that, The method includes: Receive first information, the first information including first parameters; The first parameter is parsed to obtain the first task; Obtain the target network element based on the first task; Send a second message, the second message including a second parameter, the second parameter being generated based on the first parameter, or the second parameter including the first parameter, the second message being used to instruct the target network element to perform the first task based on the second parameter.

2. The method according to claim 1, characterized in that, The step of obtaining the target network element based on the first task includes: Based on the first task and the capability information and / or location information of multiple network elements, the target network element is determined from the multiple network elements.

3. The method according to claim 1 or 2, characterized in that, The first information also includes a third parameter, which includes at least one of the following: The first network element is identified by its identifier, the first network element's task execution information, the input parameters corresponding to the first task, and the service identifier. The service is related to the first task, and the first network element is the network element that sends the first information.

4. The method according to claim 3, characterized in that, The third parameter is the input parameter corresponding to the first task, and the method further includes: The third parameter is parsed to obtain the fourth parameter, which indicates the input parameter corresponding to the first task; The step of obtaining the target network element based on the first task includes: Based on the first task, the fourth parameter, and the capability information and / or location information of multiple network elements, the target network element is determined from the multiple network elements.

5. The method according to claim 3, characterized in that, The third parameter includes the task execution information of the first network element, and the second parameter is generated based on the first parameter and the task execution information of the first network element.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Send a third message, the third message including the first task, the third message being used to instruct the second network element to determine the network element for executing the first task; Receive fourth information, which indicates the target network element.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Receive fifth information, the fifth information including the result of the target network element performing the first task.

8. The method according to claim 7, characterized in that, The method further includes: Send a sixth message, which includes the identifier of the service, the first task, and the result of the target network element executing the first task, wherein the service is related to the first task.

9. A communication method, characterized in that, The method includes: Send first information, the first information including a first parameter, the first information being used to indicate the determination of a network element for performing a first task, the first task being associated with the first parameter.

10. The method according to claim 9, characterized in that, The method further includes: The sixth information is received, which includes the identifier of the service, the first task, and the result of the target network element performing the first task, wherein the service is related to the first task.

11. The method according to claim 9 or 10, characterized in that, The first information also includes a third parameter, which includes at least one of the following: The first network element is identified by its identifier, the first network element's task execution information, the input parameters corresponding to the first task, and the service identifier. The service is related to the first task, and the first network element is the network element that sends the first information.

12. A communication method, characterized in that, The method includes: Receive second information, the second information including a second parameter, the second parameter being generated based on a first parameter, or the second parameter including the first parameter, the second information being used to instruct the target network element to perform a first task based on the second parameter, the first task being related to the first parameter; Send a fifth message, which includes the result of the target network element performing the first task.

13. The method according to claim 12, characterized in that, The second parameter is generated based on the first parameter and the task execution information of the first network element. The first network element is the network element that sends the first information, and the first information includes the first parameter and the task execution information of the first network element.

14. A communication device, characterized in that, The device includes: A communication module is configured to receive first information, the first information including first parameters; The processing module is used to parse the first parameter to obtain the first task; The processing module is further configured to obtain the target network element based on the first task; The communication module is further configured to send second information, the second information including a second parameter, the second parameter being generated based on the first parameter, or the second parameter including the first parameter, the second information being used to instruct the target network element to perform the first task based on the second parameter.

15. The apparatus according to claim 14, characterized in that, The processing module is further configured to: Based on the first task and the capability information and / or location information of multiple network elements, the target network element is determined from the multiple network elements.

16. The apparatus according to claim 14 or 15, characterized in that, The first information also includes a third parameter, which includes at least one of the following: The first network element is identified by its identifier, the first network element's task execution information, the input parameters corresponding to the first task, and the service identifier. The service is related to the first task, and the first network element is the network element that sends the first information.

17. The apparatus according to claim 16, characterized in that, The third parameter is the input parameter corresponding to the first task, and the processing module is further configured to: The third parameter is parsed to obtain the fourth parameter, which indicates the input parameter corresponding to the first task; Based on the first task, the fourth parameter, and the capability information and / or location information of multiple network elements, the target network element is determined from the multiple network elements.

18. The apparatus according to claim 16, characterized in that, The third parameter includes the task execution information of the first network element, and the second parameter is generated based on the first parameter and the task execution information of the first network element.

19. The apparatus according to any one of claims 14 to 18, characterized in that, The communication module is also used for: Send a third message, the third message including the first task, the third message being used to instruct the second network element to determine the network element for executing the first task; Receive fourth information, which indicates the target network element.

20. The apparatus according to any one of claims 14 to 19, characterized in that, The communication module is also used for: Receive fifth information, the fifth information including the result of the target network element performing the first task.

21. The apparatus according to claim 20, characterized in that, The communication module is also used for: Send a sixth message, which includes the identifier of the service, the first task, and the result of the target network element executing the first task, wherein the service is related to the first task.

22. A communication device, characterized in that, The device includes: A communication module is used to send first information, the first information including first parameters, the first information being used to indicate the network element to perform a first task, and the first task being associated with the first parameters.

23. The apparatus according to claim 22, characterized in that, The communication module is also used for: The sixth information is received, which includes the identifier of the service, the first task, and the result of the target network element performing the first task, wherein the service is related to the first task.

24. The apparatus according to claim 22 or 23, characterized in that, The first information also includes a third parameter, which includes at least one of the following: The first network element is identified by its identifier, the first network element's task execution information, the input parameters corresponding to the first task, and the service identifier. The service is related to the first task, and the first network element is the network element that sends the first information.

25. A communication device, characterized in that, The device includes: A communication module is used to receive second information, the second information including a second parameter, the second parameter being generated based on a first parameter, or the second parameter including the first parameter, the second information being used to instruct a target network element to perform a first task based on the second parameter, the first task being related to the first parameter; The communication module is also used to send fifth information, which includes the result of the target network element performing the first task.

26. The apparatus according to claim 25, characterized in that, The second parameter is generated based on the first parameter and the task execution information of the first network element. The first network element is the network element that sends the first information, and the first information includes the first parameter and the task execution information of the first network element.

27. A communication device, characterized in that, The device includes a processor configured to perform the method as described in any one of claims 1-13 by executing a computer program or computer-executable instructions stored in a memory, and / or by logic circuitry.

28. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-13.

29. A computer program product, characterized in that, The computer program product includes relevant program instructions, which, when executed, implement the method as described in any one of claims 1-13.

Images